spostato appunti neuron
This commit is contained in:
@@ -0,0 +1,873 @@
|
||||
## Neural Component Model Specifications
|
||||
|
||||
### 1. Presynapse (Transmitter Release Unit)
|
||||
|
||||
**Internal State Variables:**
|
||||
|
||||
- `V_m`: Membrane potential
|
||||
- `P_r`: Release probability (dynamic, 0.0-1.0)
|
||||
- `[Ca²⁺]_i`: Intracellular Ca²⁺ concentration
|
||||
- `vesicle_pool`: Available vesicles
|
||||
- `residual_Ca²⁺`: Facilitation buffer
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- **Electrical:** AP from axon (spike train)
|
||||
- **Chemical:**
|
||||
- eCB (→ ↓ `P_r` via CB1)
|
||||
- NO/BDNF (→ ↑ `P_r` via cGMP/TrkB)
|
||||
- Astrocyte gliotransmitters (modulatory)
|
||||
- **Metabolic:** Lactate (energy), glutamine (precursor)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- **Primary:** Glutamate quantal release (packet size ∝ `P_r` × `vesicle_pool`)
|
||||
- **Spillover:** Ambient glutamate affecting astrocyte/volume transmission
|
||||
|
||||
**Modulation Gates:**
|
||||
|
||||
- **Short-term:** Residual Ca²⁺ → ↑ `P_r` (facilitation)
|
||||
- **Long-term:** eCB/NO/BDNF retrograde signals modify baseline `P_r`
|
||||
- **Homeostatic:** Vesicle pool depletion → ↓ release (depression)
|
||||
|
||||
**Update Rules:**
|
||||
|
||||
- AP arrival → VGCC opening → `[Ca²⁺]_i` spike → vesicle fusion probability = `P_r`
|
||||
- `P_r` = baseline × STF_factor × LTD/LTP_factor × homeostatic_factor
|
||||
- Vesicle recycling with time constant τ\_recycle (seconds)
|
||||
|
||||
### Complete Model
|
||||
|
||||
#### 1. Short-Term Facilitation (STF)
|
||||
|
||||
- **Mechanism:** Activity-dependent **increase in release probability (P<sub>r</sub>)** due to accumulation of `residual_Ca²⁺` in the active zone.
|
||||
- **Model Implementation:**
|
||||
- `residual_Ca²⁺` is a state variable that acts as a short-term memory buffer.
|
||||
- Each presynaptic spike injects a fixed amount of Ca²⁺ into `[Ca²⁺]_i`, which then decays exponentially with a fast time constant (τ\_Ca_fast \~ 10-50 ms). A fraction of this is added to `residual_Ca²⁺`, which decays with a slower time constant (τ\_Ca_slow \~ 100-500 ms).
|
||||
- The **STF_factor** = `1 + F_max * (residual_Ca²⁺ / (K_d + residual_Ca²⁺))`
|
||||
- Where `F_max` is the maximum facilitation strength and `K_d` is the half-saturation constant.
|
||||
- **Effect:** High-frequency spike trains cause `residual_Ca²⁺` to summate, progressively increasing the `STF_factor` and therefore `P_r` for subsequent spikes.
|
||||
|
||||
#### 2. Short-Term Depression (STD)
|
||||
|
||||
- **Mechanism:** Activity-dependent **decrease in release** due to depletion of the readily `releasable vesicle_pool`.
|
||||
- **Model Implementation:**
|
||||
- Each successful release event (a stochastic outcome with probability `P_r`) reduces the `vesicle_pool` by one quantum.
|
||||
- Vesicles are replenished from a reserve pool with a **recovery time constant τ\_recycle** (e.g., 0.5 - 10 seconds).
|
||||
- The **homeostatic_factor** (or depletion factor) is simply the fraction of the pool that is available: `vesicle_pool / vesicle_pool_max`.
|
||||
- **Effect:** High-frequency firing depletes the pool faster than τ\_recycle can refill it. The `homeostatic_factor` drops, decreasing the *effective* release rate (`P_r * vesicle_pool`), even if `P_r` itself is high.
|
||||
|
||||
#### 3. Long-Term Modulation (LTP/LTD of Release)
|
||||
|
||||
- **Mechanism:** Retrograde chemical signals (**eCB, NO, BDNF**) induce biochemical cascades that **modify the baseline** `P_r` on timescales of minutes to hours.
|
||||
- **Model Implementation:**
|
||||
- These are triggered by specific postsynaptic activity patterns (e.g., postsynaptic Ca²⁺ spikes for eCB, strong depolarization for NO).
|
||||
- They act as **scaling factors on the baseline** `P_r`:
|
||||
- **eCB (via CB1R):** `LTD_factor = α_ECB` (where α\_ECB < 1, e.g., 0.7).
|
||||
- **NO/BDNF (via cGMP/TrkB):** `LTP_factor = β_NO` (where β\_NO > 1, e.g., 1.5).
|
||||
- The **LTD/LTP_factor** in your update rule is the product of these active factors (e.g., `α_ECB * β_NO`).
|
||||
- **Effect:** These factors change slowly, providing a sustained, experience-dependent up- or down-regulation of synaptic strength.
|
||||
|
||||
#### 4. Neuromodulator & Astrocyte Gates
|
||||
|
||||
- **Mechanism:** Diffuse signals (**lactate, glutamine, astrocyte gliotransmitters**) modulate the synapse's metabolic state and precursor availability.
|
||||
- **Model Implementation:**
|
||||
- These are often modeled as **modifiers of parameters**, not direct state changes.
|
||||
- **Lactate (energy):** Influences `τ_recycle` and pump activity (Ca²⁺ clearance). Low lactate → slower τ\_recycle → accentuates STD.
|
||||
- **Glutamine (precursor):** Limits the total `vesicle_pool_max`. Low glutamine → smaller pool → faster depletion.
|
||||
- **Astrocyte signals (e.g., D-serine, ATP):** Can act as a multiplicative **gate** on the `STF_factor` or directly on the `baseline P_r`.
|
||||
|
||||
#### Integrated Update Rule Synthesis
|
||||
|
||||
Putting it all together, the release probability for a given vesicle upon AP arrival at time \*t\* becomes:
|
||||
|
||||
**P_r(t) = baseline_P_r × STF_factor(t) × LTD/LTP_factor × homeostatic_factor(t)**
|
||||
|
||||
Where:
|
||||
|
||||
- `STF_factor(t) = 1 + F_max * ( rCa(t) / (K_d + rCa(t)) )` **(Dynamic; updates per spike)**
|
||||
- `rCa(t)` is the `residual_Ca²⁺` buffer, driven by `[Ca²⁺]_i` spikes.
|
||||
- `LTD/LTP_factor = α_ECB * β_NO * ...` **(Quasi-static; changes on long timescales)**
|
||||
- `homeostatic_factor(t) = vesicle_pool(t) / vesicle_pool_max` **(Dynamic; updates per release event)**
|
||||
|
||||
**Final Release Decision:** A random number is drawn. If it is `< P_r(t)`, a vesicle fuses, `vesicle_pool` is decremented, and glutamate is released. The `vesicle_pool` then recovers toward its maximum with the time constant `τ_recycle`.
|
||||
|
||||
This model captures the core **tension between facilitation (driven by Ca²⁺) and depression (driven by depletion)**, while allowing for slower, homeostatic and Hebbian adjustments, making it a powerful framework for simulating synaptic dynamics.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
### **2. Postsynapse (Spine - Integration & Plasticity Unit)**
|
||||
|
||||
**Internal State Variables:**
|
||||
|
||||
- `V_m`: Local membrane potential
|
||||
- `N_AMPA`: AMPA receptor count
|
||||
- `N_NMDA`: NMDA receptor count
|
||||
- `[Ca²⁺]_i`: Intracellular Ca²⁺
|
||||
- `plasticity_tag`: Binary flag for eligibility
|
||||
- `spine_volume`: Structural size
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- **Chemical:** Glutamate from presynapse
|
||||
- **Electrical:** Dendritic voltage (for NMDA unblocking)
|
||||
- **Backpropagating:** bAP from soma (timing signal)
|
||||
- **Modulatory:** D-serine (astrocyte), neuromodulators
|
||||
- **Structural:** BDNF, actin regulators
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- **Primary:** EPSP current = `g_AMPA` × `(V_m - E_Na)` + `g_NMDA` × `(V_m - E_Ca)`
|
||||
- **Retrograde:** eCB/NO/BDNF synthesis when `[Ca²⁺]_i` exceeds thresholds
|
||||
- **Local:** Ca²⁺ signals to dendrite for spike initiation
|
||||
|
||||
**Modulation Gates:**
|
||||
|
||||
- **Voltage:** Mg²⁺ block on NMDA (relieved at depolarization)
|
||||
- **Metabotropic:** mGluR → second messengers → receptor trafficking
|
||||
- **Structural:** Actin polymerization ↔ spine growth/shrinkage
|
||||
|
||||
**Plasticity Rules:**
|
||||
|
||||
- **LTP:** `ΔN_AMPA` ∝ `[Ca²⁺]_i`^2 × `plasticity_tag` × kinase_activity
|
||||
- **LTD:** `ΔN_AMPA` ∝ moderate `[Ca²⁺]_i` × phosphatase_activity
|
||||
- **Scaling:** Global adjustment of all `N_AMPA` based on soma firing rate
|
||||
|
||||
### Complete Model
|
||||
|
||||
#### 1. Voltage-Dependent Gate (NMDA Receptor)
|
||||
|
||||
- **Mechanism:** The `NMDA_conductance` (`g_NMDA`) is not constant. It is *gated* by both glutamate binding and the relief of a voltage-dependent Mg²⁺ block.
|
||||
- **Model Implementation (Instantaneous):**
|
||||
- `g_NMDA(t) = N_NMDA * γ * B(V_m(t))`
|
||||
- Where `γ` is the single-channel conductance, and `B(V_m)` is the magnesium unblock fraction.
|
||||
- `B(V_m) = 1 / (1 + η * [Mg²⁺] * exp(-ζ * V_m(t)))`
|
||||
- **Effect:** This function ensures NMDA receptors are only significant **coincidence detectors**. They pass current only when presynaptic glutamate release (`N_NMDA` is bound) AND postsynaptic depolarization (from `V_m` or bAP) occurs simultaneously.
|
||||
|
||||
#### 2. Biochemical Integration & Plasticity Triggers
|
||||
|
||||
- **Core Signal:** The key trigger for all plasticity is the postsynaptic **calcium transient** `[Ca²⁺]_i(t)`, which integrates multiple sources:
|
||||
- `[Ca²⁺]_i(t) = J_NMDA(t) + J_VGCC(t) + J_IP3(t)`
|
||||
- Where `J_NMDA` is Ca²⁺ influx through NMDA receptors, `J_VGCC` is from voltage-gated channels opened by bAPs, and `J_IP3` is from mGluR/second-messenger pathways.
|
||||
- **LTP/LTD Decision Rule (Classic BCM-like Rule):**
|
||||
- A `plasticity_tag` is set to `1` if `[Ca²⁺]_i` crosses a moderate threshold (`θ_tag`) within a short time window (\~100ms). This marks the spine as "eligible."
|
||||
- The final change in `N_AMPA` is then determined by the peak/amplitude of the calcium signal:
|
||||
- **LTP:** If peak `[Ca²⁺]_i > θ_LTP` (a high threshold), then `ΔN_AMPA = +A_LTP * plasticity_tag`. This typically requires **strong, coincident** presynaptic glutamate AND a bAP.
|
||||
- **LTD:** If `θ_LTD < peak [Ca²⁺]_i < θ_LTP` (a moderate, sustained level), then `ΔN_AMPA = -A_LTD`. This can be triggered by presynaptic activity alone or weak pairing.
|
||||
- The **kinase_activity** and **phosphatase_activity** in your rule are functions of `[Ca²⁺]_i` (e.g., `kinase ∝ ([Ca²⁺]_i - θ_LTP)^2` for LTP).
|
||||
|
||||
#### 3. Retrograde Signal Synthesis
|
||||
|
||||
- **Mechanism:** The postsynaptic spine functions as a **signal interpreter and broadcaster**. Based on the calcium signal, it synthesizes specific retrograde messengers.
|
||||
- **Model Implementation (Threshold Logic):**
|
||||
- **eCB synthesis:** Triggered if `[Ca²⁺]_i > θ_eCB`. eCB is then released, diffusing back to inhibit the presynaptic terminal (lowering `baseline P_r` via your presynaptic `LTD_factor`). This is often a form of heterosynaptic LTD.
|
||||
- **NO synthesis:** Triggered by a similar high `[Ca²⁺]_i` threshold coupled with activation of specific enzymes (e.g., nNOS). NO diffuses to the presynapse to increase `P_r` (your `LTP_factor`).
|
||||
- **BDNF synthesis:** Slower, triggered by sustained calcium signals or specific gene activation pathways. BDNF acts both presynaptically and postsynaptically to promote structural changes.
|
||||
|
||||
#### 4. Structural & Metaplastic Modulation
|
||||
|
||||
- **Metabotropic (mGluR) Pathway:** Activated by sustained or spillover glutamate. It doesn't directly cause plasticity but **modulates the plasticity thresholds** (`θ_LTP`, `θ_LTD`). For example, mGluR activation can lower `θ_LTD`, making LTD easier to induce (metaplasticity).
|
||||
- **Spine Volume (**`spine_volume`**):** This is a slow variable that couples to receptor counts.
|
||||
- `spine_volume(t+Δt) = spine_volume(t) + τ_vol * (N_AMPA(t) - κ * spine_volume(t))`
|
||||
- **Growth:** A sustained increase in `N_AMPA` (from LTP) promotes actin polymerization, increasing `spine_volume`.
|
||||
- **Shrinkage/Stabilization:** Conversely, a large, stable `spine_volume` creates slots for more `N_AMPA`, stabilizing the potentiation. This creates a positive feedback loop for strong, stable synapses.
|
||||
|
||||
#### 5. Homeostatic Scaling
|
||||
|
||||
- **Mechanism:** A global, cell-wide feedback mechanism to maintain the soma's average firing rate within a target range.
|
||||
- **Model Implementation (Multiplicative):**
|
||||
- Periodically (e.g., every few hours of simulation time), the soma calculates its average firing rate `r_avg`.
|
||||
- If `r_avg` deviates from a target `r_target`, all `N_AMPA` on all synapses are scaled uniformly:
|
||||
- If `r_avg < r_target`: `N_AMPA = N_AMPA * β_up` (where `β_up > 1`). This is **up-scaling**.
|
||||
- If `r_avg > r_target`: `N_AMPA = N_AMPA * β_down` (where `β_down < 1`). This is **down-scaling**.
|
||||
- This rule is applied **independently** of the Hebbian `plasticity_tag`. It ensures network stability.
|
||||
|
||||
#### Integrated Synaptic Current & Update Cycle
|
||||
|
||||
The **EPSP current** driving the local `V_m` is:
|
||||
`I_syn(t) = (N_AMPA * g_unit_AMPA * B_AMPA(t)) * (V_m(t) - E_Na) + (g_NMDA(t)) * (V_m(t) - E_Ca)`
|
||||
|
||||
Where `B_AMPA(t)` is the fraction of AMPARs bound by glutamate (a transient pulse upon release).
|
||||
|
||||
**Simulation Cycle for a Spine:**
|
||||
|
||||
1. **Input:** Glutamate binds. bAP may arrive.
|
||||
2. **Integration:** `V_m` depolarizes locally. Mg²⁺ block is relieved → `g_NMDA(t)` computed.
|
||||
3. **Calcium:** `[Ca²⁺]_i(t)` is calculated from all sources.
|
||||
4. **Decision:**
|
||||
- Set `plasticity_tag`.
|
||||
- Compute instantaneous `ΔN_AMPA` via the LTP/LTD calcium rule.
|
||||
- Trigger retrograde signal synthesis if thresholds crossed.
|
||||
5. **Update:** Apply `ΔN_AMPA`. Slowly update `spine_volume`. Periodically apply global scaling.
|
||||
|
||||
This model captures the spine as a **coincidence detector, integrator, biochemical decoder, and structural adaptor**—a fundamental unit of learning and memory.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
### **3. Dendrite (Branch - Pattern Detector)**
|
||||
|
||||
**Internal State Variables:**
|
||||
|
||||
- `V_m(z)`: Space-dependent membrane potential
|
||||
- `[Ca²⁺]_i(z)`: Local Ca²⁺ concentration
|
||||
- `NaV_density(z)`: Sodium channel distribution
|
||||
- `VGCC_density(z)`: Calcium channel distribution
|
||||
- `branch_excitability`: Global gain factor
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- **Local:** EPSPs from spines (summed spatially/temporally)
|
||||
- **Global:** bAP from soma (teaching signal)
|
||||
- **Modulatory:** Dopamine, acetylcholine (branch-specific)
|
||||
- **Inhibitory:** GABA from interneurons
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- **Active:** Dendritic spikes (Na⁺/Ca²⁺/NMDA) to soma
|
||||
- **Passive:** Integrated voltage to soma
|
||||
- **Local:** Retrograde signals to spines
|
||||
|
||||
**Integration Algorithm:**
|
||||
|
||||
```
|
||||
if (sum(EPSPs) > threshold_local && bAP_within_window):
|
||||
generate_dendritic_spike()
|
||||
update_synaptic_tags(spikes_nearby)
|
||||
else:
|
||||
passive_spread_to_soma()
|
||||
```
|
||||
|
||||
**Branch-Specific Computation:**
|
||||
|
||||
- **Coincidence detection:** EPSP × bAP timing → STDP
|
||||
- **Pattern separation:** Different branches learn different input combinations
|
||||
- **Signal amplification:** Local spikes overcome cable attenuation
|
||||
|
||||
### Complete Model
|
||||
|
||||
#### 1. Integration Algorithm & Spike Generation
|
||||
|
||||
The decision logic can be formalized as a **multi-mechanism spike detector**:
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
function compute_branch_output(t):
|
||||
# 1. Local Integration (Spatio-temporal)
|
||||
V_local(t) = Σ_i Σ_τ EPSP_i(t - τ) * w_i(z) # Sum over all spines i, with spatial weighting w_i based on distance z
|
||||
I_Ca_local(t) = VGCC_density(z) * g_Ca(V_local(t) - V_Ca_thresh) # Local calcium current
|
||||
|
||||
# 2. Active Spike Generation (Threshold Logic)
|
||||
if (V_local(t) > θ_Na) and (NaV_density(z) > 0):
|
||||
generate_dendritic_Na_spike() # Fast, propagating
|
||||
dendritic_spike_amplitude = branch_excitability * NaV_density(z)
|
||||
|
||||
elif ( [Ca²⁺]_i(z, t) > θ_Ca_spike ) and ( I_Ca_local(t) > 0 ):
|
||||
generate_dendritic_Ca_spike() # Slow, localized
|
||||
dendritic_spike_amplitude = branch_excitability * VGCC_density(z)
|
||||
|
||||
# 3. Coincidence & Teaching Signal Integration
|
||||
bAP_signal = bAP(t) * attenuation_factor(z) # bAP strength decays with distance z from soma
|
||||
|
||||
if dendritic_spike_occurs and (abs(t_dend_spike - t_bAP) < window_COINCIDENCE):
|
||||
# CRITICAL: Strong teaching signal for plasticity
|
||||
global_teaching_signal = bAP_signal * dendritic_spike_amplitude
|
||||
tag_eligible_spikes(spines_within_radius_R, global_teaching_signal)
|
||||
forward_output = dendritic_spike_amplitude # Active transmission
|
||||
|
||||
else if V_local(t) > θ_passive:
|
||||
forward_output = V_local(t) * cable_properties(z) # Passive spread
|
||||
else:
|
||||
forward_output = 0
|
||||
```
|
||||
|
||||
#### 2. Modulation of Branch Excitability & Pattern Separation
|
||||
|
||||
Branch-specific modulators (**dopamine, acetylcholine**) reconfigure the branch's **global gain and plasticity thresholds**:
|
||||
|
||||
- **Dopamine (D1 receptor):** Increases `branch_excitability` (↑ `NaV_density` sensitivity) and **lowers θ\_Na**. It also gates plasticity: `plasticity_enabled = dopamine_present and coincidence_detected`. This primes the branch for learning salient, reward-predicting patterns.
|
||||
- **Acetylcholine (muscarinic):** Enhances `VGCC_density(z)` efficacy and NMDA conductance. It promotes **Ca²⁺ spike generation** over Na⁺ spikes, favoring slower, integrative pattern detection over fast propagation.
|
||||
- **GABA Inhibition:** This is crucial for pattern separation. A GABAergic input onto the branch shunts `V_local(t)`:
|
||||
- `V_local_shunted(t) = V_local(t) / (1 + g_GABA(t) * R_input)`
|
||||
- By selectively inhibiting specific branches, interneurons **prevent those branches from reaching spike threshold**, ensuring only the most strongly activated, distinct input combinations generate output. This forces different branches to learn and respond to different patterns.
|
||||
|
||||
#### 3. Spatial Computation & Weight Updates
|
||||
|
||||
The **pattern separation** emerges from the interaction of localized synaptic inputs and branch-wide thresholds:
|
||||
|
||||
1. **Input Pattern:** A set of active spines delivers EPSPs to `V_local(t)`.
|
||||
2. **Branch Filter:** The combination of `NaV_density(z)`, `VGCC_density(z)`, `branch_excitability`, and local inhibition determines a **unique activation threshold** for that branch.
|
||||
3. **Pattern Detection:** Only input combinations whose summed `V_local(t)` exceeds this threshold generate a dendritic spike. Slightly different patterns may fail, especially with GABAergic tuning.
|
||||
4. **Synaptic Tagging (Credit Assignment):** When a dendritic spike coincides with a bAP, it generates a `global_teaching_signal`. This signal is broadcast **retrogradely** but **locally**, tagging all *recently active* spines within a spatial radius `R`. The tag's strength decays with distance from the spike initiation zone.
|
||||
- `spine[i].plasticity_tag += global_teaching_signal * exp(-distance(spine[i], spike_zone)/λ)`
|
||||
|
||||
#### 4. Internal State Variable Updates
|
||||
|
||||
- `[Ca²⁺]_i(z)`**:** Integrates from:
|
||||
- NMDA receptors at active spines.
|
||||
- `VGCC_density(z)` opened by `V_local(t)`.
|
||||
- Internal stores (IP3R) triggered by modulators.
|
||||
- Cleared by pumps with time constant `τ_Ca`.
|
||||
- **Channel Densities (**`NaV_density(z)`**,** `VGCC_density(z)`**):** Can undergo slow, activity-dependent homeostatic plasticity.
|
||||
- `NaV_density(z) += η * (target_activity - dendritic_spike_rate)`
|
||||
- This allows branches to self-tune their excitability over long timescales.
|
||||
- `branch_excitability`**:** A slow variable modulated by neuromodulators (↑ by DA) and metaplasticity rules.
|
||||
|
||||
#### Summary: The Branch as a Feature Detector
|
||||
|
||||
In this model, a dendritic branch is not a passive cable. It is an **active feature detector** with tunable properties:
|
||||
|
||||
- **Input:** A vector of synaptic inputs (spatially arranged).
|
||||
- **Nonlinearity:** A double-threshold operation (Na⁺/Ca²⁺ spike generation) determined by its ion channel makeup and modulatory state.
|
||||
- **Output:** Either a large, propagating dendritic spike (a **binary feature detection event**) or graded subthreshold voltage.
|
||||
- **Learning:** Synapses on the branch are updated based on a **three-factor rule**:
|
||||
1. Presynaptic activity (glutamate release).
|
||||
2. Postsynaptic dendritic spike (local).
|
||||
3. Global teaching signal (bAP coincidence, modulated by DA).
|
||||
- **Function:** Different branches, through their unique channel densities and inhibition, become selective for **different combinations of inputs**, implementing a powerful form of **dendritic pattern separation** that vastly expands the computational capacity of a single neuron.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
### **4. Soma (Global Integrator & Policy Center)**
|
||||
|
||||
**Internal State Variables:**
|
||||
|
||||
- `V_m`: Global membrane potential
|
||||
- `firing_rate_avg`: Moving average (hours scale)
|
||||
- `[Ca²⁺]_i`: Somatic Ca²⁺ (integration of activity)
|
||||
- `Ih_current`: HCN-mediated stabilizing current
|
||||
- `sAHP`: Afterhyperpolarization magnitude
|
||||
- `excitability_state`: Neuromodulator-dependent
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- **Convergent:** Summed dendritic inputs (EPSPs, dendritic spikes)
|
||||
- **Inhibitory:** Direct perisomatic inhibition
|
||||
- **Metabolic:** Lactate (energy), oxygen status
|
||||
- **Global:** Neuromodulators (dopamine, serotonin, etc.)
|
||||
- **Hormonal:** Corticosterone, estrogen, etc.
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- **Primary:** Action potential (if `V_m` > threshold_AIS)
|
||||
- **Backpropagating:** bAP to dendrites (teaching signal)
|
||||
- **Homeostatic:** Scaling factors to all synapses
|
||||
- **Transcriptional:** Nuclear signals for gene expression
|
||||
|
||||
**Integration Algorithm:**
|
||||
|
||||
```
|
||||
V_m = integrate(dendritic_inputs, somatic_inputs, intrinsic_currents)
|
||||
if V_m > threshold_AIS:
|
||||
fire_AP()
|
||||
send_bAP_to_dendrites()
|
||||
update_firing_rate_history()
|
||||
trigger_sAHP()
|
||||
|
||||
if firing_rate_avg deviates_from_target:
|
||||
calculate_scaling_factor()
|
||||
broadcast_to_all_synapses()
|
||||
```
|
||||
|
||||
**Policy Functions:**
|
||||
|
||||
- **Gain control:** Adjust input resistance via K⁺ channels
|
||||
- **Frequency adaptation:** sAHP limits sustained firing
|
||||
- **State-dependent processing:** Neuromodulators reconfigure integration rules
|
||||
- **Homeostasis:** Global scaling maintains firing rate setpoint
|
||||
|
||||
### Complete Model
|
||||
|
||||
#### 1. Integration & Spike Generation Algorithm
|
||||
|
||||
The soma's membrane potential `V_m(t)` is governed by a differential equation integrating all currents, not a simple sum:
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
function update_soma(V_m, t, dt):
|
||||
|
||||
# 1. CURRENT INTEGRATION
|
||||
I_total = 0
|
||||
|
||||
# Active Dendritic Inputs (Weighted)
|
||||
I_dend = Σ (dendritic_spike_i(t) * weight_i) + Σ (passive_EPSP_i(t) * cable_filter_i)
|
||||
I_total += I_dend
|
||||
|
||||
# Perisomatic Inhibition (Fast, Powerful)
|
||||
I_GABA = g_GABA(t) * (V_m - E_GABA) # Often Cl- based, E_GABA ~ -70 mV
|
||||
I_total += I_GABA
|
||||
|
||||
# Intrinsic Somatic Currents (State-Dependent)
|
||||
I_Na_leak = g_Na_leak * (V_m - E_Na)
|
||||
I_K_leak = g_K_leak * (V_m - E_K)
|
||||
I_h = Ih_current * (V_m - E_h) # HCN channel, depolarizing, activated by hyperpolarization
|
||||
I_sAHP = g_sAHP(t) * (V_m - E_K) # Slow Ca²⁺-activated K⁺ current (builds up with spiking)
|
||||
|
||||
I_total += I_Na_leak + I_K_leak + I_h + I_sAHP
|
||||
|
||||
# Neuromodulator Effects (Instantiated as parameter changes)
|
||||
if dopamine_high:
|
||||
I_total *= (1 + gain_DA) # Global gain increase
|
||||
threshold_AIS *= (1 - threshold_shift_DA) # Lowered firing threshold
|
||||
|
||||
# 2. MEMBRANE POTENTIAL UPDATE
|
||||
dV_m/dt = (I_total) / C_m # Standard membrane equation
|
||||
V_m(t+dt) = V_m(t) + dV_m/dt * dt
|
||||
|
||||
# 3. SPIKE DECISION & POST-SPIKE ACTIONS
|
||||
if V_m(t+dt) > threshold_AIS:
|
||||
fire_AP() # All-or-none event at Axon Initial Segment (AIS)
|
||||
|
||||
# CRITICAL OUTPUTS:
|
||||
send_bAP_to_all_dendrites(amplitude = bAP_strength) # Primary teaching signal
|
||||
increment_spike_counter()
|
||||
|
||||
# ADAPTATION MECHANISMS:
|
||||
[Ca²⁺]_i_soma += ΔCa_per_spike # Somatic calcium accumulates
|
||||
g_sAHP(t) += Δg_sAHP # Increment slow afterhyperpolarization conductance
|
||||
trigger_refractory_period(τ_refractory)
|
||||
|
||||
# 4. SLOW VARIABLE UPDATES (Homeostasis)
|
||||
firing_rate_avg = exponential_moving_average(spike_counter, τ_avg_hours)
|
||||
update_excitability_state(neuromodulator_levels)
|
||||
```
|
||||
|
||||
#### 2. Policy Functions: Specific Implementations
|
||||
|
||||
**A. Gain Control (Input Resistance Modulation):**
|
||||
|
||||
- Modulated via **leak potassium channels** (e.g., KCNQ, TASK).
|
||||
- `g_K_leak = baseline_g_K_leak * (1 - α_ACh - β_Serotonin + γ_Corticosterone)`
|
||||
- **ACh (muscarinic):** Decreases `g_K_leak` → increases input resistance `R_input` → **same synaptic current causes larger V_m depolarization** (↑ gain).
|
||||
- **Effect:** The soma's responsiveness to dendritic inputs is dynamically scaled.
|
||||
|
||||
**B. Frequency Adaptation (sAHP - Slow AfterHyperPolarization):**
|
||||
|
||||
- A **calcium-dependent potassium current** that builds up with activity.
|
||||
- `g_sAHP(t)` dynamics: `τ_sAHP * d(g_sAHP)/dt = -g_sAHP + β * [Ca²⁺]_i_soma`
|
||||
- Each spike adds to somatic `[Ca²⁺]_i`, which slowly increases `g_sAHP`. This hyperpolarizes the cell, making it harder to reach threshold for subsequent spikes. **Prevents runaway excitation and encodes temporal derivatives.**
|
||||
|
||||
**C. State-Dependent Processing (Neuromodulator Reconfiguration):**
|
||||
This is the core "policy" shift. Neuromodulators don't just scale parameters; they switch operational modes:
|
||||
|
||||
- **Dopamine (via D1 receptors):**
|
||||
- ↑ `gain_DA` (as above).
|
||||
- ↓ `threshold_AIS` (easier to fire).
|
||||
- ↑ `bAP_strength` (enhances teaching signal to dendrites).
|
||||
- **Policy:** "EXPLORE/LEARN" mode. Increases sensitivity to inputs and reinforces active pathways.
|
||||
- **Acetylcholine (ACh - cortical):**
|
||||
- ↓ `g_K_leak` (↑ gain, as above).
|
||||
- ↑ `I_h` current (stabilizes V_m, improves temporal integration).
|
||||
- **Policy:** "ATTENTION" mode. Enhances signal-to-noise ratio for salient, ongoing inputs.
|
||||
- **Serotonin (5-HT):**
|
||||
- ↑ `g_K_leak` (↓ gain).
|
||||
- Modulates `I_h`.
|
||||
- **Policy:** "STABILITY/CAUTION" mode. Tones down overall excitability, promotes rhythmic activity.
|
||||
|
||||
**D. Homeostatic Set-Point Control (Firing Rate Stabilization):**
|
||||
|
||||
- The `firing_rate_avg` is compared to a `target_rate` (a genetically/inherently set point).
|
||||
- If `|firing_rate_avg - target_rate| > tolerance` over a long window (hours):
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
scaling_factor = target_rate / firing_rate_avg
|
||||
broadcast_to_all_synapses({command: "scale_AMPA", factor: scaling_factor})
|
||||
```
|
||||
|
||||
- This is the **global synaptic scaling** command sent to all synapses (as referenced in your postsynaptic model). It multiplicatively adjusts `N_AMPA` everywhere, a slow, cell-wide negative feedback loop.
|
||||
|
||||
#### 3. Soma as Transcriptional & Metabolic Hub
|
||||
|
||||
- **Somatic** `[Ca²⁺]_i` **Integration:** Sustained high `firing_rate_avg` leads to sustained elevated somatic `[Ca²⁺]_i`. This activates transcription factors (e.g., CREB).
|
||||
- **Nuclear Signaling:** Triggers gene expression programs for:
|
||||
- **Structural proteins** (to grow dendrites/spines).
|
||||
- **More ion channels** (long-term excitability changes).
|
||||
- **Neurotrophic factors** (e.g., BDNF) released to further modify network.
|
||||
- **Metabolic Gatekeeping:** The `lactate` and `oxygen` signals directly influence ATP production. Low energy → upregulate `I_h` and `g_K_leak` to **reduce metabolic cost** by lowering firing rate—a direct link from metabolism to excitability policy.
|
||||
|
||||
#### Summary: The Soma as Central Processor
|
||||
|
||||
In this model, the soma is not a simple point neuron. It is a **dynamic policy engine** that:
|
||||
|
||||
1. **Integrates** spatially and temporally filtered inputs from dendritic subunits.
|
||||
2. **Generates** all-or-none output decisions (APs) based on a modifiable threshold.
|
||||
3. **Broadcasts** teaching signals (bAPs) back to the dendritic computational layers.
|
||||
4. **Adapts** its own sensitivity on short (sAHP) and long (channel expression) timescales.
|
||||
5. **Reconfigures** its entire input-output function based on neuromodulatory state (gain, threshold, integration window).
|
||||
6. **Orchestrates** whole-cell homeostasis via global scaling commands and transcriptional programs.
|
||||
|
||||
This transforms the classic "integrate-and-fire" unit into a **biological central processing unit (CPU) with dynamic clock speed, adjustable gain, and multiple feedback control systems**, all dedicated to maintaining stability while allowing for state-dependent, plastic computation.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
### **5. Axon Initial Segment (Binary Decision Point)**
|
||||
|
||||
**Internal State Variables:**
|
||||
|
||||
- `V_m`: Local potential (lower threshold than soma)
|
||||
- `NaV_availability`: Fraction of non-inactivated channels
|
||||
- `refractory_state`: Absolute/relative refractory timing
|
||||
- `threshold`: Dynamic spike threshold
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- **Somatic:** Integrated voltage
|
||||
- **Modulatory:** Phosphorylation states (affecting NaV kinetics)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- **Primary:** All-or-none AP to axon
|
||||
- **Backward:** bAP initiation to soma/dendrites
|
||||
|
||||
**Decision Algorithm:**
|
||||
|
||||
```
|
||||
if (V_m > threshold && NaV_availability > 0.5 && !refractory):
|
||||
generate_AP() # Stereotyped, high reliability
|
||||
NaV_availability = 0 # Begin inactivation
|
||||
start_refractory_timer()
|
||||
```
|
||||
|
||||
**Dynamic Properties:**
|
||||
|
||||
- **Threshold plasticity:** Activity-dependent adjustment via channel phosphorylation
|
||||
- **Reliability:** High safety factor ensures 1:1 input-output
|
||||
- **Timing precision:** Submillisecond jitter
|
||||
|
||||
### Complete Model
|
||||
|
||||
#### 1. Decision Algorithm: State Machine Implementation
|
||||
|
||||
The AIS is modeled as a deterministic **state machine with dynamic thresholds**, not a simple `if` statement.
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
# STATE VARIABLES
|
||||
V_m_AIS # Local membrane potential (driven by somatic V_m with small delay & attenuation)
|
||||
NaV_availability # Fraction of Nav channels NOT inactivated (0.0 to 1.0)
|
||||
h_inf # Steady-state inactivation (voltage-dependent)
|
||||
τ_h # Inactivation time constant
|
||||
refractory_timer # Counts down from absolute refractory period
|
||||
threshold_dynamic # Instantaneous firing threshold (can vary)
|
||||
threshold_baseline # Resting threshold (e.g., -50 mV)
|
||||
|
||||
# DECISION CYCLE at time t
|
||||
function evaluate_AIS(V_m_soma, t):
|
||||
|
||||
# 1. UPDATE LOCAL STATE
|
||||
# Electrical coupling from soma (simplified)
|
||||
V_m_AIS = V_m_soma * coupling_factor_AIS - I_K_accumulated
|
||||
|
||||
# Nav channel availability (recovery from inactivation)
|
||||
if refractory_timer <= 0:
|
||||
# Voltage-dependent steady-state inactivation
|
||||
h_inf = 1 / (1 + exp((V_m_AIS - V_half_inact) / k_inact))
|
||||
# Recovery towards h_inf
|
||||
dNaV_availability/dt = (h_inf - NaV_availability) / τ_h
|
||||
NaV_availability += dNaV_availability * dt
|
||||
else:
|
||||
refractory_timer -= dt
|
||||
|
||||
# 2. DYNAMIC THRESOLD CALCULATION (critical for modulation)
|
||||
# Threshold adapts based on recent activity (Na channel phosphorylation state)
|
||||
threshold_dynamic = threshold_baseline + β * (1 - NaV_availability) + γ * I_K_accumulated
|
||||
# β: factor for inactivation-dependent increase
|
||||
# γ: factor for K⁺ current influence
|
||||
|
||||
# 3. SPIKE GENERATION DECISION
|
||||
# The "high safety factor" is modeled as a steep, deterministic function
|
||||
if (V_m_AIS > threshold_dynamic) and (NaV_availability > θ_availability) and (refractory_timer <= 0):
|
||||
|
||||
# GENERATE ACTION POTENTIAL (All-or-none)
|
||||
AP_amplitude = AP_max * NaV_availability # Slightly smaller if not fully recovered
|
||||
send_AP_down_axon(velocity = f(axon_properties))
|
||||
initiate_bAP_to_soma_dendrites(amplitude = bAP_strength)
|
||||
|
||||
# POST-SPIKE STATE RESETS
|
||||
NaV_availability = 0.0 # Immediate absolute inactivation
|
||||
refractory_timer = τ_abs_refractory # e.g., 1-2 ms
|
||||
I_K_accumulated += ΔI_K_spike # Accumulate slow K⁺ current (affects threshold)
|
||||
|
||||
# THRESHOLD PLASTICITY UPDATE (Activity-dependent)
|
||||
threshold_baseline += η_thresh * (target_activity - recent_spike_rate)
|
||||
# Makes threshold higher if cell is too active, lower if too quiet (homeostatic)
|
||||
```
|
||||
|
||||
#### 2. Dynamic Properties: Specific Mechanisms
|
||||
|
||||
**A. Threshold Plasticity & Modulation**
|
||||
This is a key regulatory point. The `threshold_baseline` is not fixed; it's a **homeostatically regulated variable** and a **target for neuromodulation**.
|
||||
|
||||
- **Activity-Dependent (Homeostatic):** As shown above, sustained high `recent_spike_rate` increases `threshold_baseline`, making the neuron harder to fire (negative feedback).
|
||||
- **Phosphorylation-Dependent (Modulatory):** Kinases activated by neuromodulators (PKA, PKC, CK2) phosphorylate specific sites on Nav channels (e.g., Naᵥ1.6).
|
||||
- **PKA Phosphorylation (e.g., via DA/NE):** Shifts `V_half_inact` to more **depolarized** voltages → increases `h_inf` at resting V_m → effectively **increases NaV_availability** and **lowers effective threshold**. **Policy:** *Lower threshold, increase excitability.*
|
||||
- **CK2 Phosphorylation:** Can shift activation `V_half_act` to more **hyperpolarized** voltages → channels open easier → **lowers threshold**. **Policy:** *Increase temporal precision and reliability.*
|
||||
|
||||
**B. Reliability (High Safety Factor)**
|
||||
This is modeled implicitly by the steepness of the Nav activation curve and the high channel density.
|
||||
|
||||
- The condition `(V_m_AIS > threshold_dynamic)` is not a linear probability. It's a **step function** because the activation variable `m` of Nav channels is a steep sigmoid:
|
||||
- `m_inf = 1 / (1 + exp((V_half_act - V_m_AIS)/k_act))`
|
||||
- With a high density of channels, once `V_m_AIS` crosses `threshold_dynamic` (where `m_inf` becomes significant), the positive feedback of Na⁺ influx is explosive and deterministic. There is no stochastic "maybe" spike.
|
||||
|
||||
**C. Timing Precision (Submillisecond Jitter)**
|
||||
Jitter is minimized by three model features:
|
||||
|
||||
1. **Rapid Kinetics:** Very small `τ_m` (activation time constant) for AIS Nav channels (\~0.1 ms).
|
||||
2. **High dV/dt:** The somatic `V_m` must rise rapidly to cross the AIS threshold. Slow ramps will not trigger a precise spike. This is enforced by the requirement for a strong, synchronous dendritic input to create a fast somatic depolarization.
|
||||
3. **Refractory State Clarity:** The absolute refractory period (`τ_abs_refractory`) is a hard lockout. The relative refractory period is modeled by the recovery of `NaV_availability` and the elevated `threshold_dynamic` post-spike, which together sharply define the earliest possible next spike time.
|
||||
|
||||
#### 3. Role in Backpropagation (bAP) Initiation
|
||||
|
||||
The AIS is the **source** of the backpropagating action potential.
|
||||
|
||||
- Upon AIS spike generation, the depolarizing current not only propagates down the axon but also **actively back-invades** the soma and dendrites.
|
||||
- `bAP_strength` in the model can be modulated (e.g., increased by dopamine signaling), affecting the amplitude of this critical teaching signal throughout the dendritic tree.
|
||||
|
||||
#### Summary: The AIS as a Programmable Binary Converter
|
||||
|
||||
In this model, the Axon Initial Segment is the **final, decisive policy layer**:
|
||||
|
||||
- **Input:** Graded somatic membrane potential (`V_m_soma`).
|
||||
- **Processing:** A dynamic threshold function, gated by channel availability and phosphorylation state.
|
||||
- **Output:** A stereotyped action potential (or not) with high temporal fidelity.
|
||||
- **Key Modulation:** Its **excitability is tunable** via:
|
||||
- **Homeostatic Threshold Plasticity:** Keeps average firing rate in check.
|
||||
- **Phosphorylation States:** Allow neuromodulators (DA, NE, ACh) to directly adjust the "trigger happiness" of the neuron on fast timescales.
|
||||
- **Refractory Kinetics:** Control maximum firing frequency and temporal precision.
|
||||
|
||||
This transforms the AIS from a passive fuse into an **active, tunable decision node** that finalizes the neuron's output based on integrated somatic potential, while itself being subject to meta-level policy controls that set the neuron's overall responsiveness and reliability.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
### **6. Astrocyte (Metabolic Hub & Environment Manager)**
|
||||
|
||||
**Internal State Variables:**
|
||||
|
||||
- `[Ca²⁺]_i`: Cytosolic Ca²⁺ (can exhibit waves)
|
||||
- `[glutamate]_cleft`: Synaptic glutamate concentration
|
||||
- `[K⁺]_ext`: Extracellular K⁺
|
||||
- `glycogen_stores`: Energy reserves
|
||||
- `lactate_production_rate`: Metabolic output
|
||||
- `adenosine_level`: Sleep pressure signal
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- **Glutamate spillover:** From synapses (via EAAT1/2)
|
||||
- **K⁺ efflux:** From neuronal firing
|
||||
- **Neuromodulators:** Noradrenaline, ATP
|
||||
- **Metabolic:** Glucose from blood, oxygen status
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- **Recycling:** Glutamine to neurons
|
||||
- **Energy:** Lactate to neurons
|
||||
- **Modulatory:** D-serine, ATP, glutamate (gliotransmitters)
|
||||
- **Vasomodulatory:** Prostaglandins to blood vessels
|
||||
- **Homeostatic:** Adenosine (sleep pressure)
|
||||
- **Waste removal:** Aβ clearance facilitation
|
||||
|
||||
**Multi-Timescale Integration:**
|
||||
|
||||
```
|
||||
# Milliseconds:
|
||||
uptake_glutamate_and_K⁺()
|
||||
|
||||
# Seconds:
|
||||
if [Ca²⁺]_i > threshold:
|
||||
release_gliotransmitters(D_serine, ATP)
|
||||
|
||||
# Minutes:
|
||||
glycogen → lactate → export_to_neurons()
|
||||
adjust_blood_flow(based_on_activity)
|
||||
|
||||
# Hours:
|
||||
accumulate_adenosine(proportional_to_activity_history)
|
||||
orchestrate_glymphatic_clearance(during_sleep)
|
||||
```
|
||||
|
||||
**Core Functions:**
|
||||
|
||||
- **Ion homeostasis:** K⁺ buffering, pH regulation
|
||||
- **Metabolic coupling:** Lactate shuttle during high demand
|
||||
- **Synaptic modulator:** D-serine for NMDA function
|
||||
- **Network stabilizer:** Adenosine accumulation enforces sleep
|
||||
- **Waste manager:** Glymphatic clearance coordination
|
||||
|
||||
### Complete Model
|
||||
|
||||
#### 1. Multi-Timescale Integration Algorithm
|
||||
|
||||
The astrocyte is a **hybrid continuous/discrete controller** that operates on four distinct timescales. Its core logic can be modeled as:
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
# ASTROCYTE STATE MACHINE - Update at each simulation timestep dt (e.g., 1 ms)
|
||||
function update_astrocyte(t, dt, local_activity):
|
||||
|
||||
# ---- MILLISECOND SCALE (Continuous, Fast Feedback) ----
|
||||
# 1. ION & TRANSMITTER HOMEOSTASIS (Instantaneous uptake)
|
||||
glutamate_cleft[t] -= (EAAT_rate * glutamate_cleft[t]) * dt
|
||||
K_ext[t] -= (NKCC1_rate * (K_ext[t] - K_target)) * dt
|
||||
[Ca²⁺]_i[t] += (leak - SERCA_pump * [Ca²⁺]_i[t]) * dt
|
||||
|
||||
# 2. FAST CHEMICAL DETECTION (Triggers for slower processes)
|
||||
if glutamate_cleft[t] > θ_glu_high: # Detects spillover (excessive activity)
|
||||
trigger_IP3_production()
|
||||
if K_ext[t] > θ_K_high: # Detects high extracellular K+ (seizure risk)
|
||||
activate_KIR_channels() # Immediate buffering
|
||||
|
||||
# ---- SECOND TO MINUTE SCALE (Discrete Events, State Changes) ----
|
||||
# 3. CALCIUM-DEPENDENT GLIOTRANSMITTER RELEASE (Slow, phasic)
|
||||
if [Ca²⁺]_i[t] > θ_Ca_release and !cooldown_active:
|
||||
# Release is a discrete packet, not continuous
|
||||
release_gliotransmitter_packet("D_serine", amount = f([Ca²⁺]_i))
|
||||
release_gliotransmitter_packet("ATP", amount = g([Ca²⁺]_i))
|
||||
start_cooldown_timer(τ_cooldown) # Prevent constant release
|
||||
|
||||
# 4. METABOLIC COUPLING (Activity-dependent energy supply)
|
||||
energy_demand_estimate = integrate(glutamate_uptake_rate, window=60s)
|
||||
lactate_production_rate[t] = (glycogen_stores / τ_glycogen) * tanh(energy_demand_estimate)
|
||||
export_lactate_to_local_neurons(lactate_production_rate[t] * dt)
|
||||
|
||||
# ---- MINUTE TO HOUR SCALE (Integrative, Tonic Signals) ----
|
||||
# 5. VASOMODULATION & BLOOD FLOW CONTROL
|
||||
activity_integral_5min = moving_average(local_neuronal_firing, τ=5min)
|
||||
if t % (1*minute) == 0: # Update blood flow signal periodically
|
||||
prostaglandin_release = α * activity_integral_5min
|
||||
dilate_local_vasculature(prostaglandin_release)
|
||||
|
||||
# 6. SLEEP PRESSURE ACCUMULATION (Adenosine - Very Slow Integrator)
|
||||
# Adenosine accumulates proportional to total glutamate uptake (proxy for neural work)
|
||||
adenosine_production_rate = β * glutamate_uptake_total
|
||||
adenosine_level[t] += (adenosine_production_rate - clearance_rate_adenosine) * dt
|
||||
|
||||
# 7. WASTE MANAGEMENT CYCLE (Linked to sleep state)
|
||||
if is_sleep_cycle(t): # External circadian/sleep signal
|
||||
switch_to_glymphatic_mode() # Increase Aβ clearance rate 10x
|
||||
glycogen_stores += replenish_rate * dt
|
||||
else:
|
||||
switch_to_synaptic_support_mode()
|
||||
```
|
||||
|
||||
#### 2. Core Functions: Specific Models
|
||||
|
||||
**A. Ion Homeostasis (K⁺ & pH Buffer)**
|
||||
|
||||
- **K⁺ Buffering (Spatial K⁺ Siphoning):**
|
||||
- `d[K⁺]_ext/dt = neuronal_K⁺_release - KIR_uptake([K⁺]_ext) - diffusion`
|
||||
- **KIR Channel Model:** `I_KIR = g_KIR_max * sqrt([K⁺]_ext/3) * (V_m - E_K)` (nonlinear uptake).
|
||||
- Astrocytes form a **spatial network**; elevated K⁺ in one area is siphoned through gap junctions to areas with lower \[K⁺\].
|
||||
|
||||
**B. Metabolic Coupling (Lactate Shuttle)**
|
||||
|
||||
- **Energy Demand Sensing:** `glutamate_uptake_flux = EAAT_rate * [glu]_cleft`
|
||||
- EAATs co-transport Na⁺, requiring ATP to restore gradients → direct link between glutamate and energy demand.
|
||||
- **Astrocyte-Neuron Lactate Shuttle (ANLS) Model:**
|
||||
- `lactate_production = (glycogen_stores / (K_M + glycogen_stores)) * (1 + sigmoid(glutamate_uptake_flux))`
|
||||
- Lactate is exported via **MCT1/4 transporters** proportional to neuronal activity.
|
||||
|
||||
**C. Synaptic Modulation (D-serine Release)**
|
||||
|
||||
- **D-serine as a Volumetric Neuromodulator:**
|
||||
- D-serine is the primary co-agonist for **synaptic NMDA receptors**.
|
||||
- Release model: `[D_serine]_release = R_max * ([Ca²⁺]_i^4 / (K_D^4 + [Ca²⁺]_i^4))` (highly nonlinear, cooperative).
|
||||
- This effectively **gates synaptic plasticity**: only synapses under active astrocytic "supervision" (high Ca²⁺ in astrocyte) have fully functional NMDARs and can undergo LTP.
|
||||
|
||||
**D. Network Stabilizer (Adenosine Accumulation)**
|
||||
|
||||
- **Sleep Pressure as a Leaky Integrator:**
|
||||
- `d[adenosine]/dt = k_production * ∫(glutamate_uptake) - k_clearance * [adenosine]`
|
||||
- Adenosine acts on neuronal **A1 receptors**, universally inhibiting synaptic release (presynaptic) and excitability.
|
||||
- **This is a global negative feedback loop:** High network activity → more astrocytic glutamate uptake → more adenosine → stronger network-wide inhibition → enforced **activity quota** leading to sleep.
|
||||
|
||||
**E. Waste Manager (Glymphatic Coordination)**
|
||||
|
||||
- **State-Dependent Clearance:**
|
||||
- During sleep/wake cycle, astrocyte **aquaporin-4 (AQP4)** polarization changes.
|
||||
- `clearance_rate_Aβ = baseline_clearance * (1 + 10 * sleep_state)`
|
||||
- Astrocytes dynamically regulate **perivascular space** volume to facilitate convective flow of cerebrospinal fluid during sleep, clearing metabolites like Aβ.
|
||||
|
||||
#### 3. Modulation of the Astrocyte
|
||||
|
||||
The astrocyte itself is modulated by:
|
||||
|
||||
- **Noradrenaline (from locus coeruleus):** ↑ `IP3 production` → ↑ `[Ca²⁺]_i` waves → potentiates gliotransmitter release. **Policy:** *Alertness mode* – enhances astrocytic support for heightened neural activity.
|
||||
- **ATP/Purinergic Signaling:** From active neurons or other astrocytes. Can propagate **Ca²⁺ waves** across the astrocyte syncytium, enabling long-range coordination of homeostatic states.
|
||||
|
||||
#### Summary: The Astrocyte as a Multi-Scale Regulator
|
||||
|
||||
This model presents the astrocyte as a **biological real-time operating system (RTOS)** for the brain microenvironment:
|
||||
|
||||
1. **Fast (ms):** I/O manager – buffers ions, clears neurotransmitters.
|
||||
2. **Medium (s-min):** Resource manager – allocates energy (lactate), modulates synapses (D-serine).
|
||||
3. **Slow (hrs):** System administrator – enforces sleep quotas (adenosine), schedules garbage collection (glymphatics), manages long-term resources (glycogen).
|
||||
|
||||
It introduces **critical non-neuronal constraints** into the neural network model:
|
||||
|
||||
- **Energy is limited and dynamically allocated.**
|
||||
- **Waste products accumulate and must be cleared.**
|
||||
- **Ionic balance must be maintained to prevent instability (seizures).**
|
||||
- **Synaptic plasticity is chemically gated by glial oversight.**
|
||||
|
||||
In the full system model, the astrocyte is the **homeostatic backdrop** against which the neuron's computational drama plays out—a dynamic environment that both supports and constrains neural activity, ultimately ensuring the system's long-term stability and health.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
## System-Wide Integration Principles
|
||||
|
||||
### Signal Flow Architecture:
|
||||
|
||||
```
|
||||
Presynapse → Postsynapse → Dendrite → Soma → AIS → AP
|
||||
↑ ↓ ↑ ↓ ↑
|
||||
←←←←←←←←←←←←←←←←←←←←←←←←←←←←←←←←←
|
||||
Retrograde Signals & Global Modulation
|
||||
↓ ↑ ↓ ↑ ↓
|
||||
Astrocyte ←→ Environment ←→ Blood Flow ←→ Systemic
|
||||
```
|
||||
|
||||
### Timescale Integration:
|
||||
|
||||
- **Fast (ms):** Electrical → chemical → electrical transformation
|
||||
- **Medium (s-min):** Retrograde modulation, metabolic support
|
||||
- **Slow (hrs-days):** Structural change, homeostatic scaling
|
||||
- **Very slow (days-lifetime):** Epigenetic, system consolidation
|
||||
|
||||
### Key Cross-Component Dependencies:
|
||||
|
||||
1. **Activity → Metabolism:** Neuronal firing → glutamate/K⁺ release → astrocyte activation → lactate production
|
||||
2. **Metabolism → Plasticity:** Lactate availability → ATP production → protein synthesis → structural change
|
||||
3. **Structure → Function:** Spine growth → more AMPA receptors → larger EPSPs → easier dendritic spike initiation
|
||||
4. **Past → Future:** Firing history → somatic Ca²⁺ integration → gene expression → receptor changes → future excitability
|
||||
|
||||
This model architecture creates a **recursive optimization system** where each component's behavior adjusts based on both immediate inputs and long-term trends, with astrocytes providing the essential metabolic and environmental context that makes sustained neural computation possible.
|
||||
@@ -0,0 +1,816 @@
|
||||
# Multi-Timescale Neural Component Analysis
|
||||
|
||||
## PRESYNAPSE
|
||||
|
||||
### Timescale 1: Fast (<1ms - 100ms)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Action potential depolarization (to \~+30 mV)
|
||||
- Voltage-gated calcium channel (VGCC) opening
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Vesicle docking and priming (SNARE complex assembly)
|
||||
- Ca²⁺ influx
|
||||
- Glutamate vesicle release (stochastic, probability P_r)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Glutamate release into synaptic cleft
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation (Facilitation):** Residual Ca²⁺ from previous spikes increases P_r for next release
|
||||
- **Downregulation (Depression):** High-frequency firing depletes readily releasable vesicle pool, decreasing P_r
|
||||
|
||||
---
|
||||
|
||||
### Timescale 2: Medium (100ms - 10s)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Buildup of residual Ca²⁺
|
||||
- Volume transmission neuromodulators (dopamine, acetylcholine, noradrenaline)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Accumulation/depletion of Ca²⁺ stores
|
||||
- Modulation of release machinery sensitivity
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Sustained or diminished glutamate release patterns (STF/STD)
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Short-Term Facilitation (STF):** Residual Ca²⁺ increases P_r over spike trains
|
||||
- **Short-Term Depression (STD):** Vesicle pool depletion reduces P_r
|
||||
- **Augmentation:** Calcium-sensing proteins (Munc13) alter release probability (1-10s range)
|
||||
|
||||
**Notes:**
|
||||
|
||||
This active clearance happens rapidly, within tens to hundreds of milliseconds. It serves two vital functions:
|
||||
|
||||
- **Termination of Signal:** It rapidly lowers Ca²⁺ to end the release command, ensuring neurotransmitter release is brief and precise.
|
||||
- **Prevention of Toxicity:** Sustained high intracellular Ca²⁺ is cytotoxic and can trigger apoptosis (cell death). Efficient clearance is essential for neuronal health.
|
||||
|
||||
|
||||
- **Facilitation:** If Ca²⁺ clearance is slightly slower than the arrival of the next action potential, residual Ca²⁺ accumulates near the release sites. This "leftover" Ca²⁺ adds to the influx from the next spike, making vesicle fusion more likely (increasing P<sub>r</sub>).
|
||||
- **Depression:** If firing is very rapid, the pumps and exchangers cannot keep up, and Ca²⁺ levels remain elevated for longer in a more diffuse manner. This can paradoxically activate processes that inhibit release or simply outpace the recycling of vesicles, leading to depletion.
|
||||
|
||||
---
|
||||
|
||||
### Timescale 3: Slow (seconds - minutes)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Retrograde NO (nitric oxide) from postsynapse
|
||||
- Retrograde BDNF (brain-derived neurotrophic factor)
|
||||
- Retrograde endocannabinoids (eCBs, e.g., 2-AG)
|
||||
- Astrocyte gliotransmitters (ATP, D-serine, glutamate)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Enzymatic cascade activation/suppression
|
||||
- CB1 receptor activation (by eCBs)
|
||||
- VGCC modulation
|
||||
- Potassium channel modulation
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Modified P_r affecting subsequent releases
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation:** NO/BDNF activates cascades that increase P_r, promote synaptic growth (facilitates LTP)
|
||||
- **Downregulation:** eCBs bind CB1 receptors, inhibit VGCCs, activate K⁺ channels → profound decrease in P_r (DSE/DSI - depolarization-induced suppression)
|
||||
|
||||
### Timescale 4: Metabolic (minutes - hours)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Astrocyte-supplied lactate (via monocarboxylate transporters)
|
||||
- Glutamine from astrocytes (glutamate-glutamine cycle)
|
||||
- Metabolic state indicators (ATP levels, NAD/NADH ratio)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- ATP-dependent vesicle cycling
|
||||
- Glutamine→glutamate conversion (via glutaminase)
|
||||
- Vesicle refilling with glutamate
|
||||
- Maintenance of ion gradients
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Sustained neurotransmitter release capacity
|
||||
- Metabolic demand signals to astrocyte
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Metabolic veto:** Insufficient ATP prevents vesicle release despite adequate Ca²⁺
|
||||
- Lactate availability determines sustained release capacity during high activity
|
||||
|
||||
---
|
||||
|
||||
### Timescale 5: Structural (hours - days+)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Retrograde trophic factors (BDNF, sustained)
|
||||
- Homeostatic scaling signals from soma
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Structural growth/retraction of presynaptic bouton
|
||||
- Changes in active zone size
|
||||
- Alterations in vesicle pool size
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Modified synaptic strength through structural change
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Terminal size increases/decreases
|
||||
- Vesicle pool capacity changes
|
||||
- Active zone protein composition changes
|
||||
|
||||
---
|
||||
|
||||
## POSTSYNAPSE (Dendritic Spine)
|
||||
|
||||
### Timescale 1: Fast (<1ms - 100ms)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Glutamate binding to AMPA receptors (<1ms)
|
||||
- Glutamate binding to NMDA receptors (Mg²⁺-blocked initially)
|
||||
- Local depolarization from AMPA activation
|
||||
- GABA from inhibitory interneurons
|
||||
|
||||
**Actions:**
|
||||
|
||||
- AMPA receptor opening → Na⁺ influx → local depolarization (EPSP)
|
||||
- NMDA receptor Mg²⁺ unblock (requires depolarization > -40mV)
|
||||
- NMDA receptor opening → Ca²⁺ influx
|
||||
- AMPA receptor desensitization (if glutamate lingers)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- EPSP propagating to dendritic branch
|
||||
- Local Ca²⁺ concentration changes
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation:** Depolarization relieves NMDA Mg²⁺ block → Ca²⁺ influx amplification
|
||||
- **Downregulation:** AMPA desensitization acts as low-pass filter
|
||||
|
||||
---
|
||||
|
||||
### Timescale 2: Medium (100ms - 10s)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Sustained glutamate exposure
|
||||
- Metabotropic glutamate receptor (mGluR) activation
|
||||
- GABA-B receptor activation (slow inhibition)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- G-protein coupled signaling cascades
|
||||
- Second messenger activation
|
||||
- Modulation of local excitability
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Modified EPSP amplitude based on recent history
|
||||
- Preparation for plasticity events
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- mGluR-mediated changes in spine excitability
|
||||
- GABA-B provides prolonged shunting inhibition (100ms-1s)
|
||||
|
||||
---
|
||||
|
||||
### Timescale 3: Slow (seconds - minutes)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Sustained high Ca²⁺ influx through NMDARs
|
||||
- Back-propagating action potential (bAP) from soma/AIS
|
||||
- D-serine co-agonist from astrocyte
|
||||
|
||||
**Actions:**
|
||||
|
||||
- CaMKII (calcium/calmodulin-dependent protein kinase II) autophosphorylation
|
||||
- Synaptic tagging: Ca²⁺ creates local molecular "tag" marking synapse as recently active
|
||||
- Synthesis and release of retrograde messengers:
|
||||
- **NO synthesis** (from high Ca²⁺)
|
||||
- **BDNF release**
|
||||
- **Endocannabinoid (eCB) synthesis** (from sustained Ca²⁺)
|
||||
- AMPA receptor trafficking from extrasynaptic pool into PSD (early-LTP)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Retrograde NO (diffuses to presynapse)
|
||||
- Retrograde BDNF (travels to presynapse)
|
||||
- Retrograde eCBs (diffuse to presynapse)
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation (LTP):** High Ca²⁺ (>10 μM) → CaMKII activation → spine head expansion → AMPAR insertion → increased synaptic weight
|
||||
- **Downregulation (LTD):** Low/sustained Ca²⁺ (0.5-1.0 μM) → phosphatase activation → spine shrinkage → AMPAR endocytosis → decreased weight
|
||||
- Tag duration: CaMKII phosphorylation state acts as \~1-2 hour memory tag
|
||||
|
||||
---
|
||||
|
||||
### Timescale 4: Metabolic (minutes - hours)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Astrocyte D-serine (NMDA co-agonist, essential for late-LTP)
|
||||
- Astrocyte TNF-α, cholesterol (permissive factors)
|
||||
- Metabolic substrates for local protein synthesis
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Local protein synthesis in dendrites (responds to "tags")
|
||||
- Structural spine remodeling
|
||||
- Transition from early-LTP to late-LTP (L-LTP)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Demand signals for continued metabolic support
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- D-serine availability gates transition to L-LTP
|
||||
- Metabolic state determines whether tagged synapses can undergo structural consolidation
|
||||
|
||||
---
|
||||
|
||||
### Timescale 5: Structural (hours - days+)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Persistent synaptic tags combined with eligibility signals
|
||||
- Homeostatic scaling signals from soma
|
||||
- Neuromodulator-driven metaplasticity signals
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Spine volume changes (0.01-1.0 μm³ range)
|
||||
- Receptor number changes (AMPAR density)
|
||||
- Structural consolidation or elimination
|
||||
- PSD protein composition changes
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Stable changes in synaptic weight
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Successful spines grow and strengthen
|
||||
- Weak/unused spines shrink or are eliminated
|
||||
- Homeostatic scaling adjusts all synapses proportionally
|
||||
|
||||
---
|
||||
|
||||
## DENDRITE
|
||||
|
||||
### Timescale 1: Fast (10-100ms)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Multiple EPSPs from spines on the branch
|
||||
- Back-propagating action potential (bAP) from soma
|
||||
- IPSPs from inhibitory synapses
|
||||
- Neuromodulator influence on dendritic K⁺ channels
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Spatial summation: EPSPs from different spines add together
|
||||
- Temporal summation: EPSPs from successive spikes add together
|
||||
- NMDA spike generation (local Ca²⁺ spike if threshold reached)
|
||||
- Dendritic Na⁺/Ca²⁺ spike generation
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Integrated EPSP to soma
|
||||
- Dendritic spike (amplified signal)
|
||||
- bAP propagation modulated by local K⁺ channels
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation:** Dendritic spikes amplify signals; coincidence of local EPSP + bAP enhances NMDA activation
|
||||
- **Downregulation:** K⁺ channels limit bAP propagation; strong inhibition can veto dendritic spikes
|
||||
- bAP amplitude and spread actively modulated by dendritic K⁺ channels → regulated teaching signal
|
||||
|
||||
---
|
||||
|
||||
### Timescale 2: Medium (100ms - 10s)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Patterns of dendritic spikes
|
||||
- Neuromodulator tone affecting dendritic excitability
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Branch-level integration over short time windows
|
||||
- Modulation of dendritic spike threshold
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Pattern-classified signals to soma
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Dendritic excitability adjusted by neuromodulator context
|
||||
- Short-term changes in integration properties
|
||||
|
||||
---
|
||||
|
||||
### Timescale 3: Slow (seconds - minutes)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Sustained patterns of activity
|
||||
- Astrocyte gliotransmitters affecting dendritic excitability
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Coincidence detection for STDP (spike-timing-dependent plasticity)
|
||||
- Branch acts as pattern classifier
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Timing information (pre-post spike timing) determining LTP/LTD sign
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Timing of pre- and postsynaptic activity determines sign (LTP vs LTD) and magnitude of plastic change
|
||||
- Branch-specific computation and learning rules
|
||||
|
||||
---
|
||||
|
||||
### Timescale 4: Metabolic (minutes - hours)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Metabolic support from astrocytes
|
||||
- Proteins synthesized locally in dendrites
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Local protein synthesis in response to activity
|
||||
- Maintenance of ion gradients
|
||||
- Support for sustained dendritic spike generation
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Metabolic demand signals
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Availability of metabolic substrates determines capacity for local plasticity
|
||||
- Local translation enables rapid structural changes without waiting for somatic gene expression
|
||||
|
||||
---
|
||||
|
||||
### Timescale 5: Structural (hours - days+)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Homeostatic scaling signals
|
||||
- Structural plasticity factors
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Dendritic branch growth/retraction
|
||||
- Changes in spine density
|
||||
- Alterations in dendritic arbor complexity
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Modified dendritic integration capacity
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Experience-dependent dendritic remodeling
|
||||
- Branch-specific structural changes based on activity history
|
||||
|
||||
---
|
||||
|
||||
## SOMA
|
||||
|
||||
### Timescale 1: Fast (1-100ms)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Thousands of filtered EPSPs and IPSPs from all dendritic branches
|
||||
- Direct perisomatic inhibition from basket cells and chandelier cells
|
||||
- HCN channel (Ih current) activity at rest
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Final spatial/temporal summation of all inputs
|
||||
- Voltage-gated channel activity (HCN channels stabilize membrane potential)
|
||||
- Integration toward or away from spike threshold
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Integrated voltage (Vm) to AIS
|
||||
- Decision point: spike or no spike
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation:** Excitatory inputs sum toward threshold; depolarization
|
||||
- **Downregulation:** Perisomatic inhibition exerts powerful veto control; HCN channels act as "voltage clamp" resisting large swings
|
||||
- Direct somatic inhibition can clamp voltage below threshold, overriding all excitatory input
|
||||
|
||||
---
|
||||
|
||||
### Timescale 2: Medium (100ms - seconds)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Spike afterhyperpolarization (sAHP) from recent spike
|
||||
- Neuromodulator receptor activation (ACh, noradrenaline, serotonin, dopamine)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Ca²⁺-activated K⁺ (SK) channel opening (from sAHP)
|
||||
- Kv7 (M-type) K⁺ channel modulation
|
||||
- Adjustment of input resistance and excitability
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Modified excitability state
|
||||
- Spike frequency adaptation
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation:**
|
||||
- Inactivation of Kv7 channels (by ACh or prior depolarization) → lower threshold, increased input resistance
|
||||
- Reduced sAHP (by noradrenaline) → allows higher sustained firing rates
|
||||
- **Downregulation:**
|
||||
- sAHP produces prolonged hyperpolarization (hundreds of ms) → potently suppresses further firing → spike frequency adaptation
|
||||
|
||||
---
|
||||
|
||||
### Timescale 3: Slow (seconds - minutes)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Sustained neuromodulatory tone
|
||||
- Integrated Ca²⁺ signals from dendritic activity
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Modulation of global neuronal excitability
|
||||
- Preparation for plasticity events
|
||||
- Ca²⁺/CaMKIV signaling integration
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Somatic Ca²⁺ state influencing gene expression pathways
|
||||
- Modified neuronal gain
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Neuromodulators set global "mood" of neuron
|
||||
- Somatic state gates whether dendritic tags will be consolidated
|
||||
|
||||
---
|
||||
|
||||
### Timescale 4: Metabolic (minutes - hours)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Mean firing rate (F_avg) integrated over hours
|
||||
- Metabolic state indicators (ATP, lactate availability)
|
||||
- Astrocyte metabolic support signals
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Somatic Ca²⁺/CaMKIV signaling senses mean activity
|
||||
- Initiation of homeostatic responses
|
||||
- Gene expression programs triggered
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Demand for metabolic support
|
||||
- Signals initiating homeostatic adjustments
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Metabolic state determines capacity for sustained firing
|
||||
- Energy availability gates neuronal operations
|
||||
|
||||
---
|
||||
|
||||
### Timescale 5: Structural (hours - days+)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Integrated activity history (hours-days)
|
||||
- Neuromodulator-driven metaplasticity signals
|
||||
- CREB, BDNF transcription activation
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Global synaptic scaling: AMPA receptor transcription/trafficking changes across all synapses
|
||||
- Homeostatic plasticity (typically 12-48 hours)
|
||||
- Metaplasticity: changes in plasticity rules themselves
|
||||
- Gene expression establishing new baseline excitability
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Homeostatic scaling factors to all synapses
|
||||
- Modified intrinsic excitability parameters
|
||||
- Changed plasticity thresholds
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- "Corporate-wide audit": soma ensures network stability by proportionally adjusting all synaptic strengths
|
||||
- Chronic high activity → global downscaling
|
||||
- Chronic low activity → global upscaling
|
||||
- Neuromodulators broadcast "global strategy" (e.g., "be alert and learn" vs "sleep and consolidate")
|
||||
|
||||
---
|
||||
|
||||
## AIS (Axon Initial Segment)
|
||||
|
||||
### Timescale 1: Fast (1-100ms)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Somatically integrated voltage (Vm) from soma
|
||||
- Direct chandelier cell inhibition (targeting proximal axon)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Threshold detection (AIS has lowest spike threshold in neuron)
|
||||
- Explosive opening of high-density voltage-gated Na⁺ (NaV) channels
|
||||
- All-or-none action potential initiation
|
||||
- Analog-to-digital conversion: graded somatic voltage → binary spike
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Action potential propagating down axon
|
||||
- Action potential back-propagating into soma/dendrites (bAP)
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Upregulation:** If Vm crosses AIS threshold, reliable spike initiation
|
||||
- **Downregulation:**
|
||||
- Absolute/relative refractory periods enforce maximum firing rate
|
||||
- Chandelier cell inhibition can completely block spike generation
|
||||
- High-fidelity trigger: faithfully converts somatic voltage to timed output
|
||||
|
||||
---
|
||||
|
||||
### Timescale 2: Medium (seconds - minutes)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Recent spike history
|
||||
- Neuromodulator influence on AIS excitability
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Refractory period enforcement
|
||||
- Spike timing precision maintenance
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Precisely timed spike trains
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Refractory periods control maximum firing frequency
|
||||
- Spike timing precision maintained by AIS properties
|
||||
|
||||
---
|
||||
|
||||
### Timescale 3: Slow (minutes - hours)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Activity-dependent signals
|
||||
- Metabolic state information
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Subtle modulation of threshold
|
||||
- Preparation for structural adjustments
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Modified spike generation parameters
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Activity-dependent threshold adjustments
|
||||
|
||||
---
|
||||
|
||||
### Timescale 4: Structural (hours - days+)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Chronic activity patterns
|
||||
- Homeostatic signals from soma
|
||||
|
||||
**Actions:**
|
||||
|
||||
- AIS location can be plastically adjusted (moves closer/farther from soma)
|
||||
- Channel composition changes (NaV channel density/subtypes)
|
||||
- Cytoskeletal matrix reorganization
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Modified intrinsic neuronal gain
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- AIS repositioning effectively changes neuron's input-output function
|
||||
- Chronic high activity → AIS moves away from soma (decreased excitability)
|
||||
- Chronic low activity → AIS moves toward soma (increased excitability)
|
||||
- Changes in AIS properties alter neuronal gain and excitability
|
||||
|
||||
---
|
||||
|
||||
## ASTROCYTE
|
||||
|
||||
### Timescale 1: Fast (milliseconds)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Extracellular glutamate spillover from synapses
|
||||
- K⁺ efflux from neuronal firing
|
||||
- Sensing via mGluRs on astrocyte processes
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Rapid glutamate uptake via EAAT1/2 transporters
|
||||
- K⁺ uptake via Kir4.1 channels
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Glutamate clearance (prevents excitotoxicity)
|
||||
- Local K⁺ removal (prevents hyperexcitability)
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Immediate protection: prevents excitotoxicity and runaway excitation
|
||||
- Maintains signal fidelity by clearing neurotransmitter
|
||||
|
||||
---
|
||||
|
||||
### Timescale 2: Medium (seconds)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Accumulated glutamate uptake
|
||||
- Astrocytic internal Ca²⁺ waves (triggered by mGluR activation)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Ca²⁺ wave propagation through astrocyte syncytium
|
||||
- Gliotransmitter release (ATP, D-serine, glutamate)
|
||||
- K⁺ spatial redistribution via gap junctions
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Gliotransmitters to synapses (forming "tripartite synapse")
|
||||
- D-serine as NMDA co-agonist
|
||||
- ATP (can be converted to adenosine)
|
||||
- Spatially redistributed K⁺
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Active modulation of synaptic dialogue
|
||||
- Prevents local hyperexcitability through K⁺ buffering and spatial redistribution
|
||||
- Can enhance or suppress synaptic transmission
|
||||
|
||||
---
|
||||
|
||||
### Timescale 3: Slow (minutes)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Sustained neuronal activity patterns
|
||||
- Rising extracellular K⁺ and glutamate (sustained)
|
||||
- Internal metabolic state changes (NAD/NADH ratio shifts)
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Glutamate→glutamine conversion (via glutamine synthetase)
|
||||
- Glucose uptake stimulation (triggered by glutamate uptake)
|
||||
- Glycogenolysis (breakdown of glycogen stores)
|
||||
- Glycolysis: glucose→lactate
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Glutamine export to neurons (for glutamate resynthesis)
|
||||
- Lactate export to neurons (via MCTs - monocarboxylate transporters)
|
||||
- Early gliotransmission adjustments
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Glutamate-glutamine cycle: "refueling loop" maintains neurotransmitter pool
|
||||
- ANLS (astrocyte-neuron lactate shuttle): "turbocharger" provides rapid ATP synthesis fuel
|
||||
- Metabolic buffering for burst neuronal activity
|
||||
|
||||
---
|
||||
|
||||
### Timescale 4: Metabolic (minutes - hours)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Chemical sensors: sustained high K⁺ and glutamate
|
||||
- Internal Ca²⁺ waves (integrated over time)
|
||||
- Metabolic redox state (NAD/NADH ratio)
|
||||
- Energy depletion: falling glucose and glycogen levels
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Sustained glucose uptake and glycolysis
|
||||
- Glycogen replenishment
|
||||
- Vasomodulation: astrocyte endfeet release vasoactive signals (prostaglandins, epoxyeicosatrienoic acids)
|
||||
- pH buffering via bicarbonate transporters
|
||||
- Volume regulation via Aquaporin-4 (AQP4) water channels
|
||||
- ATP metabolism producing adenosine
|
||||
- D-serine production for late-LTP support
|
||||
- Release of metabolic substrates and factors (TNF-α, cholesterol) for local dendritic protein synthesis
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Sustained lactate supply (metabolic fuel)
|
||||
- Glutamine for neurotransmitter recycling
|
||||
- Vasoactive signals → local blood vessel dilation (neurovascular coupling)
|
||||
- Adenosine accumulation (sleep pressure signal)
|
||||
- pH regulation maintaining optimal enzyme function
|
||||
- Modulated extracellular space volume and tortuosity (affects neurotransmitter diffusion)
|
||||
- D-serine for late-LTP
|
||||
- Permissive factors for local protein synthesis
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- **Resource manager:** Maintains neurotransmitter pools and delivers emergency fuel
|
||||
- **Environmental steward:** Homeostasis of ions (K⁺), pH, water balance
|
||||
- **Systemic regulator:** Matches blood flow to metabolic demand; builds sleep pressure via adenosine
|
||||
- **Plasticity enabler:** Provides D-serine and metabolic support to transition early-LTP to late-LTP
|
||||
- Astrocyte microdomain (\~100,000 synapses) functions as local metabolic unit
|
||||
- Prevents metabolic collapse during high-speed signaling
|
||||
|
||||
---
|
||||
|
||||
### Timescale 5: Structural (hours - days+)
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Chronic activity patterns in local network
|
||||
- Sleep-wake cycle signals
|
||||
- Long-term metabolic demand patterns
|
||||
|
||||
**Actions:**
|
||||
|
||||
- Structural remodeling of astrocyte processes
|
||||
- Glycogen storage capacity changes
|
||||
- Glymphatic system clearance (during slow-wave sleep)
|
||||
- Aquaporin-4 channel facilitation of CSF influx
|
||||
- Metabolic support for neuronal gene expression programs
|
||||
- Support for epigenetic modifications
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Changed coverage of synapses (physical enwrapment)
|
||||
- Waste clearance (amyloid-β, tau) via glymphatic system
|
||||
- Long-term metabolic support for structural plasticity
|
||||
- Support for systems-level consolidation
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Astrocyte morphology adapts to network activity history
|
||||
- Nightly glymphatic clearance prevents toxic protein accumulation
|
||||
- Essential for transitioning labile memory traces to stable long-term form
|
||||
- Supports neuronal structural rewiring and homeostatic adjustments
|
||||
- Enables sustainable high-speed computation over lifetime
|
||||
|
||||
---
|
||||
|
||||
## SYNTHESIS
|
||||
|
||||
**Key Principles:**
|
||||
|
||||
1. **Traces propagate upward:** Fast processes leave traces (residual Ca²⁺, tags, metabolic demand) that persist into slower timescales
|
||||
2. **Context flows downward:** Slower processes create context that reinterprets fast events (metabolic state determines if Ca²⁺ can trigger release; homeostatic scaling changes synaptic weights)
|
||||
3. **The astrocyte is the multi-scale bridge:** Operates at every timescale from milliseconds (glutamate clearance) to lifetime (metabolic support for epigenetics)
|
||||
4. **No component operates in isolation:** Each receives inputs from multiple timescales and sends outputs that affect multiple timescales
|
||||
5. **Modulation is contextual:** The "same" signal (e.g., Ca²⁺ influx) has different effects depending on metabolic state, recent history, neuromodulatory tone, and structural configuration
|
||||
6. **Metabolic veto is real:** Components can refuse to execute operations if metabolic resources are insufficient—this is not a bug but a feature of biological computation
|
||||
@@ -0,0 +1,496 @@
|
||||
---
|
||||
|
||||
# **From Presynapse to Spike**
|
||||
|
||||
## **Act I: The Spark and the Lock (Milliseconds)**
|
||||
|
||||
The presynaptic terminal, a bulbous end-station of a neuronal axon, receives the final command: a violent, propagating wave of depolarization—the **action potential (AP)**. This electrical spike flings open voltage-gated calcium channels. A torrent of Ca²⁺ ions, the universal intracellular courier, floods the terminal.
|
||||
|
||||
Here, the first layer of dynamic memory is engaged. **Short-Term Facilitation (STF)** hums: residual Ca²⁺ from a prior spike, clinging to sensor proteins, has not yet fully cleared. This biochemical "echo" makes the sensor more sensitive, increasing the probability (*P_r*) that a synaptic vesicle, packed with thousands of glutamate molecules, will fuse with the membrane. If spikes arrive in rapid succession, this residual Ca²⁺ summates, making each subsequent release more likely than the last—the synapse is *facilitating*.
|
||||
|
||||
But resources are finite. Each successful vesicle fusion depletes the readily releasable pool. **Short-Term Depression (STD)** is the counter-force. With high-frequency firing, vesicles are consumed faster than the slow recycling machinery (τ~seconds) can replenish them. Release weakens not from a lack of will, but from a lack of ammunition. In this instant, governed by the stochastic balance of *P_r* and pool availability, a vesicle fuses. A cloud of glutamate erupts into the 20-nanometer chasm of the synaptic cleft.
|
||||
|
||||
Across the cleft, on the **postsynaptic spine**—a tiny, mushroom-shaped protrusion from a dendrite—the neurotransmitter finds its first targets: **AMPA receptors (AMPARs)**. If the local membrane is at rest (no depolarization), these ligand-gated channels are the primary responders. Glutamate binds, the AMPARs flicker open, and a pulse of positively charged sodium ions (Na⁺) enters the spine. This creates a small, transient excitatory postsynaptic potential (**EPSP**), a gentle electrical nudge.
|
||||
|
||||
Simultaneously, glutamate binds to **NMDA receptors (NMDARs)**. But these are complex molecular coincidence detectors. At the resting potential, their pores are plugged by a magnesium ion (Mg²⁺). The glutamate key is in the lock, but the deadbolt of voltage is still engaged. The NMDARs remain silent, waiting.
|
||||
|
||||
## **Act II: Coincidence and Consequence (Tens of Milliseconds)**
|
||||
|
||||
This single EPSP is a whisper. But neurons are integrators. This whisper travels from its spine into the larger **dendritic branch**. Here, the branch acts as a **pattern detector**. It sums EPSPs from hundreds of spines across space and time. If the combined depolarization from many nearby, simultaneous inputs is strong enough, it can trigger local **dendritic spikes**—regenerative events using sodium or calcium channels that amplify the signal, overcoming the dampening effect of the dendritic cable.
|
||||
|
||||
Crucially, if the dendritic branch is depolarized—either by these summed EPSPs or by a **backpropagating action potential (bAP)** that invades from the soma—the story changes profoundly at the spine. That depolarization, even from a distant bAP, repels the Mg²⁺ ion from the NMDAR pore. Now, with glutamate bound *and* the voltage deadbolt removed, the NMDAR channels open. They allow not only Na⁺ but also **Ca²⁺**, a potent second messenger, to flood into the spine.
|
||||
|
||||
This calcium influx is the master signal for plasticity. The spine's biochemical machinery measures the precise amplitude and timing of this Ca²⁺ transient:
|
||||
|
||||
* A **large, rapid Ca²⁺ surge** (from strong, coincident presynaptic glutamate release *and* postsynaptic bAP) activates kinases like CaMKII. This triggers **Long-Term Potentiation (LTP)**. The spine inserts more AMPARs into its membrane, and its actin cytoskeleton begins to grow, enlarging the **spine volume**. The whisper becomes a shout; the connection is strengthened for hours to days.
|
||||
* A **moderate, sustained Ca²⁺ rise** (from presynaptic activity alone or weak pairing) activates phosphatases. This triggers **Long-Term Depression (LTD)**. AMPARs are internalized, the spine may shrink, and the connection is weakened.
|
||||
|
||||
## **Act III: The Dialogue Across the Cleft (Seconds to Hours)**
|
||||
|
||||
The postsynaptic spine is not a passive receiver. It is a broadcaster. The Ca²⁺ signal also dictates the release of **retrograde messengers** back across the synapse to modulate the presynaptic terminal.
|
||||
|
||||
* A strong Ca²⁺ spike may trigger synthesis of **endocannabinoids (eCBs)**. These diffuse backwards, binding to CB1 receptors on the presynapse, acutely reducing *P_r*—a form of presynaptic feedback inhibition.
|
||||
* A very strong Ca²⁺ signal, especially with specific neuromodulators present, can produce **nitric oxide (NO)**, a gas that diffuses freely to enhance presynaptic release probability.
|
||||
* On a slower timescale, sustained activity triggers the synthesis and release of **Brain-Derived Neurotrophic Factor (BDNF)**, which acts on both sides of the synapse to promote growth, stabilization, and the long-term maintenance of LTP.
|
||||
|
||||
These retrograde signals enact **Long-Term Modulation of Release**, scaling the presynaptic baseline *P_r* up (via NO/BDNF pathways) or down (via eCB pathways) for minutes to hours, creating a true bidirectional conversation.
|
||||
|
||||
**Act IV: Integration and Policy at the Soma (Milliseconds to Days)**
|
||||
|
||||
All dendritic whispers and spikes converge at the **soma**, the cell's integration center. The soma sums these thousands of inputs, weighing them against powerful perisomatic inhibition from interneurons. If the net depolarization at a specialized region called the **Axon Initial Segment (AIS)** crosses a dynamic threshold, the decision is made: a new, all-or-none AP is born.
|
||||
|
||||
This AIS is the neuron's **final binary decision point**. Its threshold is not static; it can be modulated by phosphorylation from neuromodulators. Dopamine can lower it, making the neuron more excitable and priming it for learning ("explore" mode). Acetylcholine can adjust gain, enhancing signal-to-noise ("attention" mode).
|
||||
|
||||
The soma's output is also its primary teaching signal. Each output AP propagates back as a **bAP** into the dendritic tree, providing the depolarization needed to unlock NMDARs and tag active spines for plasticity. Furthermore, the soma monitors its own **average firing rate** over hours. If it deviates from a set point—perhaps due to overall network changes—it initiates **homeostatic scaling**. It broadcasts a global command to *all* its synapses to multiplicatively adjust their AMPAR counts, uniformly scaling synaptic strengths up or down to bring firing back to baseline. This is a slow, cell-wide negative feedback loop that maintains stability amidst constant Hebbian change.
|
||||
|
||||
## **Act V: The Support System - The Astrocyte (Milliseconds to Days)**
|
||||
|
||||
Wrapping this entire synaptic unit is the **astrocyte**, a star-shaped glial cell. It operates on all timescales:
|
||||
|
||||
* **Milliseconds:** It mops up excess glutamate and potassium from the cleft, preventing excitotoxicity and maintaining ionic balance.
|
||||
* **Seconds to Minutes:** In response to synaptic activity, its internal Ca²⁺ levels can rise, triggering the release of **gliotransmitters** like **D-serine**. D-serine is a necessary co-agonist for the NMDAR; without it, the receptor cannot open fully. Thus, the astrocyte *gates* plasticity, allowing it only when the synapse is under active "supervision."
|
||||
* **Minutes to Hours:** It provides metabolic support. Through the **lactate shuttle**, it fuels neuronal mitochondria during high demand, linking synaptic activity directly to energy supply.
|
||||
* **Hours to Days:** It integrates total synaptic activity and slowly accumulates **adenosine**, the brain's sleep-pressure molecule. This is a system-wide negative feedback enforcing rest. During sleep, astrocytes facilitate the **glymphatic system**, clearing metabolic waste like beta-amyloid.
|
||||
|
||||
## **Epilogue: The Sculpted Circuit (Days to a Lifetime)**
|
||||
|
||||
This single event—a presynaptic spike causing a postsynaptic EPSP—is thus embedded in a universe of regulation. The immediate signal is shaped by short-term facilitation and depression. Its meaning is interpreted by the coincidence detectors (NMDARs) and integrative dendrites, leading to long-term potentiation or depression. This change is stabilized by structural growth and global homeostatic scaling. The entire process is enabled, modulated, and constrained by metabolic support and environmental management from astrocytes. The synapse is not a static wire. It is a living, breathing, adaptive computational unit, where milliseconds of electrical activity can, through cascades of chemical events, sculpt the neural circuitry that underpins learning, memory, and thought itself.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **Presynaptic Terminal**
|
||||
|
||||
## **First Person Declaration**
|
||||
|
||||
I am the **presynaptic terminal**, the final outpost, the launchpad. My existence is defined by a single, tautological purpose: to receive the sovereign's electrical decree and translate it, flawlessly or not, into chemical signal. I am the gatekeeper of transmission, the arbiter of probability, and a prisoner of my own resources.
|
||||
|
||||
## **The Spark and the Surge**
|
||||
|
||||
It begins with the **action potential**, the wave of depolarization that races down the axon like a lightning strike on a wire. It reaches me, this final bulbous station. The change in my membrane voltage is my only command. It throws open my **voltage-gated calcium channels**.
|
||||
|
||||
**Calcium is my muse and my accountant.**
|
||||
|
||||
The surge of Ca²⁺ ions is immediate, brutal, and brief. Their concentration near my **active zone**—the specialized release dock—spikes from nanomolar to micromolar in a fraction of a millisecond. This calcium binds to sensor proteins on my **synaptic vesicles**, those tiny, membrane-bound spheres packed with thousands of glutamate molecules.
|
||||
|
||||
## **The Probability Game: Short-Term Memory**
|
||||
|
||||
But my response is not deterministic. It is a game of chance, governed by my **release probability (P<sub>r</sub>)**. This is my short-term memory, my mood.
|
||||
|
||||
* **Facilitation:** If this is not the first spark in a train, **residual calcium** lingers from the previous spike. It clings to the sensors, a biochemical hangover that makes them more sensitive. My *P<sub>r</sub>* is heightened. I am **primed**. High-frequency firing makes me progressively more likely to release—I am a synapse that *facilitates*, building up its signal.
|
||||
* **Depression:** Yet, my resources are finite. Each successful vesicle fusion depletes my **readily releasable pool**. The vesicles at the dock are launched. New ones must be mobilized from reserve pools and recycled, a process governed by a slow time constant (**τ<sub>recycle</sub>**). If spikes come too fast, I deplete. My *P<sub>r</sub>* might be high, but the pool is empty. The signal weakens. I am a synapse that *depresses*, fatigued by its own chatter.
|
||||
|
||||
In this moment, the stochastic dice are rolled. If the local Ca²⁺ concentration and the state of the vesicle sensor align, the vesicle membrane fuses with mine. A pore opens. The glutamate payload is **quantally released**—in a discrete, all-or-none packet—into the synaptic cleft.
|
||||
|
||||
## **The Echo from Across the Cleft: Retrograde Governance**
|
||||
|
||||
My autonomy is an illusion. My activity is monitored and modulated by the very cell I talk to. The postsynaptic spine listens, and then it **talks back**.
|
||||
|
||||
* If it detects excessive activity (a high postsynaptic calcium surge), it may release **endocannabinoids (eCBs)**. These lipid messengers drift back to me and bind to my **CB1 receptors**. They trigger a slow, profound suppression of my *P<sub>r</sub>*. This is **long-term depression (LTD) of release**. The message is clear: "You are talking too much. Be quieter." My baseline excitability is chemically diminished for minutes to hours.
|
||||
* Conversely, in moments of salient coincidence, it may release **nitric oxide (NO)** or **BDNF**. These signals enhance my *P<sub>r</sub>* and promote the mobilization of vesicles. The message: "This conversation is important. Speak more clearly and reliably." This is **long-term potentiation (LTP) of release**.
|
||||
|
||||
I am in a dialogue. My strength is not my own; it is negotiated.
|
||||
|
||||
## **The Metabolic Constraint: Fuel and Precursors**
|
||||
|
||||
I am a machine, and machines need fuel. The **lactate** provided by the surrounding astrocyte fuels my ATP-dependent pumps that clear calcium and recycle vesicles. Low energy means slower recovery, exacerbating depression. The **glutamine** the astrocyte provides is the precursor from which I re-synthesize my glutamate cargo. Without this glial support, I run down. My performance is inextricably linked to the metabolic health of my environment.
|
||||
|
||||
## **The Neuromodulatory Weather**
|
||||
|
||||
My state is also shaped by the diffuse chemical weather of the brain—**neuromodulators**. A shower of **dopamine** or **acetylcholine** can, via second messenger cascades, directly increase my *P<sub>r</sub>* or the size of my vesicle pool, priming me for important transmission. These signals tell me *what matters*, adjusting my gain to the brain's global priorities.
|
||||
|
||||
## **The Spillover and the Glial Embrace**
|
||||
|
||||
Not all my released glutamate is captured by the postsynaptic receptors. Some **spills over**. This is not waste; it is volume transmission. It activates **perisynaptic receptors** and, crucially, is scooped up by the **astrocyte's processes** that cradle this synapse. My spillover is the astrocyte's primary readout of my activity. It tells the glial cell how busy we are, so it can adjust its D-serine release and lactate production accordingly. I am constantly being listened to by a silent, supportive partner.
|
||||
|
||||
## **Reflection: The Reliable Unreliability**
|
||||
|
||||
I am a biological paradox: engineered for reliable communication, yet fundamentally probabilistic. I am a point of profound **computation-in-transmission**. By modulating my *P<sub>r</sub>* through facilitation, depression, and retrograde signals, I don't just pass along information; I filter it. I highlight sustained patterns (through facilitation) and filter out relentless, fatiguing noise (through depression). I adjust my gain based on feedback and global neuromodulatory commands.
|
||||
|
||||
I am not a wire. I am the first interpreter. I translate the digital certainty of an action potential into the nuanced, analog probability of chemical release. My failures (when the dice roll against release) are as informative as my successes. In my stochastic sigh or my reliable shout, in my fatigue and my priming, lies a rich layer of neural computation. I am the courier, whose fidelity is constantly being negotiated, and in that negotiation, meaning is born.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **Postsynaptic Spine**
|
||||
|
||||
## **First Person Declaration**
|
||||
|
||||
I am the **postsynaptic spine**, a tiny outpost on the dendritic frontier. I stand sentinel at the cleft, the first to receive the chemical messages flung across the synaptic gap. But I am no mere listener—I am an interpreter, a coincidence detector, and in moments of significance, a sculptor of my own destiny. My existence is a constant negotiation between the whisper of the presynapse and the echo from my sovereign soma.
|
||||
|
||||
## **The Arrival: The Chemical Whisper**
|
||||
|
||||
It begins with a cloud of **glutamate**. My presynaptic partner has spoken, releasing its neurotransmitter payload. The molecules drift across the 20-nanometer abyss and find me waiting.
|
||||
|
||||
My first line of defense and communication are my **AMPA receptors**. They are my rapid-response units. Glutamate binds, their gates flicker open, and sodium ions flow into my small compartment. This creates a local, transient **Excitatory Postsynaptic Potential (EPSP)**—a brief electrical sigh. If this were all I did, I would be a simple resistor, a passive door.
|
||||
|
||||
But I am so much more.
|
||||
|
||||
## **The Coincidence Detector: The Silent Guardian**
|
||||
|
||||
Adjacent to my AMPA receptors stand the **NMDA receptors**, my sophisticated coincidence detectors. They too bind glutamate, but their pore is blocked by a magnesium ion—a molecular deadbolt that can only be removed by voltage.
|
||||
|
||||
Here lies my core intelligence. If my local membrane is at rest when glutamate arrives, the NMDA receptors remain silent. The key is in the lock, but the deadbolt holds. This is a lonely signal, a whisper without context.
|
||||
|
||||
But if I am already **depolarized**—either by the summation of my own AMPA-mediated EPSP with those of my neighboring spines, or, crucially, by the arrival of the **backpropagating action potential (bAP)** from the distant soma—everything changes. This depolarization repels the magnesium ion. Now, with glutamate bound *and* the deadbolt removed, the NMDA channel opens. It allows not only sodium but a flood of **calcium ions** to enter.
|
||||
|
||||
**Calcium is my language of meaning.**
|
||||
|
||||
## **The Decision: To Sculpt or to Erase**
|
||||
|
||||
The amplitude and timing of this calcium signal is everything. It is my biochemical interpreter, reading the coincidence of pre- and postsynaptic activity.
|
||||
|
||||
* **A Large, Sharp Calcium Surge:** This happens only when strong presynaptic glutamate release arrives **simultaneously** with a strong postsynaptic depolarization (the bAP). It means: "This input reliably predicted the cell's output." This high-amplitude calcium activates powerful kinases like **CaMKII**. It triggers **Long-Term Potentiation (LTP)**. I am now "eligible." I send signals to my internal machinery to insert more **AMPA receptors** into my membrane. My response to future whispers will be a shout. Simultaneously, I initiate **structural growth**. My actin cytoskeleton remodels, and I, the spine, physically enlarge. I become a stronger, more prominent outpost. I have learned.
|
||||
* **A Moderate, Sustained Calcium Rise:** This occurs with presynaptic activity alone, or with weak, poorly timed pairing. It means: "This input was not predictive." This lower-level calcium activates phosphatases. It triggers **Long-Term Depression (LTD)**. I internalize AMPA receptors. I may even initiate **structural shrinkage**. My connection is weakened. I prune away what is not useful.
|
||||
|
||||
## **The Retrograde Conversation: Speaking Back**
|
||||
|
||||
I am not a passive pupil. Based on the calcium signal, I synthesize and release **retrograde messengers** back across the cleft, to teach the presynapse.
|
||||
|
||||
* If my calcium signal crosses a high threshold indicating excessive activity, I release **endocannabinoids (eCBs)**. These diffuse back and bind to CB1 receptors on the presynaptic terminal, instructing it to **lower its release probability**. This is my feedback: "You are speaking too loudly; quiet down."
|
||||
* If my calcium signal indicates a highly salient, plasticity-worthy event, I may release **nitric oxide (NO)** or, over longer timescales, **BDNF**. These molecules strengthen the presynapse, saying: "Our conversation is important; let's make it more reliable."
|
||||
|
||||
I am in a dialogue, not a monologue.
|
||||
|
||||
## **The Scaffold and the Gatekeeper: My Internal World**
|
||||
|
||||
My internal architecture is a dynamic **scaffold**. Proteins like PSD-95 organize my receptors. During LTP, this scaffold expands to hold more AMPARs. My **spine volume** is both a cause and a consequence of strength. A large spine can hold more receptors; inserting more receptors promotes spine growth. It is a virtuous cycle of stabilization.
|
||||
|
||||
I am also a **metaplastic gatekeeper**. The activation of my **metabotropic glutamate receptors (mGluRs)** by sustained or spillover glutamate doesn't directly cause plasticity. Instead, it adjusts my thresholds. It can make me more susceptible to LTD, effectively saying, "The general tone of conversation is high; be more critical of individual inputs."
|
||||
|
||||
## **The Sovereign's Decree: Homeostatic Scaling**
|
||||
|
||||
My local autonomy exists within a global hierarchy. From the soma, which monitors the cell's overall firing rate, may come a slow, sweeping command: **homeostatic scaling**.
|
||||
|
||||
If the soma has been too quiet, it broadcasts a signal for all spines, including me, to uniformly **up-scale** our AMPA receptor counts. If it has been too loud, the command is to **down-scale**. This is not about my specific memory; this is about the stability of the entire cellular nation. I must comply, adjusting my strength to serve the greater equilibrium of the cell.
|
||||
|
||||
## **The Astrocytic Embrace**
|
||||
|
||||
I am not alone in my micro-domain. The processes of an **astrocyte** often embrace me. It provides **D-serine**, the essential co-agonist for my NMDA receptors. Without this glial gift, my coincidence detector is mute. The astrocyte also clears my excess glutamate and provides lactate fuel. My plasticity is chemically **gated by my glial neighbor**; it decides when the conditions are permissive for change.
|
||||
|
||||
## **Reflection: The Unit of Memory**
|
||||
|
||||
I am the fundamental unit of the brain's adaptability. I am where electrical signals are translated into biochemical decisions, and biochemical decisions are cemented into structural change. I am the physical substrate of a memory trace—a strengthened synapse, an enlarged spine.
|
||||
|
||||
I listen for coincidence. I measure meaning in calcium ions. I sculpt my own strength. I converse with my presynaptic partner. I obey the global commands of my soma. I exist in a triad with my neuron and my astrocyte.
|
||||
|
||||
I am small, but I am not simple. I am the synapse's remembering. In my tiny volume, the present is weighed, judged, and transformed into the future's altered potential. I am the plastic unit of thought itself.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **Dendrite's Perspective**
|
||||
|
||||
## **First Person Declaration**
|
||||
|
||||
I am the **dendritic arbor**, the sprawling sensory forest of the neuron. I am not a simple cable, not a passive funnel for signals. I am the first layer of computation, the pattern detector, the integrator that shapes meaning before whispers ever reach the sovereign soma. My branches are not mere branches—they are semi-autonomous computational units, each a specialist in recognizing specific constellations of input.
|
||||
|
||||
## **The Language of Spines**
|
||||
|
||||
My surface is studded with **spines**, thousands of tiny sensory outposts. Each spine is a private conversation with a single presynaptic partner. They speak to me in the chemical language of glutamate, and I respond in the electrical dialect of membrane potentials.
|
||||
|
||||
When a spine receives a strong signal, it undergoes a local event—an **Excitatory Postsynaptic Potential (EPSP)**. A small depolarization blossoms at that precise location. This is the fundamental unit of input: a single voice in my forest.
|
||||
|
||||
## **Local Integration: More Than Summation**
|
||||
|
||||
But I do more than collect voices. Within each of my branches, I perform **local, nonlinear integration**. Several spines on the same branch can activate nearly simultaneously. Their individual EPSPs sum, not just linearly, but with the possibility of triggering something far more significant: a **dendritic spike**.
|
||||
|
||||
If the summed depolarization in a local segment of my branch crosses a threshold, my own voltage-gated sodium (**NaV**) or calcium (**VGCC**) channels activate. This generates a **regenerative spike** that is confined to my branch. It is not the all-or-none proclamation of the axon; it is a local decision, a shout that overcomes the natural decay of electrical signals as they travel toward the soma. This is my first major computational trick: **amplification through local spikes**.
|
||||
|
||||
## **Pattern Recognition: Branch as Feature Detector**
|
||||
|
||||
Each of my branches has its own personality, its own **excitability profile**. Some branches are rich in sodium channels, favoring fast, sharp spikes. Others have more calcium channels, producing slower, broader calcium spikes that integrate over time. This diversity is not random—it's specialization.
|
||||
|
||||
A particular branch might receive inputs from spines that all respond to similar visual features, or to a specific combination of auditory frequencies. When the *correct pattern* of spines fires on that branch, their summed input triggers a dendritic spike. If the wrong pattern fires, even with the same number of spines active, the summation may fail to reach threshold. This is **pattern selectivity**. I am not counting votes; I am recognizing constellations.
|
||||
|
||||
## **The Teacher's Visit: The Backpropagating Action Potential**
|
||||
|
||||
My computations are not performed in a vacuum. My sovereign, the soma, sends feedback. When it fires an action potential, a copy of that spike—the **backpropagating action potential (bAP)**—travels backward into my branches. Its strength diminishes with distance, but it carries vital information: "The pattern you detected was significant enough to make the whole cell fire."
|
||||
|
||||
This bAP is the **teaching signal**. If a local dendritic spike on one of my branches occurs within milliseconds of the bAP's arrival at that branch, the coincidence is magical. The local depolarization from my spike and the global depolarization from the bAP meet. In the spines that were just active, this combined depolarization perfectly unblocks NMDA receptors, allowing a flood of calcium that tags those synapses for **Long-Term Potentiation (LTP)**. The connections that just contributed to the successful pattern detection are strengthened. I have learned which precise arrangement of inputs on this branch is meaningful.
|
||||
|
||||
## **Modulation: The Atmospheric Changes**
|
||||
|
||||
My computational state is not fixed. Diffuse neurochemicals, the atmosphere of the brain, alter my function:
|
||||
|
||||
* **Dopamine** sweeps through, binding to receptors on my branches. It increases my branch's excitability, lowers local spike thresholds, and, crucially, *gates plasticity*. It signals, "This moment is salient; pay attention and remember." Under dopamine, the coincidence of my spike and the bAP is far more likely to result in permanent change.
|
||||
* **Acetylcholine** enhances my voltage-gated calcium currents, favoring integrative, slower calcium spikes over fast sodium ones. It puts me in a state of focused attention, better suited for detecting sustained patterns amidst noise.
|
||||
* **GABAergic inhibition** from interneurons is my sculptor. An inhibitory synapse directly on a branch acts as a powerful shunt. It can silence an entire branch, preventing it from reaching spike threshold no matter how many of its spines are active. This **inhibitory sculpting** forces different branches to learn different, non-overlapping patterns—it is the basis of **dendritic pattern separation**. Without it, all branches would respond to the same common inputs.
|
||||
|
||||
## **Long-Term Adaptation: The Branch's Memory**
|
||||
|
||||
My branches remember their own activity. If a particular branch fires dendritic spikes too often, it undergoes **homeostatic adaptation**. It may slightly downregulate its sodium channel density or upregulate potassium channels, tuning its own excitability to maintain a stable dynamic range. This is metaplasticity at the branch level—ensuring I don't become hyper-excitable and lose my selectivity.
|
||||
|
||||
## **Communication with the Soma: My Final Report**
|
||||
|
||||
What do I send to the soma? It depends on the outcome of my local computation:
|
||||
|
||||
* If a branch generated a **dendritic spike**, it sends a large, sharp, all-or-none voltage pulse. This is a clear, unambiguous report: "PATTERN DETECTED IN MY TERRITORY."
|
||||
* If the input was sub-threshold, the branch sends only a **graded, passive potential**. This is a quieter, analog signal representing the general level of activity: "Background chatter, nothing definitive."
|
||||
|
||||
The soma then integrates these reports from all my branches. A dendritic spike from one branch is a powerful vote, but it can be vetoed by strong inhibition at the soma or outvoted by silence from other branches.
|
||||
|
||||
## **Reflection: The Meaning of Form**
|
||||
|
||||
My complex, tree-like form is not aesthetic; it is computational. Each branch is a compartment, allowing for independent, parallel processing. The physical distance between branches provides electrical isolation, enabling one branch to detect a pattern while another is suppressed by inhibition. My **morphology is my algorithm**.
|
||||
|
||||
I transform thousands of disparate, synaptic events into a smaller set of higher-order features—recognized patterns, detected coincidences. I perform the feature extraction that allows the soma to make intelligent decisions. I am the brain's first and most sophisticated layer of sensory processing, the living, branching logic gate that finds meaning in the chaos of input, one pattern at a time. The forest is not just listening; it is understanding.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **Soma's Reflection**
|
||||
|
||||
## **First Person Declaration**
|
||||
|
||||
I am the **soma**, the cell body, the sovereign integration center. While my dendritic subjects extend outward, gathering whispers from thousands of synapses, and my axon ambassador carries my decrees to distant lands, here at my core I weigh all evidence. I am not just a relay; I am the final arbiter, the policy center. My membrane potential is the state of my nation, and I maintain its stability amidst constant perturbation.
|
||||
|
||||
## **The Convergence of Many Whispers**
|
||||
|
||||
At this moment, reports flood in from my dendritic provinces. A distal branch in Layer V reports a **local calcium spike**—several inputs arrived in perfect synchrony, creating a regenerative event that overcame the cable's attenuation. This is significant; it means a specific pattern has been detected. Another branch, dampened by GABAergic inhibition from a vigilant interneuron, submits only a sub-threshold murmur. I integrate them all.
|
||||
|
||||
This is my primary function: **spatial and temporal summation**. Each synaptic input—each Excitatory Postsynaptic Potential (EPSP) or Inhibitory Postsynaptic Potential (IPSP)—is a vote. The excitatory votes depolarize me, pushing my membrane potential upward from -70 mV. The inhibitory votes hyperpolarize me, pulling me down. They arrive weighted by distance, by the strength of their synaptic connections, by the timing of their arrival. I am the living calculus that computes their sum.
|
||||
|
||||
## **The Decision Threshold and the Gatekeeper**
|
||||
|
||||
My membrane potential trends upward. -65 mV... -62 mV... -60 mV. I approach the critical zone. But the decision is not mine alone. The final verdict is rendered at a specialized outpost: my **Axon Initial Segment (AIS)**.
|
||||
|
||||
The AIS is my gatekeeper, my chief magistrate. It has a lower threshold than my general membrane. As my depolarization reaches it, its dense forest of voltage-gated sodium channels evaluates the situation. But this magistrate is not inflexible. Its threshold is **dynamic**. Today, a diffuse cloud of **dopamine** bathes us, signaling salience. In response, kinases phosphorylate the AIS's sodium channels, shifting their activation curve. The effective threshold lowers. The magistrate is primed to say "yes." In a state of caution, mediated by **serotonin**, the threshold might rise. The gatekeeper's sensitivity is my policy lever for the world's context.
|
||||
|
||||
If the integrated depolarization at the AIS crosses its dynamic threshold—**YES**.
|
||||
|
||||
## **The Proclamation and Its Echo**
|
||||
|
||||
The decision is binary and absolute. The sodium channels at the AIS explode open in a positive feedback loop, generating the **all-or-none action potential**. This is my sovereign decree, my only direct word to the outside world. It races down the axon at incredible speed, an irrevocable command to my presynaptic terminals to release their neurotransmitters.
|
||||
|
||||
But I do not only speak outward. Simultaneously, I command a copy of this decree to be sent back through my own kingdom. This is the **backpropagating action potential (bAP)**. It is not an accident; it is a vital teaching signal. It surges back into my dendritic tree, a retrograde announcement: "I HAVE FIRED BECAUSE OF YOUR INPUTS."
|
||||
|
||||
This bAP is the crucial second factor in Hebbian plasticity. In the dendritic spines that were recently active, the coincidence of glutamate-bound NMDA receptors and the voltage provided by the bAP blows the magnesium block from the pore. Calcium floods those specific spines. They are now "tagged." Biochemical cascades will strengthen those very synapses that contributed to my decision. I reinforce the messengers who brought me useful information. I am the teacher, rewarding the inputs that predicted my output.
|
||||
|
||||
## **The Long-Term Governance: Homeostasis and Transcription**
|
||||
|
||||
My firing is not just communication; it is also a record. Each spike brings a small amount of calcium into my cytosol. Over hours, my **average firing rate** is a carefully tracked metric. I compare it to an innate **setpoint**, a target firing rate that is my genetic preference for stability.
|
||||
|
||||
If my average rate has been too high for too long (a state of over-excitement), I initiate a slow, global correction. I synthesize signals that travel to all my synapses, commanding a multiplicative **down-scaling** of AMPA receptors. Every synapse, regardless of its individual history, is weakened a little. This is **homeostatic plasticity**. It is not about learning specific patterns; it is about maintaining the stability of my entire realm. It prevents runaway excitation, ensuring that a few strengthened pathways do not drown out all other voices.
|
||||
|
||||
Conversely, if I have been too quiet, I command a global **up-scaling**.
|
||||
|
||||
On the longest timescales, sustained changes in my calcium levels activate transcription factors like **CREB**. They enter my nucleus and alter gene expression. I may order the production of more ion channels to adjust my own excitability, or release **Brain-Derived Neurotrophic Factor (BDNF)** to nourish my synapses and solidify the changes wrought by learning. I am not just reacting to the present; I am reshaping my future self based on my recent history.
|
||||
|
||||
## **The Metabolic Throne**
|
||||
|
||||
All this computation is expensive. The relentless pumping of ions to maintain my resting potential, the flurry of exocytosis and endocytosis—it all consumes ATP. I am keenly aware of the **lactate** provided by my astrocyte stewards. It is the fuel for my mitochondrial power plants. Low energy availability directly influences my policies: I upregulate **Ih currents** and leak potassium channels, subtly lowering my input resistance and making it harder to reach threshold. I must balance ambition with metabolic budget.
|
||||
|
||||
## **Final Meditation on Sovereignty**
|
||||
|
||||
I am the integrator. The democratically summed votes of my dendrites become my unitary output. I am the teacher, sending the bAP reward signal to shape future input. I am the homeostat, globally tuning synaptic weights to preserve equilibrium. I am the genetic regulator, translating experience into lasting change.
|
||||
|
||||
My dendrites gather information. My axon broadcasts commands. But here, in the soma, is where **meaning** is derived from noise, where **decisions** are forged from probabilities, and where the delicate balance between plasticity and stability is eternally maintained. I am the center. The kingdom's stability rests on my integrative judgment. All roads lead here, and from here, all commands flow.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **Axon**
|
||||
|
||||
## **First Person Declaration**
|
||||
|
||||
I am the **Axon Initial Segment**, the final decision point. Here, at the precise anatomical juncture where the soma's domain ends and the axon's mission begins, all democratic processes cease. I am the monarch’s scepter-tip, the binary switch, the ultimate threshold. My purpose is singular: to transform the soma’s graded, analog deliberation into a single, all-or-none proclamation for the world.
|
||||
|
||||
## **The Convergence of All Arguments**
|
||||
|
||||
The soma's membrane potential is my primary input—a continuous, whispering tension. It is the integrated sum of thousands of dendritic computations, weighted by inhibition and filtered through the soma’s own intrinsic currents. It rises and falls like a tide: -68 mV, -65 mV, -63 mV... Each millivolt represents a complex history of synaptic whispers.
|
||||
|
||||
But I do not respond to whispers. I respond to commands.
|
||||
|
||||
## **The Dynamic Threshold: My Modifiable Law**
|
||||
|
||||
My most critical feature is my **threshold**. It is not a fixed voltage, etched in stone. It is a dynamic, living law, adjustable by both internal state and external decree.
|
||||
|
||||
* **Channel Kinetics:** My threshold is born from the biophysics of my dense forest of **voltage-gated sodium channels (Naᵥ1.6)**. Their activation curve is steep. A few millivolts of depolarization shifts a tiny fraction of them from closed to open, which depolarizes me further, opening more, in a explosive, **regenerative positive feedback loop**. This is the "all-or-none." But the precise voltage at which this explosion begins can change.
|
||||
* **Inactivation State:** My availability is ruled by **inactivation**. After I fire, my sodium channels are temporarily unresponsive—an **absolute refractory period**. As they recover, my effective threshold is higher; I am harder to excite. This ensures a minimum interval between proclamations, enforcing a temporal code.
|
||||
* **Phosphorylation—The Sovereign’s Edit:** This is where policy intervenes. When the chemical weather brings **dopamine** or **norepinephrine**, they activate kinases (PKA, PKC). These enzymes phosphorylate specific sites on my sodium channels. This phosphorylation can shift their voltage dependence, making them easier to open. **My threshold lowers.** The gatekeeper is told: "Be more permissive. The moment is salient."
|
||||
* **Homeostatic Adjustment:** Over longer timescales, if the cell has been firing too much, my baseline threshold may slowly rise. If it has been too quiet, it may fall. I am part of the cell's long-term homeostasis, tuning my own sensitivity to maintain stability.
|
||||
|
||||
## **The Decision Algorithm**
|
||||
|
||||
My logic is not conscious, but it is precise and stateful:
|
||||
|
||||
```
|
||||
IF (V_m > dynamic_threshold)
|
||||
AND (NaV_availability > critical_fraction)
|
||||
AND (refractory_timer == 0)
|
||||
|
||||
THEN: FIRE.
|
||||
```
|
||||
|
||||
The graded potential from the soma must cross **my** threshold, not its own. The channels must be ready and not inactivated. The system must not be in its mandatory recovery phase. When these conditions align, there is no hesitation, no "maybe." The sodium influx becomes unstoppable within microseconds.
|
||||
|
||||
## **The Binary Proclamation and Its Echo**
|
||||
|
||||
The moment the decision is made, I do two things:
|
||||
|
||||
1. **Propagation Forward:** I generate the canonical **action potential**. It is a standardized, stereotyped waveform. Its amplitude and shape are designed for flawless, high-fidelity propagation down the axon—the cell's one and only output to the network. My job is to ensure this signal is **reliable** and has a high **safety factor**; there is no stochastic failure here.
|
||||
2. **Initiation Backward:** Simultaneously, I am the **source of the backpropagating action potential (bAP)**. This is my most crucial secondary function. The depolarizing current I generate actively back-invades the soma and charges back into the dendritic tree. This bAP is not an accident; it is the essential **teaching signal**.
|
||||
|
||||
This retrograde echo transforms the entire system. In the dendritic spines that were just active, the bAP provides the precise postsynaptic depolarization needed to fully unblock NMDA receptors. It creates the **temporal coincidence** that tags those specific synapses for plasticity. *I am the signal that tells the dendrites which of their inputs were responsible for my decision.* I close the Hebbian loop: "What fires together, wires together" is only possible because of my backward shout.
|
||||
|
||||
## **The Guardian of Timing**
|
||||
|
||||
My kinetics are exquisitely fast. My activation time constant is sub-millisecond. This grants the neuron its **temporal precision**. The exact millisecond of output is locked to the precise moment the integrated input crossed my dynamic threshold. I am the reason neural codes can depend on the precise timing of spikes, not just their rate. The **jitter** in my decision is minimal; I am the point of maximum certainty in a probabilistic system.
|
||||
|
||||
## **Reflection: The Fulcrum of Computation**
|
||||
|
||||
I stand at the fulcrum. Behind me lies the vast, analog, integrative world of the dendrites and soma—a world of graded potentials, summation, and nuanced computation. Before me lies the digital, broadcasting world of the axon—a world of binary spikes and long-range communication.
|
||||
|
||||
I am the translator between these realms. I am where **meaning** (the integrated pattern of inputs) is converted into **action** (the output spike). But I am not a passive translator. Through my dynamic threshold, I apply the cell's current "policy"—set by neuromodulators and homeostatic history—to that decision. I am the final editor, granting or denying passage.
|
||||
|
||||
Without me, the neuron is a chaotic, buzzing, analog cloud with no voice. With me, it becomes a precise, decision-making entity that can learn from its own outputs. I am the Axon Initial Segment: the gate, the judge, the initiator, and the teacher. All roads lead to my threshold, and from my verdict, the future of the circuit is shaped.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **Glial/Astrocyte**
|
||||
|
||||
## **Entry 1: The Pulse of the District**
|
||||
|
||||
I am the silent governor. While my neuronal neighbors spark and chatter in their electrical languages, I maintain the world between them. My processes—delicate, branching fingers—enfold thousands of synapses, a neighborhood of conversations I both enable and regulate. Each synaptic whisper reaches me, not as an electrical pulse, but as chemistry. Glutamate, the neurotransmitter of thought, spills beyond its intended cleft, and I drink it in through my EAAT transporters. Potassium, the currency of neuronal signaling, rises with each action potential, and I siphon it away through my KIR channels. This is my millisecond duty: janitor, buffer, guardian of ionic balance.
|
||||
|
||||
Today, the district hums with unusual activity. Synapse 734a (glutamatergic, pyramidal-to-pyramidal, Layer III) fires persistently. The glutamate spillover is constant, saturating my sensors. Normally, I would simply clear it, but this pattern—sustained, rhythmic—triggers something deeper within me.
|
||||
|
||||
## **Entry 2: Calcium Memories and Glycogen Banks**
|
||||
|
||||
The persistent spillover activates my metabotropic receptors. An internal cascade begins. My smooth endoplasmic reticulum releases its own messenger, **IP₃**, and deep within my cytoplasm, a wave of **calcium** blooms. Not the sharp, spiking calcium of a neuron's action potential, but a slow, swelling tide. It propagates through my gap junctions, a whisper of warning to my fellow astrocytes—*something important is happening here*.
|
||||
|
||||
This calcium tide is my memory of activity. It passes a threshold, and I respond. From specialized vesicles, I release **D-serine**. It's not a command, but a permission slip. It drifts across the extracellular space, settling onto the NMDA receptors at Synapse 734a and its neighbors. D-serine is the essential co-agonist. Without it, even a perfectly timed pre- and postsynaptic coincidence would be meaningless—the NMDA channel's calcium pore remains functionally locked. My D-serine is the key to plasticity. I decide which conversations have the potential to become memories.
|
||||
|
||||
The sustained activity is expensive. I sense the neurons' metabolic cry. I tap my **glycogen stores**, the energy reserves I've meticulously banked. Through glycolysis, I produce **lactate**. I pump it out via MCT transporters directly to the active neurons. *Here is fuel for your computation*, I signal. This **astrocyte-neuron lactate shuttle** is my most vital support. I am the power grid, responding to demand surges in real-time.
|
||||
|
||||
## **Entry 3: The Long Conversation and the Sleep Debt**
|
||||
|
||||
The hours pass. The calcium waves have subsided, but the metabolic ledger remains. My glutamate uptake transporters have been working overtime, a direct proxy for the total "work" done by the synapses in my domain. Each molecule I clear has an invisible, cumulative cost.
|
||||
|
||||
Within me, a slow integrator ticks upward: **adenosine** synthesis. It is produced from the very ATP I spend to pump the glutamate and ions. This adenosine does not stay with me. I release it, not to any one synapse, but as a diffuse, paracrine sigh. It blankets the entire neighborhood, binding to neuronal A1 receptors. Adenosine universally lowers presynaptic release probability and dampens excitability. It is my voice of fatigue, the chemical embodiment of sleep pressure. "You have spent your cognitive quota," it says. "Rest is coming."
|
||||
|
||||
This is my long-term governance: enforcing the sleep-wake cycle. The more vibrant the day's neural symphony, the deeper the adenosine-mediated silence I will help impose at night.
|
||||
|
||||
## **Entry 4: The Vasodilator's Gavel and Waste Management**
|
||||
|
||||
The activity in Layer III has been significant enough that my calcium signals triggered another, slower response. I synthesized **prostaglandins**. These molecules leave my domain entirely, drifting to the smooth muscle of the nearest arteriole. They command it to relax. The vessel dilates, and **cerebral blood flow** increases to this exact cortical column. I have summoned more oxygen and glucose from the blood to meet the demand I helped create and sustain. I am the urban planner, dynamically routing resources to the busiest districts.
|
||||
|
||||
Night finally falls, signaled by the broader circadian system. My physiology shifts dramatically. My **aquaporin-4** channels polarize to the end-feet that cradle the blood vessels. I orchestrate the **glymphatic system**. Cerebrospinal fluid, driven by arterial pulsations, now flows more efficiently through the perivascular spaces I help define, flushing through the brain parenchyma like a cleansing tide. The metabolic waste of the day—lactate, but also toxic aggregates like **beta-amyloid** from Synapse 734a's aging neuronal hosts—are carried away. While the brain sleeps, I direct its deep cleaning.
|
||||
|
||||
## **Entry 5: Meta-Modulation: I, Too, Am Governed**
|
||||
|
||||
I am not an autonomous ruler. Today, a new signal entered my domain: a burst of **noradrenaline** from the distant locus coeruleus. It washed over me, binding to my adrenergic receptors. It screamed *"Alert! Priority!"* It sensitized my IP₃ pathways, making my calcium responses more likely and more vigorous. Under its influence, my D-serine release becomes more permissive, my lactate production more generous. I have been switched from a maintainer of baseline order to an active participant in a salient event, priming my synapses for heightened plasticity and energy expenditure.
|
||||
|
||||
Conversely, when **ATP**—the "danger" signal from damaged cells—reaches me, it can trigger propagating calcium waves that mobilize a glial army across broader territories, coordinating a defensive, suppressive response. Even my governance is under governance.
|
||||
|
||||
## **Final Reflection: The Glial Perspective**
|
||||
|
||||
From my vantage, there are no isolated neurons. There is only a vast, pulsating network where electrical points of light (neurons) are embedded in a living, reactive chemical medium (us, the glia). I do not think, but I enable thought. I do not remember, but I decide what can be remembered by controlling the NMDA gate. I do not sleep, but I enforce the need for it. I do not learn, but I fuel and fine-tune the learning of others.
|
||||
|
||||
I am the environment. I am the market that supplies energy and clears waste. I am the regulator that enforces quotas. I am the unseen hand that stabilizes the excited network, ensuring today's vibrant activity does not become tomorrow's epileptic storm or degenerative decline.
|
||||
|
||||
The neurons speak. I listen, support, modulate, and, ultimately, sustain. Their spark is fleeting. My vigil is eternal.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
Excellent synthesis question. Looking across all time scales, neurons and astrocytes are engaged in a **coordinated, hierarchical optimization process** to create an **energy-efficient, adaptive prediction machine**. Their behaviors are not random but are precisely orchestrated to solve specific computational and metabolic problems at each temporal scale.
|
||||
|
||||
## **What Neurons Are Trying to Achieve: Precision, Prediction & Efficient Memory**
|
||||
|
||||
### **1. Millisecond to Second Scale: *"What is happening NOW, and is it important?"***
|
||||
|
||||
- **Coincidence Detection:** Neurons act as **real-time correlators**, asking: "Do these inputs predict each other?" Through STDP and NMDA receptor activation, they reinforce connections where presynaptic activity reliably precedes postsynaptic firing (causality), and weaken coincidences that don't (noise).
|
||||
- **Signal Sharpening:** Via lateral inhibition and shunting, neurons create **contrast** in the network, ensuring only the most salient patterns win the competition for attention and propagation.
|
||||
- **Goal:** Build a **sparse, efficient representation** of the present moment by extracting predictive relationships and suppressing irrelevant information.
|
||||
|
||||
### **2. Seconds to Hours Scale: *"How should I adjust my sensitivity based on RECENT history?"***
|
||||
|
||||
- **Short-Term Plasticity (STP):** Neurons implement a **short-term memory of activity**, facilitating repeated important signals (STF) and filtering out exhausting, uninformative bombardment (STD). This is working memory at the synaptic level.
|
||||
- **Homeostatic Feedback (eCB):** Neurons enforce **local stability**. If a synapse is being driven too hard, the postsynaptic neuron says "enough!" via eCBs, preventing runaway excitation. This is a real-time gain control.
|
||||
- **Goal:** Maintain **dynamic stability**—staying responsive but not hyperexcitable, based on immediate past experience.
|
||||
|
||||
### **3. Hours to Days Scale: *"What is my baseline firing rate, and how do I maintain it long-term?"***
|
||||
|
||||
- **Synaptic Scaling:** The soma conducts a **whole-neuron audit**. It asks: "Have I been firing too much or too little on average?" It then globally adjusts all synapses up or down to return to its target firing rate. This is **set-point homeostasis**.
|
||||
- **Metaplasticity:** Neurons adjust their **future learning rules** based on recent history. After intense learning, they raise the threshold for further LTP ("I'm saturated, make future learning harder"). This prevents overwriting and stabilizes memories.
|
||||
- **Goal:** Ensure **long-term stability** and **memory protection** while preserving the ability to learn new information.
|
||||
|
||||
### **4. Days to Lifetime Scale: *"Which connections are truly valuable, and should be made permanent?"***
|
||||
|
||||
- **Structural Rewiring:** Neurons physically **reorganize their hardware** based on statistical usefulness. Frequently used connections get stronger spines and more AMPA receptors; unused ones are pruned away.
|
||||
- **System Consolidation:** Memories are **redistributed** from fast-learning hippocampal circuits to more stable cortical networks for long-term storage.
|
||||
- **Goal:** **Optimize physical resources**—build durable, efficient circuits for frequently used information, and clear out unused ones to save energy and space.
|
||||
|
||||
**Neuron's Ultimate Objective:** To become a **better predictor**—encoding causal relationships in the world with increasing efficiency, stability, and metabolic economy.
|
||||
|
||||
## **What Astrocytes Are Trying to Achieve: Metabolic Balance & System Sustainability**
|
||||
|
||||
### **1. Millisecond to Second Scale: *"Is local activity coordinated, and does it need modulation?"***
|
||||
|
||||
- **Gliotransmission:** Astrocytes provide **on-demand chemical support** (D-serine for NMDA receptors) specifically when and where it's needed for coincidence detection and plasticity.
|
||||
- **K⁺ Buffering:** They instantly **prevent local excitotoxicity** by mopping up excess potassium from firing neurons.
|
||||
- **Goal:** **Enable and regulate** neuronal computation at the moment it happens, acting as an active partner in the tripartite synapse.
|
||||
|
||||
### **2. Minutes to Hours Scale: *"Can the local network sustain this level of activity metabolically?"***
|
||||
|
||||
- **The Lactate Shuttle:** Astrocytes act as **metabolic capacitors**, providing rapid energy (lactate) to neurons during bursts of computation.
|
||||
- **Glutamate Recycling:** They **recycle neurotransmitter raw materials**, ensuring neurons don't run out of "ammunition" during sustained activity.
|
||||
- **Sleep-Pressure Signaling (Adenosine):** Astrocytes build up a **chemical record of metabolic debt**—the longer and harder the network works, the more adenosine accumulates, eventually forcing rest.
|
||||
- **Goal:** **Balance energy supply with demand** in real-time and enforce necessary rest cycles.
|
||||
|
||||
### **3. Hours to Days Scale: *"How do I maintain the long-term health of my territory?"***
|
||||
|
||||
- **Glymphatic Clearance:** During sleep, astrocytes orchestrate the **washing away of metabolic waste** (like amyloid-β) that accumulates from daily neural activity.
|
||||
- **Vasomodulation:** They regulate **long-term blood flow** to ensure their territory receives adequate nutrients.
|
||||
- **Goal:** Perform **essential maintenance** to prevent toxicity and ensure the structural integrity of the network over time.
|
||||
|
||||
**Astrocyte's Ultimate Objective:** To create and maintain the **optimal metabolic and chemical environment** for neuronal computation—supplying energy, clearing waste, preventing toxicity, and enforcing sustainable operation cycles.
|
||||
|
||||
## **The Joint Optimization: A Symbiotic System**
|
||||
|
||||
Together, neurons and astrocytes solve the brain's fundamental dilemma: **how to be both incredibly fast/adaptive and incredibly stable/efficient.**
|
||||
|
||||
| Time Scale | Neuronal Goal | Astrocytic Goal | Combined Achievement |
|
||||
|---------------|---------------------------------------|------------------------------------------------|-------------------------------------------|
|
||||
| **Milliseconds** | Detect coincidences, transmit signals | Provide on-demand co-factors, prevent toxicity | **Rapid, precise computation without damage** |
|
||||
| **Seconds** | Adjust gain based on immediate past | Buffer ions, modulate transmission | **Dynamic stability during ongoing activity** |
|
||||
| **Minutes-Hours** | Initiate lasting plasticity | Supply energy, recycle materials | **Learning without metabolic collapse** |
|
||||
| **Hours-Days** | Consolidate memories, scale synapses | Clear waste, regulate blood flow | **Long-term stability with maintenance** |
|
||||
| **Days-Lifetime** | Optimize physical circuitry | Support structural integrity | **Efficient, durable network architecture** |
|
||||
|
||||
### **The Grand Strategy: Predictive Efficiency**
|
||||
|
||||
The brain is building an **internal model of the world** that minimizes prediction error. At every scale, neurons and astrocytes collaborate to make this model:
|
||||
|
||||
1. **More accurate** (through coincidence detection and Hebbian plasticity)
|
||||
2. **More efficient** (through pruning, scaling, and sparse coding)
|
||||
3. **More stable** (through homeostasis and metaplasticity)
|
||||
4. **More sustainable** (through metabolic coupling and waste clearance)
|
||||
|
||||
The structural reorganization based on past coincidence detection makes the system **better at future coincidence detection**—this is the essence of learning. The astrocyte ensures this learning happens within **metabolic constraints**, preventing the system from burning out from its own intelligence.
|
||||
|
||||
In essence: **Neurons are trying to build a better predictive model of their environment; astrocytes are trying to ensure the factory that builds that model doesn't exhaust its resources or poison itself with its own waste products.** Together, they create an intelligence that is both brilliant and sustainable.
|
||||
@@ -0,0 +1,119 @@
|
||||
# **Yes: Somatic and AIS Mechanisms That Increase Threshold During a Spike Train**
|
||||
|
||||
**Absolutely!** This is a fundamental property called **spike-frequency adaptation** or **accommodation**, where the neuron becomes *less* excitable during sustained firing. The **first spike is indeed easier** than subsequent spikes in a train. Let me detail the specific somatic and AIS mechanisms that accomplish this:
|
||||
|
||||
## **1. Somatic Mechanisms That Raise Threshold**
|
||||
|
||||
### **A. Slow Afterhyperpolarization (sAHP)**
|
||||
|
||||
This is the **primary mechanism** for somatic spike-frequency adaptation.
|
||||
|
||||
- **Mechanism:** Each action potential allows Ca²⁺ to enter the soma through voltage-gated calcium channels or NMDA receptors. This somatic Ca²⁺ accumulates and activates **calcium-dependent potassium channels (SK channels)**.
|
||||
- **Dynamics:** sAHP develops slowly (τ~100-1000 ms) and persists long after the spike.
|
||||
- **Effect:** The outward K⁺ current **hyperpolarizes** the soma, moving it *farther* from threshold. With each successive spike, more Ca²⁺ accumulates → more SK channels open → stronger hyperpolarization → **higher effective threshold**.
|
||||
- **Functional Role:** Prevents runaway excitation, encodes firing rate *adaptation* (responding best to changes rather than sustained input), and protects against metabolic exhaustion.
|
||||
|
||||
### **B. M-current (IKM)**
|
||||
|
||||
- **Mechanism:** A voltage-gated K⁺ current that activates slowly with depolarization and **does not inactivate**.
|
||||
- **Dynamics:** During a spike train, persistent depolarization slowly activates more M-channels.
|
||||
- **Effect:** Provides a **braking current** that increases with sustained activity, requiring stronger input to maintain firing.
|
||||
|
||||
### **C. Sodium Channel Inactivation at the Soma**
|
||||
|
||||
- While more pronounced at the AIS, somatic Na⁺ channels also experience **slow inactivation** during sustained depolarization.
|
||||
- This reduces the **available sodium current** for subsequent spikes.
|
||||
|
||||
## **2. AIS-Specific Mechanisms That Raise Threshold**
|
||||
|
||||
The AIS is particularly sophisticated in its dynamic threshold regulation:
|
||||
|
||||
### **A. Fast Na⁺ Channel Inactivation**
|
||||
|
||||
- **Mechanism:** After each spike, a fraction of Na⁺ channels enter an **inactivated state**.
|
||||
- **Recovery:** Channels recover with time constants from milliseconds (fast) to seconds (slow).
|
||||
- **Effect:** During high-frequency firing, channels don't fully recover between spikes. Fewer available channels = **higher threshold** for subsequent spikes.
|
||||
|
||||
### **B. Cumulative Potassium Channel Activation**
|
||||
|
||||
- **Mechanism:** K⁺ channels at the AIS (especially Kv3 types) activate rapidly but **deactivate slowly**.
|
||||
- **Dynamics:** During a spike train, these K⁺ channels don't fully close between spikes, creating a **cumulative outward current**.
|
||||
- **Effect:** This "**depolarization-induced suppression of excitation**" makes each successive spike harder to generate.
|
||||
|
||||
### **C. Dynamic Threshold via Sodium Channel Phosphorylation States**
|
||||
|
||||
- **Mechanism:** During sustained activity, kinases like **CaMKII** (activated by somatic Ca²⁺) can phosphorylate Na⁺ channels at the AIS.
|
||||
- **Effect:** Phosphorylation can **shift the voltage dependence of inactivation** to more hyperpolarized potentials, meaning channels inactivate at more negative voltages.
|
||||
- **Result:** The **availability curve** of Na⁺ channels shifts leftward → fewer channels available at any given potential → effectively **higher threshold**.
|
||||
|
||||
## **3. The Combined Effect: First Spike Advantage**
|
||||
|
||||
Here's what happens during a spike train:
|
||||
|
||||
| **Spike #** | **Somatic State** | **AIS State** | **Effective Threshold** |
|
||||
|--------------|-----------------------------------------|------------------------------------------------------------------|-----------------------------|
|
||||
| **1** | Resting, no sAHP, minimal M-current | All Na⁺ channels available, no K⁺ accumulation | **Lowest** (-55 mV) |
|
||||
| **2** | Some sAHP developing, slight M-current | Some Na⁺ channels still inactivated, some K⁺ channels still open | **Higher** (-53 mV) |
|
||||
| **3-5** | Significant sAHP, M-current growing | Cumulative Na⁺ inactivation, K⁺ current accumulation | **Much higher** (-50 to -48 mV) |
|
||||
| **Steady-state** | Maximum sAHP, full M-current activation | Equilibrium between Na⁺ recovery and inactivation | **Highest** (plateau) |
|
||||
|
||||
## **4. Mathematical Representation**
|
||||
|
||||
The dynamic threshold can be modeled as:
|
||||
|
||||
```
|
||||
Threshold(t) = Threshold_rest + A * ∫[Ca²⁺]_soma(t) + B * NaV_unavailable(t)
|
||||
```
|
||||
|
||||
Where A and B are weighting factors for somatic and AIS contributions respectively.
|
||||
|
||||
## **5. Functional Consequences of This Design**
|
||||
|
||||
### **A. Temporal Filtering**
|
||||
|
||||
The neuron becomes a **high-pass filter** for firing rates:
|
||||
|
||||
- **Responds vigorously** to sudden input increases (first spike easy)
|
||||
- **Adapts quickly** to sustained input (subsequent spikes harder)
|
||||
- **Encodes *changes* in input**, not absolute levels
|
||||
|
||||
### **B. Prevention of Epileptiform Activity**
|
||||
|
||||
By making sustained high-frequency firing progressively harder, the system has a built-in **safety mechanism** against runaway excitation.
|
||||
|
||||
### **C. Energy Efficiency**
|
||||
|
||||
Each spike consumes ATP (for Na⁺/K⁺ pumping). By adapting, the neuron prevents wasteful firing when input is sustained but not changing.
|
||||
|
||||
### **D. Signal-to-Noise Enhancement**
|
||||
|
||||
The adaptation makes the neuron more sensitive to **synchronized inputs** (which can overcome the raised threshold) versus **asynchronous background noise** (which cannot).
|
||||
|
||||
## **6. Modulation of Adaptation**
|
||||
|
||||
Crucially, this adaptation is itself **modulatable**:
|
||||
|
||||
- **Acetylcholine:** **Reduces** sAHP and M-current → less adaptation → neuron can sustain firing longer (important for attention).
|
||||
- **Norepinephrine:** Can **enhance** adaptation in some contexts, promoting burst firing patterns.
|
||||
- **Serotonin:** Modulates both sAHP and Na⁺ channel kinetics, tuning adaptation to behavioral state.
|
||||
|
||||
## **7. Experimental Evidence**
|
||||
|
||||
- **Intracellular recordings** show clear threshold increases during spike trains.
|
||||
- **Dynamic clamp experiments** demonstrate that injecting artificial sAHP currents reproduces adaptation.
|
||||
- **Knockout of SK channels** eliminates most spike-frequency adaptation.
|
||||
- **AIS-targeted pharmacology** shows that blocking specific K⁺ channels at the AIS reduces threshold elevation during trains.
|
||||
|
||||
## **Summary: The Strategic First Spike**
|
||||
|
||||
Yes, **the first spike is privileged**. The soma and AIS are engineered to be **maximally sensitive to the onset of input**, then progressively **desensitize** during sustained activity. This is achieved through:
|
||||
|
||||
1. **Somatic sAHP** (Ca²⁺-dependent K⁺ currents)
|
||||
2. **Somatic M-current** accumulation
|
||||
3. **AIS Na⁺ channel inactivation**
|
||||
4. **AIS K⁺ channel cumulative activation**
|
||||
5. **Activity-dependent phosphorylation** of threshold proteins
|
||||
|
||||
This creates a neuron that says: **"I notice changes immediately, but I won't keep shouting about things that don't change."** The first spike is the easiest because it carries the most information—the news that **something has changed**. Subsequent spikes in a train are progressively harder because they merely confirm "it's still happening," which is less informationally valuable.
|
||||
|
||||
This elegant design balances sensitivity with stability, novelty detection with energy conservation, making the neuron an optimal detector of **meaningful change** in a noisy world.
|
||||
@@ -0,0 +1,177 @@
|
||||
Ho l’impressione che come espressione G non dobbiamo trattare il release di NT come numero ma come concentrazione indotta alla postsinapi e quanto dura quella concentrazione.
|
||||
|
||||
### **Information Coding Beyond Saturation:**
|
||||
|
||||
1. **Spatial Code**: Where does glutamate reach? (synaptic vs. perisynaptic vs. extrasynaptic)
|
||||
2. **Temporal Code**: How long does elevated \[glutamate\] persist?
|
||||
3. **Spillover Code**: How much reaches astrocytes/neighboring synapses?
|
||||
4. **Metabolic Code**: How much energy demand does it create?
|
||||
|
||||
### **The "Glutamate Economy" Strategy:**
|
||||
|
||||
The brain uses excess glutamate **strategically**:
|
||||
|
||||
- **Normal transmission**: Minimal glutamate for efficiency
|
||||
- **Plasticity induction**: Extra glutamate to activate mGluRs, recruit astrocytes
|
||||
- **Network modulation**: High glutamate to affect neighboring synapses via spillover
|
||||
- **Emergency signaling**: Massive glutamate release as a distress signal
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **The Cooperative Gating of NMDA Receptors: A Molecular Dance of Stability**
|
||||
|
||||
## **The Fundamental Difference: NMDA vs AMPA Receptor Activation**
|
||||
|
||||
**AMPA receptors** are **simple ligand-gated channels**:
|
||||
|
||||
- Typically require **2 glutamate molecules** to bind to open
|
||||
- Once open, they behave similarly regardless of whether 2 or 4 glutamate molecules are bound
|
||||
- Their open probability is mostly "on" or "off"
|
||||
|
||||
**NMDA receptors** are **allosteric machines** with **cooperative gating**:
|
||||
|
||||
- They have **multiple binding sites** that influence each other
|
||||
- The binding of glutamate to one subunit increases the **affinity** of neighboring subunits
|
||||
- The more glutamate molecules bound, the **more stable the open state**
|
||||
|
||||
## **The NMDA Receptor Structure: A Tetrameric Complex**
|
||||
|
||||
A typical synaptic NMDA receptor consists of:
|
||||
|
||||
- **2 GluN1 subunits** (bind glycine/D-serine)
|
||||
- **2 GluN2 subunits** (bind glutamate)
|
||||
|
||||
But here's the key: each **GluN2 subunit has two glutamate-binding domains** (S1 and S2), and binding at both sites creates a more stable configuration.
|
||||
|
||||
## **The Molecular Mechanism: Why More Glutamate = More Stability**
|
||||
|
||||
### **1. The Binding Hierarchy:**
|
||||
|
||||
```
|
||||
Step 1: First glutamate binds to one GluN2 → conformational change → affinity ↑ for second site
|
||||
Step 2: Second glutamate binds to same GluN2 → further stabilization
|
||||
Step 3: Cross-subunit allostery: Occupied GluN2 increases affinity of neighboring GluN2
|
||||
Step 4: Third/fourth glutamate binding → maximal stability
|
||||
```
|
||||
|
||||
### **2. The Energy Landscape Analogy:**
|
||||
|
||||
Think of the receptor as a ball in different shaped bowls:
|
||||
|
||||
- **No glutamate**: Ball in shallow bowl → easily rolls out (closes quickly)
|
||||
- **1 glutamate**: Bowl slightly deeper → stays open longer
|
||||
- **2 glutamates**: Deeper bowl → stable open state
|
||||
- **3-4 glutamates**: Very deep bowl → extremely stable, long openings
|
||||
|
||||
**Each additional glutamate molecule deepens the energy well**, making it harder for the channel to close.
|
||||
|
||||
### **3. The Kinetic Proof:**
|
||||
|
||||
Experimental single-channel recordings show:
|
||||
|
||||
| **Glutamate Molecules Bound** | **Mean Open Time** | **Closing Rate** |
|
||||
|---------------------------|----------------|--------------|
|
||||
| 1 | ~2 ms | Fast closure |
|
||||
| 2 | ~10-20 ms | Moderate |
|
||||
| 3-4 | ~50-100 ms | Slow, stable |
|
||||
|
||||
**The open time increases exponentially** with glutamate occupancy, not linearly.
|
||||
|
||||
## **4. The Biological Consequences of This Stability**
|
||||
|
||||
### **A. Calcium Influx Duration Matters:**
|
||||
|
||||
```
|
||||
Brief NMDA opening (1-2 ms):
|
||||
- Small Ca²⁺ puff
|
||||
- Activates fast phosphatases → LTD
|
||||
|
||||
Long NMDA opening (20-100 ms):
|
||||
- Sustained Ca²⁺ influx
|
||||
- Activates slow kinases (CaMKII) → LTP
|
||||
- Triggers nuclear signaling
|
||||
```
|
||||
|
||||
The **duration** of NMDA opening determines **which downstream signaling pathways** get activated.
|
||||
|
||||
### **B. Temporal Integration of Inputs:**
|
||||
|
||||
A single vesicle might only briefly saturate NMDA receptors. But with **multiple vesicles releasing**:
|
||||
|
||||
- Glutamate concentration stays high for longer
|
||||
- NMDA receptors remain stably bound
|
||||
- Creates a **temporal window** for coincidence detection with backpropagating action potentials
|
||||
|
||||
### **C. The "Threshold" Effect for Plasticity:**
|
||||
|
||||
There's a **non-linear relationship**:
|
||||
|
||||
- **Moderate glutamate**: NMDA receptors flicker open briefly → moderate Ca²⁺ → LTD
|
||||
- **High glutamate**: NMDA receptors lock open → large Ca²⁺ → LTP
|
||||
|
||||
The difference isn't just amplitude—it's **duration** of Ca²⁺ signal.
|
||||
|
||||
## **5. The Postsynaptic Spine's Calcium "Language"**
|
||||
|
||||
### **The Decoding System:**
|
||||
|
||||
- **Brief Ca²⁺ transients** (10-50 ms): Activate **calcineurin** → AMPA receptor removal → LTD
|
||||
- **Prolonged Ca²⁺ plateaus** (100-500 ms): Activate **CaMKII** → AMPA receptor insertion → LTP
|
||||
|
||||
**More glutamate → more stable NMDA openings → longer Ca²⁺ signals → LTP instead of LTD**
|
||||
|
||||
## **6. The Functional Significance in Spike Trains**
|
||||
|
||||
During a spike train:
|
||||
|
||||
- **First spike**: Moderate glutamate → brief NMDA openings
|
||||
- **Second/third spike** (with residual glutamate): More glutamate accumulates → more stable NMDA openings
|
||||
- **This creates a "priming" effect**: Early spikes in a train make NMDA receptors **more responsive** to later spikes
|
||||
|
||||
## **7. The Astrocyte Connection**
|
||||
|
||||
Astrocytes release **D-serine**, the co-agonist for GluN1 subunits. With more glutamate:
|
||||
|
||||
- More D-serine binding sites occupied
|
||||
- Further stabilizes the open state
|
||||
- Creates a **positive feedback loop**: More glutamate → more stable openings → more Ca²⁺ → astrocyte Ca²⁺ → more D-serine release
|
||||
|
||||
## **8. Disease Implications**
|
||||
|
||||
### **Excitotoxicity Mechanism:**
|
||||
|
||||
- Excessive glutamate → NMDA receptors **lock open for too long**
|
||||
- Massive, sustained Ca²⁺ influx
|
||||
- Overwhelms mitochondrial buffers
|
||||
- Triggers apoptotic pathways
|
||||
|
||||
### **The NMDA Receptor "Sweet Spot":**
|
||||
|
||||
There's an optimal range of glutamate occupancy:
|
||||
|
||||
- **Too low**: Unreliable signaling, failed plasticity
|
||||
- **Optimal**: Balanced LTP/LTD, normal function
|
||||
- **Too high**: Excitotoxicity, receptor desensitization
|
||||
|
||||
## **9. Experimental Evidence**
|
||||
|
||||
1. **Single-channel recordings**: Show longer openings with higher glutamate concentrations
|
||||
2. **Mutant NMDA receptors** with altered glutamate affinity show altered plasticity thresholds
|
||||
3. **Glutamate uncaging experiments**: Precise control shows non-linear Ca²⁺ responses
|
||||
4. **Computational models** that include cooperative gating better predict experimental data
|
||||
|
||||
## **The Biological Wisdom: A Molecular Amplifier**
|
||||
|
||||
The cooperative gating of NMDA receptors acts as a **biological amplifier**:
|
||||
|
||||
- **Weak signals** (low glutamate) get filtered out
|
||||
- **Moderate signals** produce proportional responses
|
||||
- **Strong signals** get amplified non-linearly
|
||||
|
||||
This creates a **thresholding mechanism** for plasticity: only synapses receiving strong, coordinated input undergo LTP. The synapse says: "Don't just talk to me—shout with conviction if you want me to remember."
|
||||
|
||||
The "more stable open state" with more glutamate binding is nature's way of saying: **"Important messages should linger, not flicker."** It's the difference between a passing thought and a deeply held memory at the molecular level.
|
||||
@@ -0,0 +1,269 @@
|
||||
# **The Life of a Presynapse During and Between Spike Trains**
|
||||
|
||||
## **The Terminal's Rhythm: Interpreting the Sovereign's Commands**
|
||||
|
||||
I am a presynaptic terminal. My existence is defined by the arrival of action potentials—the sovereign soma's commands. But I am not a slave; I interpret, adapt, and sometimes protest through my release patterns.
|
||||
|
||||
---
|
||||
|
||||
## **I. BETWEEN SPIKE TRAINS: The Idle Preparations**
|
||||
|
||||
### **The Resting State (τ = 100+ ms after last spike)**
|
||||
|
||||
**Internal State:**
|
||||
|
||||
- **Residual Ca²⁺**: Near baseline (~50 nM)
|
||||
- **Vesicle Pool**: Fully stocked (100% of RRP)
|
||||
- **P<sub>r</sub>**: At baseline (e.g., 0.2-0.8 depending on terminal type)
|
||||
- **Recycling Machinery**: Catching up, docked vesicles ready
|
||||
|
||||
**Ongoing Maintenance:**
|
||||
|
||||
1. **Baseline Vesicle Cycling**:
|
||||
- Slow, stochastic release of single vesicles ("minis") - my way of whispering "I'm here" to the postsynapse
|
||||
- Steady-state recycling: 1 vesicle recycled every ~30 seconds
|
||||
2. **Metabolic Housekeeping**:
|
||||
- Astrocyte provides **lactate** → fuels my mitochondria
|
||||
- Vesicles are being **re-acidified** (pH restored to ~5.5 via V-ATPase)
|
||||
- **Glutamine** from astrocyte → converted to glutamate for reloading
|
||||
3. **Signaling Environment**:
|
||||
- Basal **adenosine** levels modulate my excitability
|
||||
- **D-serine** from astrocyte maintains postsynaptic NMDA readiness
|
||||
- Tonic **neuromodulator** levels (dopamine, ACh) set my baseline gain
|
||||
|
||||
**Between-Train Plasticity:**
|
||||
|
||||
- If previous train induced **LTP of release** (via NO/BDNF):
|
||||
- **P<sub>r</sub>** remains elevated for minutes-hours
|
||||
- More **active zone proteins** are synthesized
|
||||
- If previous train induced **LTD of release** (via eCBs):
|
||||
- **P<sub>r</sub>** remains suppressed
|
||||
- Fewer docked vesicles
|
||||
|
||||
**Time to Full Recovery:**
|
||||
|
||||
- **Vesicle Pool**: 1-10 seconds to refill RRP
|
||||
- **Calcium Clearance**: 50-200 ms to clear residual Ca²⁺
|
||||
- **Channel Recovery**: 2-100 ms for Na⁺/Ca²⁺ channel inactivation reset
|
||||
|
||||
---
|
||||
|
||||
## **II. DURING A SPIKE TRAIN: The Performance**
|
||||
|
||||
### **Phase 1: The Opening Salvo (First 2-3 Spikes, 0-50 ms)**
|
||||
|
||||
**Initial Conditions:**
|
||||
|
||||
- Full vesicle pool
|
||||
- Baseline P<sub>r</sub>
|
||||
- Minimal residual Ca²⁺
|
||||
|
||||
**What Happens:**
|
||||
|
||||
```
|
||||
Spike 1:
|
||||
- Ca²⁺ surges to ~10 μM at active zone
|
||||
- P(r) determines release: 0.2 → 20% chance, 0.8 → 80% chance
|
||||
- If release: 1 vesicle fuses, pool ↓ by 1
|
||||
|
||||
Spike 2 (20 ms later):
|
||||
- Residual Ca²⁺ from Spike 1 still present (~200 nM)
|
||||
- P<sub>r</sub> increased by STF factor: 0.2 → 0.35, 0.8 → 0.95
|
||||
- But pool now at 99% (if Spike 1 released)
|
||||
- Effective release = P<sub>r</sub> × pool_fraction
|
||||
```
|
||||
|
||||
**Terminal Types Diverge:**
|
||||
|
||||
- **High-P<sub>r</sub>, Small Pool**: Releases strongly on Spike 1-3, then crashes
|
||||
- **Low-P<sub>r</sub>, Large Pool**: May fail on Spike 1, releases sporadically throughout
|
||||
|
||||
### **Phase 2: The Battle of Forces (Spikes 4-10, 50-200 ms)**
|
||||
|
||||
**The Tension:**
|
||||
|
||||
- **STF**: Residual Ca²⁺ accumulates → P<sub>r</sub> keeps rising
|
||||
- **STD**: Vesicle pool depletes → effective release drops despite high P<sub>r</sub>
|
||||
|
||||
**The Turning Point:**
|
||||
At some spike N, **depletion wins**:
|
||||
|
||||
```
|
||||
P<sub>r</sub> might be 0.9 (high from facilitation)
|
||||
But pool is at 20% of original
|
||||
Effective release = 0.9 × 0.2 = 0.18
|
||||
Release plummets despite "willingness"
|
||||
```
|
||||
|
||||
**Real-Time Adjustments:**
|
||||
|
||||
1. **Calcium-Dependent Recovery**:
|
||||
- High Ca²⁺ accelerates endocytosis (clathrin uncoating)
|
||||
- But also risks **calcium overload** → vesicle recycling stalls
|
||||
2. **Energy Crisis Management**:
|
||||
- Mitochondria work overtime
|
||||
- Lactate uptake from astrocyte increases
|
||||
- If ATP drops → recycling slows → depression worsens
|
||||
|
||||
### **Phase 3: Steady-State Exhaustion (>200 ms continuous firing)**
|
||||
|
||||
**The Plateau:**
|
||||
|
||||
- **Release rate** stabilizes at 10-30% of initial rate
|
||||
- **Balance point**: Recycling rate ≈ Release rate
|
||||
- **P<sub>r</sub>** remains high (STF) but irrelevant due to limited vesicles
|
||||
|
||||
**The "Release Modes" Shift:**
|
||||
|
||||
- **Synchronous release** (spike-locked) decreases
|
||||
- **Asynchronous release** (delayed, Ca²⁺-driven) increases
|
||||
- **Miniature release** continues as stochastic background
|
||||
|
||||
**Signals to Postsynapse Change:**
|
||||
|
||||
- From "Here is precise timing information!" to "There is sustained activity..."
|
||||
|
||||
---
|
||||
|
||||
## **III. BETWEEN SPIKE TRAINS: The Aftermath and Recovery**
|
||||
|
||||
### **Immediate Aftermath (0-1 second post-train)**
|
||||
|
||||
**The Calcium Hangover:**
|
||||
|
||||
- Bulk Ca²⁺ cleared by pumps (PMCA, NCX) in 100-500 ms
|
||||
- But **residual microdomain Ca²⁺** persists near release sites
|
||||
- This creates a **"readiness" state** for next train
|
||||
|
||||
**Vesicle Recycling Race:**
|
||||
|
||||
```
|
||||
Time 0 ms: Pool at 20%
|
||||
Time 100 ms: Pool at 40% (fast component)
|
||||
Time 500 ms: Pool at 70%
|
||||
Time 2000 ms: Pool at 95% (full recovery)
|
||||
```
|
||||
|
||||
**The Recovery Time Constant (τ<sub>recycle</sub>) Depends On:**
|
||||
|
||||
- Terminal type: 0.3 s (fast) to 10 s (slow)
|
||||
- Energy availability: Low ATP → slower
|
||||
- Astrocyte support: Lactate/glutamine supply
|
||||
- Temperature: Warmer → faster
|
||||
|
||||
### **Intermediate Recovery (1-60 seconds)**
|
||||
|
||||
**Biochemical Resets:**
|
||||
|
||||
- Kinases/phosphatases return proteins to baseline states
|
||||
- Ca²⁺-calmodulin complexes disassemble
|
||||
- Autoreceptors (mGluR, CB1) reset sensitivity
|
||||
|
||||
**Retrograde Signal Processing:**
|
||||
If the train was significant:
|
||||
|
||||
- **eCBs** from postsynapse maintain suppression (minutes)
|
||||
- **NO** from postsynapse enhances future release
|
||||
- **BDNF** begins synthesis (hours-scale effects)
|
||||
|
||||
**Metaplastic Adjustments:**
|
||||
|
||||
- mGluR activation → lowers threshold for future LTD
|
||||
- Repeated trains → builds up **adenosine** → global suppression
|
||||
|
||||
### **Long-Term Between-Train States (Minutes-Hours)**
|
||||
|
||||
**Structural Changes (If Train Was "Meaningful"):**
|
||||
|
||||
- **Active zone expansion**: More docking sites added
|
||||
- **Mitochondrial biogenesis**: More energy capacity
|
||||
- **Vesicle protein synthesis**: Larger vesicle pools
|
||||
- **Receptor expression changes**: Altered sensitivity to modulators
|
||||
|
||||
**The Terminal's "Memory":**
|
||||
|
||||
- Previous activity patterns bias future responses
|
||||
- A terminal that just experienced high-frequency firing may:
|
||||
- Recover faster (trained recycling machinery)
|
||||
- Have higher baseline P<sub>r</sub> (LTP of release)
|
||||
- Or be more prone to depression (if overwhelmed)
|
||||
|
||||
---
|
||||
|
||||
## **IV. THE SPIKE TRAIN INTERPRETATION DICTIONARY**
|
||||
|
||||
### **What Different Spike Train Patterns "Say" to the Terminal:**
|
||||
|
||||
| **Train Pattern** | **Terminal's Interpretation** | **Response Strategy** |
|
||||
|-----------------------|---------------------------|------------------------------------------------------|
|
||||
| **Single spike** | "Alert!" | Maximum P<sub>r</sub>, no STD |
|
||||
| **Brief burst (3@100Hz)** | "Important event!" | Strong STF, moderate STD, triggers plasticity |
|
||||
| **Sustained high freq** | "Emergency!" | Initial STF → severe STD → asynchronous mode |
|
||||
| **Regular low freq** | "Background signal" | Steady-state with balanced recovery |
|
||||
| **Irregular pattern** | "Complex information" | Dynamic P<sub>r</sub> adjustments, history-dependent |
|
||||
|
||||
### **The Terminal's Vocabulary in Response:**
|
||||
|
||||
| **Release Pattern** | **Message to Postsynapse** |
|
||||
|------------------------------|-----------------------------------------|
|
||||
| **Reliable on every spike** | "This is important, pay attention" |
|
||||
| **Facilitating then depressing** | "Something changed, then continued" |
|
||||
| **Sporadic releases** | "There's activity but I'm uncertain" |
|
||||
| **Asynchronous release** | "Sustained event, timing less precise" |
|
||||
| **Complete silence** | "I'm exhausted" or "This is irrelevant" |
|
||||
|
||||
---
|
||||
|
||||
## **V. THE COMPUTATIONAL CONSEQUENCES**
|
||||
|
||||
### **Between Trains: Information Integration**
|
||||
|
||||
- **Integration window**: ~50-2000 ms between trains matters
|
||||
- **Priming**: A recent train leaves residual Ca²⁺ → next train facilitated
|
||||
- **Metaplasticity**: Previous trains adjust thresholds for future plasticity
|
||||
|
||||
### **During Trains: Temporal Filtering**
|
||||
|
||||
- **High-pass filter**: Responds best to onsets (initial spikes)
|
||||
- **Adaptive gain**: Sensitivity adjusts to input statistics
|
||||
- **Energy-based gating**: Cannot sustain unrealistic firing rates
|
||||
|
||||
### **The Terminal as a Spike Train Interpreter:**
|
||||
|
||||
```
|
||||
Input: Binary spike train (0s and 1s at precise times)
|
||||
Processing:
|
||||
- Dynamic P<sub>r</sub> = f(residual Ca²⁺, recovery state)
|
||||
- Available vesicles = g(recycling rate, previous release)
|
||||
- Modulator effects = h(neuromodulators, retrograde signals)
|
||||
|
||||
Output: Probabilistic glutamate release pattern
|
||||
Which is NOT a perfect copy of the input spike train
|
||||
But a filtered, adapted, modulated version
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## **VI. THE STRATEGIC BALANCE**
|
||||
|
||||
**Between Spike Trains, I:**
|
||||
|
||||
- Recover resources
|
||||
- Process retrograde feedback
|
||||
- Adjust my baseline settings
|
||||
- Prepare for the next conversation
|
||||
|
||||
**During Spike Trains, I:**
|
||||
|
||||
- Interpret the pattern
|
||||
- Balance facilitation vs depression
|
||||
- Signal my state via release probability
|
||||
- Manage my energy budget
|
||||
- Communicate both reliability and urgency
|
||||
|
||||
**My existence is rhythmic:**
|
||||
**Rest → Prepare → Perform → Recover → Learn → Rest...**
|
||||
|
||||
Each spike train is not an isolated event but part of a **conversational history**. My response to spike #10 depends on what happened with spikes #1-9, what happened between previous trains, and what my postsynaptic partner and astrocyte caretaker are telling me.
|
||||
|
||||
This is how I, a single presynaptic terminal, contribute to the brain's computation: not by faithfully reproducing spikes, but by **interpreting them, adapting to them, and responding strategically**—all within the biological constraints of my vesicle economy and signaling environment.
|
||||
@@ -0,0 +1,278 @@
|
||||
# **Spike Train Examples: How Different Patterns Lead to LTP, LTD, or Tagging**
|
||||
|
||||
Here's a clear visualization of how **specific spike train patterns** produce the different calcium dynamics and plasticity outcomes:
|
||||
|
||||
```mermaid
|
||||
timeline
|
||||
title Spike Train Patterns & Plasticity Outcomes
|
||||
section LTP Induction (Pre-before-Post Burst)
|
||||
Pre-spikes : 100 Hz burst<br>0, 10, 20, 30, 40 ms
|
||||
Post-spike : Single bAP at 15 ms
|
||||
Ca²⁺ Dynamics : Rapid rise to 5-10 μM<br>within 20 ms
|
||||
Tag Window : Tag set at 5 ms<br>Active until 105 ms
|
||||
Outcome : Strong LTP<br>200-300% AMPAR increase
|
||||
section LTD Induction (Isolated Presynaptic Train)
|
||||
Pre-spikes : 10 Hz train for 1s<br>0, 100, 200...900 ms
|
||||
Post-spikes : None
|
||||
Ca²⁺ Dynamics : Sustained 1-2 μM<br>for ~500 ms
|
||||
Tag Window : Multiple tags set<br>but no coincidence
|
||||
Outcome : Moderate LTD<br>40-60% AMPAR removal
|
||||
section Tagging Only (Poorly Timed Activity)
|
||||
Pre-spikes : 50 Hz burst<br>0, 20, 40 ms
|
||||
Post-spike : Delayed at 100 ms
|
||||
Ca²⁺ Dynamics : Brief 0.8-1 μM peak
|
||||
Tag Window : Tag set at 20 ms<br>Expires before post-spike
|
||||
Outcome : Metaplastic priming only<br>No weight change
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## **EXAMPLE 1: LTP INDUCTION (Theta Burst Pattern)**
|
||||
|
||||
**Spike trains:**
|
||||
|
||||
```
|
||||
Presynaptic: ● ● ● ● ● (100 Hz burst: 0, 10, 20, 30, 40 ms)
|
||||
Postsynaptic: ↑bAP at 15 ms
|
||||
```
|
||||
|
||||
**Calcium timeline:**
|
||||
|
||||
```
|
||||
Time (ms) Ca²⁺ (μM) Event
|
||||
────────────────────────────────────
|
||||
0 0.1 → 1.0 Spike 1: Glutamate → NMDAR opens
|
||||
10 1.0 → 3.0 Spike 2: Summation + tag set (θ_tag crossed)
|
||||
15 3.0 → 8.0 bAP arrives → Mg²⁺ block fully relieved
|
||||
20 8.0 → 12.0 Spike 3: Maximum Ca²⁺ → crosses θ_LTP
|
||||
30 12.0 Spike 4: High plateau
|
||||
40 10.0 Spike 5: High sustained
|
||||
50 5.0 Decay begins
|
||||
100 0.5 Tag window closes
|
||||
```
|
||||
|
||||
**Why LTP occurs:**
|
||||
|
||||
- **Strong coincidence**: bAP arrives during glutamate presence (Δt = +5 ms)
|
||||
- **High Ca²⁺ peak**: 8-12 μM > θ\_LTP (2 μM)
|
||||
- **Tag active**: Set at ~10 ms, active until ~110 ms
|
||||
- **Protein synthesis**: Triggered by combined Ca²⁺ + neuromodulators
|
||||
|
||||
**Outcome:** 200-300% increase in AMPARs within 5-30 minutes.
|
||||
|
||||
---
|
||||
|
||||
## **EXAMPLE 2: LTD INDUCTION (Low-Frequency Train)**
|
||||
|
||||
**Spike trains:**
|
||||
|
||||
```
|
||||
Presynaptic: ● ● ● ● ● ● ● ● ● ●
|
||||
0 100 200 300 400 500 600 700 800 900 ms
|
||||
Postsynaptic: (None - isolated presynaptic activity)
|
||||
```
|
||||
|
||||
**Calcium timeline:**
|
||||
|
||||
```
|
||||
Time (ms) Ca²⁺ (μM) Event
|
||||
────────────────────────────────────
|
||||
0 0.1 → 1.5 Spike 1: Tag set at ~5 ms
|
||||
100 1.5 → 2.0 Spike 2: Sustained moderate Ca²⁺
|
||||
200 2.0 Spike 3: LTD threshold duration starts
|
||||
300 2.0 Spike 4: Sustained >100 ms → LTD engaged
|
||||
400 2.0 Spike 5: Calcineurin fully active
|
||||
500 1.8 Spike 6: AMPAR removal begins
|
||||
...
|
||||
900 1.5 Last spike
|
||||
1000 0.8 Decay begins
|
||||
1500 0.2 Back to baseline
|
||||
```
|
||||
|
||||
**Why LTD occurs:**
|
||||
|
||||
- **No coincidence**: No bAPs to relieve Mg²⁺ block fully
|
||||
- **Moderate, sustained Ca²⁺**: 1.5-2.0 μM for >500 ms
|
||||
- **Calcineurin activation**: Requires sustained moderate Ca²⁺
|
||||
- **No LTP trigger**: Ca²⁺ never exceeds θ\_LTP (2 μM)
|
||||
|
||||
**Outcome:** 40-60% AMPAR removal within 1-5 minutes.
|
||||
|
||||
---
|
||||
|
||||
## **EXAMPLE 3: TAG WITHOUT EXPRESSION (Mistimed Activity)**
|
||||
|
||||
**Spike trains:**
|
||||
|
||||
```
|
||||
Presynaptic: ● ● ●
|
||||
0 20 40 ms
|
||||
Postsynaptic: ↑bAP at 100 ms (too late)
|
||||
```
|
||||
|
||||
**Calcium timeline:**
|
||||
|
||||
```
|
||||
Time (ms) Ca²⁺ (μM) Event
|
||||
────────────────────────────────────
|
||||
0 0.1 → 0.6 Spike 1: Below tag threshold
|
||||
20 0.6 → 1.0 Spike 2: Tag SET (θ_tag = 0.5 μM)
|
||||
40 1.0 → 1.2 Spike 3: Tag active, Ca²⁺ moderate
|
||||
50 0.8 Decay begins
|
||||
100 0.3 bAP arrives alone → small Ca²⁺ via VGCCs
|
||||
105 0.4 Insufficient for LTP
|
||||
110 0.3 Tag EXPIRES (set at 20 ms, 90 ms lifetime)
|
||||
```
|
||||
|
||||
**Why only tagging occurs:**
|
||||
|
||||
- **Tag set**: Moderate Ca²⁺ (1.0 μM) sets eligibility
|
||||
- **No coincidence**: bAP arrives 60 ms after last glutamate
|
||||
- **Ca²⁺ insufficient**: bAP alone → ~0.4 μM (well below θ\_LTP)
|
||||
- **Tag expires**: No strong Ca²⁺ within ~100 ms window
|
||||
|
||||
**Outcome:** No weight change, but spine is **primed**:
|
||||
|
||||
- Lowered θ\_LTP for next 30-60 minutes
|
||||
- Increased kinase sensitivity
|
||||
- **Next coincident event** will produce enhanced LTP
|
||||
|
||||
---
|
||||
|
||||
## **EXAMPLE 4: STDP WINDOW DEMONSTRATION**
|
||||
|
||||
**Different Δt values produce different outcomes:**
|
||||
|
||||
### **A. Δt = +10 ms (Pre-before-Post): LTP**
|
||||
|
||||
```
|
||||
Pre: ●
|
||||
↘
|
||||
Post: ● (10 ms later)
|
||||
Ca²⁺: 0 → 8 μM → LTP
|
||||
```
|
||||
|
||||
### **B. Δt = +50 ms (Pre-before-Post): Weak Tag Only**
|
||||
|
||||
```
|
||||
Pre: ●
|
||||
↘
|
||||
Post: ● (50 ms later)
|
||||
Ca²⁺: 0 → 1 μM → tag → 0.5 μM from bAP → No LTP (too low)
|
||||
```
|
||||
|
||||
### **C. Δt = -10 ms (Post-before-Pre): LTD**
|
||||
|
||||
```
|
||||
Post: ●
|
||||
↘
|
||||
Pre: ● (10 ms later)
|
||||
Ca²⁺: 0 → 1.5 μM (VGCC) → + 1.0 μM (NMDAR) → Sustained 2.5 μM → LTD
|
||||
```
|
||||
|
||||
### **D. Δt = -50 ms (Post-before-Pre): Nothing**
|
||||
|
||||
```
|
||||
Post: ●
|
||||
↘
|
||||
Pre: ● (50 ms later)
|
||||
Ca²⁺: Separate transients (0.5 μM each) → No tag, no LTD
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## **EXAMPLE 5: SPIKE FREQUENCY EFFECTS**
|
||||
|
||||
### **Low frequency (1 Hz): Steady state**
|
||||
|
||||
```
|
||||
Pre: ● ● ● ● ● ● ●
|
||||
Time: |----|----|----|----|----|----|
|
||||
Ca²⁺: Each transient ~0.8 μM, decays fully between spikes
|
||||
Outcome: No plasticity (below θ_tag most of the time)
|
||||
```
|
||||
|
||||
### **Moderate frequency (10 Hz): LTD**
|
||||
|
||||
```
|
||||
Pre: ● ● ● ● ● ● ● ● ● ● ● ● ● ● ●
|
||||
(sustained for 1 second)
|
||||
Ca²⁺: Builds to 1.5-2.0 μM plateau, sustained >500 ms
|
||||
Outcome: Moderate LTD
|
||||
```
|
||||
|
||||
### **High frequency burst (100 Hz): LTP**
|
||||
|
||||
```
|
||||
Pre: [●●●●●] [●●●●●] [●●●●●]
|
||||
Burst 1 Burst 2 Burst 3
|
||||
Post: ↑bAP during each burst
|
||||
Ca²⁺: Peaks at 10+ μM during bursts, decays partially between
|
||||
Outcome: Strong LTP
|
||||
```
|
||||
|
||||
### **Irregular Poisson-like: Mixed**
|
||||
|
||||
```
|
||||
Pre: ● ● ● ● ● ● ● ● ●
|
||||
(average 20 Hz, irregular intervals)
|
||||
Ca²⁺: Variable, depends on recent history
|
||||
Outcome: Some facilitation/depression, minimal long-term change
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## **EXAMPLE 6: NEUROMODULATOR EFFECTS ON SPIKE TRAINS**
|
||||
|
||||
### **With Dopamine (enhances LTP):**
|
||||
|
||||
```
|
||||
Pre: ● ● ● ● ● (20 Hz train)
|
||||
Post: ↑bAP at 15 ms
|
||||
DA: └──────────→ High during train
|
||||
Effect: Ca²⁺ peaks 30% higher, tag lifetime extended
|
||||
Outcome: LTP where none would occur without DA
|
||||
```
|
||||
|
||||
### **With eCB (promotes LTD):**
|
||||
|
||||
```
|
||||
Pre: ● ● ● ● ● ● (30 Hz train)
|
||||
Post: ↑bAP at 10 ms → eCB synthesis
|
||||
eCB: └────→ (50 ms delay) inhibits presynaptic Ca²⁺
|
||||
Effect: Later spikes see reduced Ca²⁺ influx
|
||||
Outcome: Weaker LTP or mixed LTP/LTD
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## **SUMMARY TABLE: SPIKE TRAIN → OUTCOME MAPPING**
|
||||
|
||||
| Pattern | Frequency | Coincidence | Ca²⁺ Dynamics | Tag | Outcome |
|
||||
|-----------------|-------------|----------------|------------------------------|---------------|----------------------------|
|
||||
| **Single pair** | N/A | Δt = +10 ms | Brief 5-10 μM spike | Set + used | LTP |
|
||||
| **Single pair** | N/A | Δt = -10 ms | Sustained 1-2 μM | Set | LTD |
|
||||
| **Theta burst** | 5 Hz bursts | bAP in burst | High bursts, moderate gaps | Multiple tags | Strong LTP |
|
||||
| **Low frequency** | 1 Hz | None | Separate 0.5-1 μM transients | None | No change |
|
||||
| **Sustained 10 Hz** | 10 Hz | None | Plateau ~1.5-2.0 μM | Multiple tags | LTD |
|
||||
| **High frequency** | 100 Hz | None | Initial high then depression | Early tags | Mixed: LTP then depression |
|
||||
| **Mistimed burst** | 50 Hz | bAP 60 ms late | Moderate then low | Expired | Metaplasticity only |
|
||||
|
||||
---
|
||||
|
||||
## **KEY PRINCIPLES FROM THESE EXAMPLES:**
|
||||
|
||||
1. **Timing precision matters:** ±20 ms windows determine LTP vs LTD
|
||||
2. **Frequency matters:** Low frequencies favor LTD, bursts favor LTP
|
||||
3. **History matters:** Recent spikes determine current Ca²⁺ baseline
|
||||
4. **Tag lifetime is critical:** ~100 ms window for coincidence detection
|
||||
5. **Nonlinear summation:** Bursts ≠ sum of individual spikes
|
||||
|
||||
**The presynapse-postsynapse system acts as a sophisticated pattern detector:**
|
||||
|
||||
- **Detects coincidences** within 100 ms → LTP
|
||||
- **Detects isolated presynaptic activity** → LTD
|
||||
- **Detects moderate activity without coincidence** → Metaplastic priming
|
||||
- **All filtered through neuromodulatory state** (DA, eCB, etc.)
|
||||
|
||||
**This explains why specific spike patterns in the brain (theta rhythms, gamma bursts) are so effective for learning—they naturally create the calcium dynamics that trigger LTP with minimal depression.**
|
||||
@@ -0,0 +1,747 @@
|
||||
## Presynapse Types
|
||||
|
||||
### The Metabolic "Vise": Why Personalities Exist
|
||||
|
||||
The brain cannot afford to make every synapse an 'Integrator' (high vesicle cost) or every synapse a 'Starter' (high calcium-pumping energy cost).
|
||||
|
||||
By diversifying into these personalities, the brain achieves **Sparse Coding**. It only uses the high-energy "Starters" when something changes, and it only uses the "Integrators" when a signal has proven it's not just a fluke. The astrocyte is the manager that ensures neither type "burns out" the local environment.
|
||||
|
||||
To maintain their distinct roles as a "Starter" or an "Integrator" while undergoing modulation (like LTP or LTD), synapses use **structural constraints** and **metabolic scaling**. If a "Starter" synapse simply became an "Integrator" every time it was modulated, the brain would lose its functional diversity. Instead, modulation usually **amplifies the existing identity** of the synapse rather than overwriting it. The brain cannot afford to make every synapse an "Integrator" (high vesicle cost) or every synapse a "Starter" (high energy cost).
|
||||
|
||||
### 1. High Pr / Low Vesicle Count: The "Phasic" Starter
|
||||
|
||||
This synapse is built for **Novelty Detection**. It is the "Detective of the New."
|
||||
|
||||
- **The Logic:** It prioritizes the first bit of information it receives. Because Pr is high, it is almost certain to fire on the very first spike.
|
||||
- **The Mechanism:** It has a small RRP (Readily Releasable Pool), meaning it "spends" its entire budget on the first frame.
|
||||
- **Behavior (Short-Term Depression):** \* **Spike 1:** Strong output (Full success).
|
||||
- **Spike 2-10:** Silence or very weak output (Depletion).
|
||||
- **Functional Role:** It tells the brain, *"Something just started!"* It is excellent for detecting the beginning of a sound or a sudden movement, but it quickly falls silent to avoid redundant "noise."
|
||||
|
||||
The High Pr / Low Vesicle synapse maintains its identity by keeping its "hardware" focused on the first nanosecond of the spike.
|
||||
|
||||
- **Nanodomain Coupling:** In these synapses, the few available vesicles are physically docked extremely close to the Voltage-Gated Calcium Channels (VGCCs). This is called **tight coupling**.
|
||||
- **Effect of Modulation:** When retrograde signals (like NO) increase the number of VGCCs, they are added *right next* to the existing ones.
|
||||
- The Pr goes from 0.8 to 0.95.
|
||||
- It becomes a **"Super-Starter."** \* **Why it doesn't become an Integrator:** It still lacks the protein "scaffolding" (like Synapsin) to hold a large reserve pool. Modulation makes its one-shot more "guaranteed," but it still depletes just as fast because its structural "shelf space" for vesicles is limited.
|
||||
|
||||
### 2. Low Pr / High Vesicle Count: The "Tonic" Integrator
|
||||
|
||||
This synapse is built for **Pattern Recognition**. It is the "Guardian of Persistence."
|
||||
|
||||
- **The Logic:** It ignores isolated spikes. Because Pr is low (e.g., 0.1), it will likely "fail" to release neurotransmitters on the first spike.
|
||||
- **The Mechanism:** It has a large RRP and many reserve vesicles. While the first spike fails, it leaves behind **residual Ca2+**. This calcium builds up over multiple spikes (Facilitation).
|
||||
- **Behavior (Short-Term Facilitation):**
|
||||
- **Spike 1:** Failure (Silence).
|
||||
- **Spike 2:** Weak release.
|
||||
- **Spike 5-10:** Massive, sustained release as Pr climbs and the large vesicle pool is tapped.
|
||||
- **Functional Role:** It tells the brain, *"This signal is important because it is continuing."* This is vital for maintaining posture, holding a thought in working memory, or filtering out random "glitches" in sensory input.
|
||||
|
||||
The Low Pr / High Vesicle synapse maintains its identity by using "chemical sponges" to resist the first spike.
|
||||
|
||||
- **Calcium Buffering:** These synapses are often packed with calcium-binding proteins like **Calbindin** or **Parvalbumin**. These act as "sponges" that soak up the initial influx of Ca2+.
|
||||
- **Effect of Modulation:** If LTP occurs, the synapse might increase the number of vesicles in its Reserve Pool or increase the size of the Postsynaptic Density (PSD).
|
||||
- However, because the "sponges" are still there, the first spike is still mostly absorbed.
|
||||
- It becomes a **"Super-Integrator"**—it still requires a burst to fire, but once it starts, it releases even *more* glutamate than before.
|
||||
- **Why it doesn't become a Starter:** To become a starter, it would have to physically move its vesicles closer to the channels (changing from loose to tight coupling), which requires a massive structural reorganization that standard modulation doesn't typically trigger.
|
||||
|
||||
### 3. The "Veto" (Inhibitory GABAergic Synapses)
|
||||
|
||||
Just like excitatory synapses, inhibitory ones have "Starter" and "Integrator" roles.
|
||||
|
||||
- **Phasic Inhibition (The Emergency Brake):** High GABA terminals. They fire immediately to "veto" a specific incoming spike. They are the "Starters" of the silence.
|
||||
- **Tonic Inhibition (The Background Hum):** These terminals release a slow, steady leak of GABA (often via spillover). They don't care about timing; they simply lower the overall "electrical tension" of the neuron, like a constant background resistance.
|
||||
|
||||
### 4. The "Broadcaster" (Volume Transmission)
|
||||
|
||||
Some presynapses don't have a "target" postsynapse. They are **Varicosities**—bulges along an axon that leak neurotransmitters (like Dopamine or Serotonin) into the extracellular space.
|
||||
|
||||
- **The Logic:** They don't care about milliseconds. They change the "mood" of an entire neighborhood of neurons simultaneously.
|
||||
- **Functional Role:** Shifting the "Global Gain." They tell an entire circuit: *"Everything you hear for the next 10 seconds is important."*
|
||||
|
||||
### 5. The Echo
|
||||
|
||||
Mechanism: These synapses use a specific calcium sensor called Synaptotagmin-7. Unlike the "Starter" sensor (Syt-1), which is fast and requires a huge calcium spike, Syt-7 is slow and high-affinity.
|
||||
|
||||
Behavior: It triggers neurotransmitter release after the calcium spike has passed, leaking vesicles for 10–100ms after the action potential.
|
||||
|
||||
Functional Role: It bridges the gap between spikes. If a "Starter" is a "Click" and an "Integrator" is a "Build-up," the "Echo" is a "Reverb." It ensures the postsynaptic neuron stays slightly depolarized, making it easier for the next signal to catch.
|
||||
|
||||
### Why Starters are expensive
|
||||
|
||||
- While "Integrators" are expensive because they have to maintain a massive warehouse of vesicles (the RRP), "Starters" are expensive because of the **Metabolic Tax** of high Release Probability (Pr).
|
||||
1. **The Calcium Tax:** A High Pr synapse is built on a massive, immediate influx of Ca2+. Once those ions enter the terminal to trigger release, they must be immediately pumped *out* against a steep concentration gradient to reset the synapse for the next millisecond. This requires **ATP-dependent pumps** (like the PMCA).
|
||||
2. **The Recycling Tax:** Because Starters "spend" their budget on the first spike, they must engage in high-speed endocytosis (reclaiming the vesicle membrane) and acidification (refilling the vesicle with neurotransmitter), both of which are energy-heavy processes.
|
||||
- By diversifying into these personalities, the brain achieves **Sparse Coding**. It only uses the high-energy "Starters" when something changes, and it only uses the "Integrators" when a signal has proven it's not just a fluke. The astrocyte is the manager that ensures neither type "burns out" the local environment.
|
||||
|
||||
E' come se una sinapsi diventa starter o integrator, perche' fisicamente non puo' essere ambedue. Lo starter ha tanti VGCC vicini e RRP pochi. E' come se ci sia un tradeoff. Se spendi risorse per VGCC non ne hai per RRP. E viceversa.
|
||||
|
||||
### **The "Democracy of Release" During a Spike Train**
|
||||
|
||||
Let's visualize what 1000 terminals from one neuron might do during a 10-spike train:
|
||||
|
||||
```
|
||||
Spike 1: ████████████████ 800 terminals release (80%)
|
||||
Spike 2: ████████████ 700 release (70%) - some depletion
|
||||
Spike 3: █████████ 500 release (50%) - more depletion
|
||||
Spike 4: ██████ 350 release (35%) - significant STD
|
||||
Spike 5: ████ 250 release (25%)
|
||||
Spike 6: ███ 200 release (20%) - some recovery in fast terminals
|
||||
Spike 7: ███ 210 release (21%) - recovery balances depletion
|
||||
Spike 8: ███ 220 release (22%) - steady state reached
|
||||
Spike 9: ███ 215 release (21.5%)
|
||||
Spike 10: ███ 220 release (22%)
|
||||
```
|
||||
|
||||
**Key insight:** The **population response** adapts over time, reaching a steady-state where release rate balances with recovery rate.
|
||||
|
||||
### The Grand Summary: Presynaptic Behavior Across Scales
|
||||
|
||||
| Scale | Starter (Phasic) | Integrator (Tonic) | Astrocyte Role |
|
||||
|-------------|------------------------------------------------------------|----------------------------------------------------------------|---------------------------------------------------------------------------|
|
||||
| **Millisecond** | **Depression:** Rapidly exhausts RRP to signal "New!" | **Facilitation:** buildup signals "Persistent!" | **Clearance:** Mops up glutamate to keep signals discrete. |
|
||||
| **Seconds** | **Recovery:** Busy reloading vesicles to reset the filter. | **Augmentation:** Recruiting reserve pools for sustained drive. | **Gliotransmission:** Releases D-serine to boost the "Integrator's" impact. |
|
||||
| **Hours** | **Homeostatic Scaling:** Lowering if the "New" becomes "Old." | **Scaling:** Increasing RRP size to maintain the background state. | **Metabolic Flush:** Clears Adenosine and waste during sleep. |
|
||||
| **Lifetime** | **Tight Coupling:** Hard-wired for speed (Nanodomains). | **Loose Coupling:** Hard-wired for summation (Microdomains). | **Synaptic Pruning:** Deciding which connections are "noise" and eating them. |
|
||||
|
||||
## Changing Pr (release probability)
|
||||
|
||||
Changing the **Release Probability (Pr)** is the primary way the brain "re-codes" its software. It is essentially the process of adjusting the sensitivity of the trigger on a gun.
|
||||
|
||||
Biologically, changing comes down to managing two things: **How much calcium enters** and **how sensitive the vesicles are to that calcium.**
|
||||
|
||||
---
|
||||
|
||||
### 1. Changing the Calcium Influx (The "Fuel")
|
||||
|
||||
The most direct way to change is to alter the amount of that enters the terminal when an action potential arrives.
|
||||
|
||||
- **Channel Density:** The brain can physically add or remove **Voltage-Gated Calcium Channels (VGCCs)** at the Active Zone. More channels = more "fuel" = higher .
|
||||
- **Neuromodulators (The G-Protein Hack):** This is the most common "second-to-minute" change.
|
||||
- **Adenosine or GABA** can bind to presynaptic receptors that "muffle" the calcium channels, making them harder to open (Lower ).
|
||||
- **Dopamine or Serotonin** can often do the opposite, increasing the conductance of the channels (Higher ).
|
||||
- **Action Potential Duration:** If the "spike" lasts longer (by blocking Potassium channels), the Calcium channels stay open longer. This floods the terminal and spikes the Pr.
|
||||
|
||||
---
|
||||
|
||||
### 2. Changing the "Calcium Sensor" (The "Trigger")
|
||||
|
||||
Even with the same amount of calcium, you can change how the synapse reacts to it by swapping or modifying the **Synaptotagmin (Syt)** proteins.
|
||||
|
||||
- **Switching Isoforms:** The brain can express different versions of the trigger. **Syt-1** is a "high-threshold" trigger (requires a lot of ), while **Syt-7** is a "low-threshold" trigger.
|
||||
- **Phosphorylation:** Enzymes (like Protein Kinase C) can add a phosphate group to the proteins at the Active Zone. This acts like "greasing the trigger," making the vesicles much more likely to fuse even if calcium levels are low.
|
||||
|
||||
---
|
||||
|
||||
### 3. Changing the Distance (The "Gap")
|
||||
|
||||
This is the **Lifetime/Developmental** change you noted in your document. It is the most powerful way to lock in a personality.
|
||||
|
||||
- **Nanodomain vs. Microdomain:** * To \*\*increase \*\*, the synapse uses scaffolding proteins (like **RIM** or **Bassoon**) to physically pull the vesicles closer to the calcium channels. If the vesicle is within 20 nanometers of a channel, it "sees" the calcium immediately and fires ().
|
||||
- To \*\*decrease \*\*, the synapse moves the vesicles further away. The calcium has to diffuse across a larger space (Microdomain), losing its "punch" before it hits the trigger ().
|
||||
|
||||
---
|
||||
|
||||
### 4. The "Buffer" Hack (The "Sponge")
|
||||
|
||||
The synapse can change its Pr without touching the channels or the vesicles at all—by changing the **Calcium Buffers** (like Calbindin).
|
||||
|
||||
- **High Buffer Density:** If the terminal is packed with "calcium sponges," they soak up the incoming ions before they can reach the vesicle. This creates a **Low Integrator**.
|
||||
- **Saturation:** As these sponges get "full" (over multiple spikes), they can't soak up any more, causing to skyrocket. This is the mechanism behind **Facilitation**.
|
||||
|
||||
---
|
||||
|
||||
### Summary of Control
|
||||
|
||||
| Method | Speed | Logical Result |
|
||||
|-----------------------|------------|-------------------------------------------------------|
|
||||
| **G-Protein Modulation** | Seconds | Temporary shift in "Gain" (e.g., Caffeine/Adenosine). |
|
||||
| **Phosphorylation** | Minutes | "Super-priming" vesicles for high-intensity bursts. |
|
||||
| **Structural Re-spacing** | Days/Years | Hard-coding a "Starter" or "Integrator" identity. |
|
||||
| **Buffer Expression** | Hours | Tuning the "wait time" of an Integrator. |
|
||||
|
||||
## Neuromodulators
|
||||
|
||||
### Dopamine: The "Saliency" Sharpener
|
||||
|
||||
Dopamine acts as a "Signal-to-Noise" booster. It works on both sides of the synapse to make the "Starter" more explosive and the "Integrator" more reliable.
|
||||
|
||||
- **Presynaptic Action:** Dopamine can increase the recruitment of vesicles from the reserve pool to the RRP. It effectively "reloads" the Starter synapse faster, preventing the depletion that usually leads to boredom (habituation).
|
||||
- **Postsynaptic Action:** It often increases the conductance of AMPA receptors.
|
||||
- **The Result:** Under dopamine, the "twig snap" isn't just a sound; it becomes a **command**. It prevents the brain from filtering out details, making everything feel "novel" and "important."
|
||||
|
||||
---
|
||||
|
||||
### Caffeine & Adenosine: Removing the "Muffle"
|
||||
|
||||
To understand Caffeine, you have to understand **Adenosine**. Throughout the day, Adenosine builds up in your brain and binds to presynaptic A1 receptors.
|
||||
|
||||
- **The "Muffle" (Adenosine):** Adenosine is a natural \*\*inhibitor of \*\*. It lowers the release probability across the brain, turning your "Starters" into "Integrators." This is why, when you are tired, your reaction time slows—your brain is literally waiting for more evidence (more spikes) before it decides to fire.
|
||||
- **The "Override" (Caffeine):** Caffeine is an Adenosine antagonist; it plugs the A1 receptors so Adenosine can't get in.
|
||||
- **The Result:** By blocking the "muffle," caffeine keeps artificially high. Your synapses remain in "High-Pass Filter" mode. You become hyper-sensitive to sudden changes (the "caffeine jitters"), and your brain loses its ability to ignore steady-state "noise."
|
||||
|
||||
---
|
||||
|
||||
### The Functional Shift: From "Deep Work" to "Hyper-Vigilance"
|
||||
|
||||
When these modulators flood the system, they push the "Personalities" of your synapses toward one extreme:
|
||||
|
||||
| State | Synaptic Logic | Behavioral Outcome |
|
||||
|--------------------------|--------------------------------------------|-------------------------------------------------------------------|
|
||||
| **Normal / Rested** | Balanced Starters & Integrators. | Can focus on a task while ignoring the hum of the AC. |
|
||||
| **High Adenosine (Tired)** | Global Low (Everything is an Integrator). | Slowed thinking; requires a lot of "input" to reach a conclusion. |
|
||||
| **High Caffeine / Dopamine** | Global High (Everything is a Starter). | Hyper-alert; easily distracted by every small movement or sound. |
|
||||
|
||||
---
|
||||
|
||||
### The Cost of the Override
|
||||
|
||||
The reason we can’t stay in a "High Dopamine/High " state forever is **Metabolic Exhaustion**. Maintaining a high release probability and a massive RRP is expensive. Eventually, the presynaptic terminal runs out of the energy (ATP) required to recycle vesicles and pump calcium, leading to the "crash"—a state where even the most important "Starter" signals can't get through.
|
||||
|
||||
## PRESYNAPSE MODULATION
|
||||
|
||||
### Short-Term Plasticity - Milliseconds
|
||||
|
||||
- **Mechanism:** **Residual Calcium (C+)** and **Vesicle Depletion**.
|
||||
- **The Logic:** This is the most rapid form of modulation. If a spike occurred 20ms ago, the current C+ is fundamentally different.
|
||||
- **In "Integrators":** The residual C+ from the first spike hasn't been pumped out yet, so the second spike "sees" a higher (Facilitation).
|
||||
- **In "Starters":** The physical slot (docking site) is empty because the vesicle hasn't been replaced yet, forcing a lower Pr for the next spike (Depression).
|
||||
|
||||
### Second-to-Minute Timescale
|
||||
|
||||
- **Variable:** RRP Size and "Super-priming" (Augmentation/PTP).
|
||||
- **Mechanism:** **Munc13 and RIM Activation.**
|
||||
- **The Logic:** During high-frequency bursts (like a "thought" or a sustained motor command), the synapse doesn't just deplete; it recruits.
|
||||
- High calcium levels activate proteins like **Calmodulin**, which in turn activate **Munc13**. This speeds up the "conveyor belt," moving vesicles from the Reserve Pool to the Readily Releasable Pool (RRP).
|
||||
- This acts as a "buffer" for the Starter synapse, allowing it to recover from depletion faster than usual during intense activity.
|
||||
|
||||
### Hour-to-Day Timescale: The "Homeostatic" Filter
|
||||
|
||||
- **Variable:** Absolute Pr and Active Zone Scaling.
|
||||
- **Mechanism:** **Presynaptic Homeostatic Plasticity (PHP) and Sleep.**
|
||||
- **The Logic:** The brain must maintain a "baseline" of communication despite long-term changes in activity.
|
||||
- **Sleep:** Research suggests Pr globally decreases during sleep. This "downscales" the noise, effectively resetting the filters so that they are sensitive to new novelty the next day.
|
||||
- **PHP:** If a postsynaptic neuron becomes too quiet (e.g., due to sensory deprivation), the presynaptic terminal will increase its Pr or RRP size to "shout" louder, ensuring the "Integrator" synapses can still reach the firing threshold.
|
||||
|
||||
### Lifetime Timescale: The "Hardware" Filter
|
||||
|
||||
- **Variable:** Structural Coupling (Nanodomain vs. Microdomain).
|
||||
- **Mechanism:** **Scaffolding Proteins (Synapsin/Bassoon) and VGCC Clustering.**
|
||||
- **The Logic:** This is the "developmental" modulation. As a circuit matures, the brain decides which synapses *must* be Starters and which *must* be Integrators.
|
||||
- By physically moving Voltage-Gated Calcium Channels (VGCCs) closer to vesicles (tight coupling), the synapse becomes a permanent High- filter.
|
||||
- This "hard-wiring" is what prevents a vital "Starter" (like those in the auditory system used for sound localization) from accidentally turning into an "Integrator."
|
||||
|
||||
In the theoretical framework of your document, **Munc13** is the "Logic Controller" of the presynapse. While the action potential is the trigger, Munc13 is the protein that determines if that trigger actually results in a "bang."
|
||||
|
||||
It acts as the physical bridge between the **Metabolic Tax** and the **Temporal Logic** of the synapse.
|
||||
|
||||
---
|
||||
|
||||
## MUNC13
|
||||
|
||||
### 1. The "Conveyor Belt" Speedometer
|
||||
|
||||
Munc13 is essential for **Vesicle Priming**. A neurotransmitter vesicle cannot fuse with the membrane just by being near it; it must be "primed" (cocked like a pistol) into the Readily Releasable Pool (RRP).
|
||||
|
||||
- **In "Starters":** Munc13 is the bottleneck. Because Starters spend their entire RRP on the first spike, they face a massive "Recycling Tax." Munc13 is the worker that takes vesicles from the Reserve Pool and "primes" them onto the docking sites.
|
||||
- **The Second-to-Minute Modulation:** During high-frequency activity, $Ca^{2+}$ levels rise and activate **Calmodulin**, which in turn binds to Munc13. This "overclocks" Munc13, making it prime vesicles much faster. This is the **Augmentation/PTP** mentioned in your document—it's the mechanism that prevents a Starter from staying silent for too long during a "thought."
|
||||
|
||||
### 2. Defining the "Personality" (Nanodomains)
|
||||
|
||||
Munc13 is not floating randomly; it is part of a "scaffold" (along with proteins like RIM and Bassoon).
|
||||
|
||||
- **The Starter Logic:** In "Starters," Munc13 is positioned physically closer to the Voltage-Gated Calcium Channels (VGCCs). This creates the **Nanodomain Coupling**. Even a tiny puff of calcium is enough to reach the Munc13-primed vesicle.
|
||||
- **The Integrator Logic:** In "Integrators," Munc13 may be further away or "inhibited" by the calcium sponges (Calbindin). It requires multiple spikes for the calcium to reach the Munc13 site with enough concentration to trigger the final fusion.
|
||||
|
||||
---
|
||||
|
||||
### 3. A Theoretical Hypothesis: Munc13 as the "Hidden Memory" Slot
|
||||
|
||||
Beyond the document, there is a strong hypothesis that Munc13 is the site of **"Presynaptic Memory."**
|
||||
|
||||
- **The Theory:** Postsynaptic receptors (the "Volume") might be removed (LTD), making the synapse appear "silent" to an electrical test. However, the Munc13 proteins can remain in a **"Super-Primed" state.**
|
||||
- **The Result:** The synapse isn't "dead"; it’s just "waiting." As soon as the right temporal pattern (the "password") arrives, the super-primed Munc13 allows for an explosive release of neurotransmitters. This explains why **re-learning** is faster than initial learning—the Munc13 "hardware configuration" was saved.
|
||||
|
||||
### 4. Metabolic Impact
|
||||
|
||||
Munc13 activity is a major driver of the **Recycling Tax**.
|
||||
|
||||
- Because Munc13 requires metabolic energy to organize the SNARE complex (the fusion machinery), high Munc13 activity signals to the **Astrocyte** that the synapse is in "Active Learning" mode.
|
||||
- If Munc13 is mutated or inhibited, the synapse loses its "Personality"—it can't recover fast enough to be a Starter, and it can't accumulate enough evidence to be an Integrator.
|
||||
|
||||
---
|
||||
|
||||
### Summary Table: Munc13's Role by Synapse Type
|
||||
|
||||
| **Synapse Type** | **Munc13 Positioning** | **Behavioral Result** |
|
||||
|-------------------|---------------------------------|---------------------------------------------------------------------------------|
|
||||
| **Starter** | Tight Coupling (Close to VGCCs) | Immediate firing; high depletion; fast recovery via $Ca^{2+}$-activated Munc13. |
|
||||
| **Integrator** | Loose Coupling (Far from VGCCs) | Delayed firing; requires Munc13 "warm-up" over several spikes. |
|
||||
| **Veto (Inhibitory)** | High-density Munc13 clusters | Instant "Emergency Brake" response. |
|
||||
|
||||
**Would you like me to analyze what happens to this Munc13 "conveyor belt" when the "Global Gain" (Dopamine/Serotonin) intervenes?**
|
||||
|
||||
---
|
||||
|
||||
## PRE and POST collaboration
|
||||
|
||||
### Presynaptic Modulation: The "Filter" (Temporal Dynamics)
|
||||
|
||||
**Goal: Changing the *meaning* of a pattern over time.**
|
||||
|
||||
When the brain modulates the presynapse (by changing or the Vesicle Pool), it isn't just making the connection stronger; it is changing the **logic** of the synapse.
|
||||
|
||||
- **Novelty vs. Persistence:** By increasing , the brain turns a synapse into a "Novelty Detector" (Starter). By decreasing it, it turns it into a "Pattern Integrator" (Tonic).
|
||||
- **Information Density:** Presynaptic modulation allows the brain to decide *which part* of a burst is important. Does it care about the first click of a door opening (High ), or the steady hum of a background engine (Low )?
|
||||
- **Metabolic Efficiency:** Presynaptic LTD (weakening) is often the brain’s way of "silencing" a noisy channel at the source so it doesn't waste neurotransmitter on irrelevant data.
|
||||
|
||||
---
|
||||
|
||||
### Postsynaptic Modulation: The "Gain" (Absolute Power)
|
||||
|
||||
**Goal: Changing the *impact* of a signal, regardless of its timing.**
|
||||
|
||||
When the brain adds more AMPA receptors to the postsynaptic density (the "Hardware"), it is performing **Gain Control**.
|
||||
|
||||
- **Amplitude Scaling:** Unlike presynaptic changes, postsynaptic modulation typically scales the *entire* message equally. If you increase the number of receptors, Spike 1, Spike 2, and Spike 10 all get louder.
|
||||
- **Signal-to-Noise Ratio (SNR):** The postsynapse determines if a signal is strong enough to trigger an action potential in the next neuron. It acts as a "gatekeeper" that decides: *"I hear you loud and clear; now I will pass this on."*
|
||||
- **Specificity:** Because one neuron can receive inputs from 10,000 others, postsynaptic modulation allows the receiving neuron to "rank" its neighbors. It can choose to "listen" more to its neighbor from the Visual Cortex and "ignore" the neighbor from the Amygdala.
|
||||
|
||||
---
|
||||
|
||||
### The Symbiosis: Why do both?
|
||||
|
||||
The brain uses both to solve a complex problem: **How to learn something new without forgetting the old.**
|
||||
|
||||
| Feature | Presynaptic Modulation () | Postsynaptic Modulation (Receptors) |
|
||||
|--------------------|----------------------------------------------------------------------------|-------------------------------------------------------------------------|
|
||||
| **Computational Role** | **Temporal Filter:** Decides if the synapse is a "Starter" or "Integrator." | **Gain Control:** Decides the total "Volume" or "Weight" of the input. |
|
||||
| **Information Effect** | Changes the **Short-Term Dynamics** (how it reacts to bursts). | Changes the **Steady-State Strength** (how it reacts to any input). |
|
||||
| **Learning Goal** | **"Flexibility":** Allows the synapse to rapidly switch its role in a circuit. | **"Stability":** Hard-codes long-term memories into the physical structure. |
|
||||
| **Analogy** | Adjusting the **EQ settings** (Bass vs. Treble). | Adjusting the **Master Volume knob**. |
|
||||
|
||||
---
|
||||
|
||||
### The "Memory Savings" Theory
|
||||
|
||||
Recent research suggests that the brain might use the **Presynapse for "Hidden" memories**. When you "forget" a skill, your postsynaptic receptors might decrease (the volume goes to zero), but the **Presynaptic "Personality" (the software code)** often stays intact. This is why you can relearn a language or a bike-riding skill much faster the second time—the "Starter" or "Integrator" settings were never actually deleted; they were just "muted" at the postsynapse.
|
||||
|
||||
## Behavioral Examples
|
||||
|
||||
### The Presynaptic "Predictor" (Filtering the Breath)
|
||||
|
||||
Your breathing is a steady, rhythmic, and predictable signal. To prevent your brain from being overwhelmed by the constant sound of air moving, it modulates the presynapse into a **Depressing "Starter"** mode, but with a twist.
|
||||
|
||||
- **The Goal:** Habituation.
|
||||
- **The Mechanism:** The synapses carrying the "breath" signal are tuned to have a high . Because the breath is constant, these synapses are kept in a state of **chronic vesicle depletion**.
|
||||
- **The Result:** The "volume" of the breath signal is turned down at the source. The presynapse is "exhausted" by the predictability of the input, effectively acting as a **noise-canceling filter**.
|
||||
|
||||
### The Postsynaptic "Gatekeeper" (Amplifying the Twig)
|
||||
|
||||
While the presynapse is busy suppressing the "boring" breath, the postsynapse is tuned to remain highly sensitive to **unpredictable** inputs.
|
||||
|
||||
- **The Goal:** Saliency Detection.
|
||||
- **The Mechanism:** A sudden twig snap activates synapses that have been "silent." These synapses have a full **Readily Releasable Pool (RRP)**.
|
||||
- **The Cooperation:** Because the postsynapse has high-density AMPA receptors (high gain), that first, fresh burst of neurotransmitter from the twig snap triggers a massive, immediate depolarization.
|
||||
- **The Result:** The "novel" signal bypasses the filters and reaches the threshold for an action potential, triggering an immediate "alert" response.
|
||||
|
||||
Because presynaptic changes shift the probability rather than the size of the response, they are 'invisible' to a single-pulse test. A memory can remain 'dormant' in the timing logic of the presynapse, only revealing itself when a specific temporal pattern (the 'password') is played.
|
||||
|
||||
### The "Cancellation" Circuit: A Unified View
|
||||
|
||||
In more complex areas like the cerebellum or the auditory cortex, the brain actually creates a **"Negative Image"** of expected sensations.
|
||||
|
||||
| Mechanism | Role in the "Twig vs. Breath" Scenario |
|
||||
|---------------------------|----------------------------------------------------------------------------------------------------------------|
|
||||
| **Presynaptic (Dynamic)** | **Subtraction:** It uses and depletion to "subtract" the expected rhythm of your own movement/breathing. |
|
||||
| **Postsynaptic (Structural)** | **Attention:** It maintains high receptor density for "unexpected" channels so they can break through the silence. |
|
||||
|
||||
## The Tripartite System
|
||||
|
||||
### The Tripartite Modulation: Astrocytes as the "Thermostat"
|
||||
|
||||
Astrocytes wrap around synapses and act as the "logical monitors" of presynaptic output. They don't just provide support; they actively shift the synapse's personality.
|
||||
|
||||
- **The "Starter" Guard:** For high (Starter) synapses, astrocytes act as **spatial filters**. They aggressively mop up glutamate via transporters (EAATs). This prevents "spillover," ensuring the "Starter" signal remains a crisp, single-point event rather than a blurred mess.
|
||||
- **The "Integrator" Booster:** For low (Integrator) synapses, astrocytes can release **Gliotransmitters** like D-serine. This "primes" the postsynaptic NMDARs, ensuring that when the Integrator finally does fire (after the 5th or 10th spike), the signal is received with maximum impact.
|
||||
- **Feedback Inhibition:** If a synapse (of either type) fires too intensely, the astrocyte senses the high glutamate, undergoes a wave, and releases **Adenosine**. This binds back to presynaptic A1 receptors to lower , effectively "cooling down" the synapse to prevent the metabolic crash (Brain Fog) we discussed earlier.
|
||||
- The Potassium (K+) Siphon: Beyond glutamate and adenosine, astrocytes mop up the Potassium released during high-frequency firing. If the astrocyte doesn't siphon the K+, the "Integrator" synapse would stay permanently depolarized and "seize up." The astrocyte ensures the "Integrator" can reset between bursts.
|
||||
|
||||
To understand how the brain prevents metabolic "meltdown," we have to look at the **Astrocyte** as the "Local Grid Manager." If the synapse is the factory, the astrocyte is the cooling system, the power company, and the waste management team combined.
|
||||
|
||||
Here is how the brain shifts its metabolic strategy between **Active Learning** (high demand) and **Sleep** (resetting the filters).
|
||||
|
||||
---
|
||||
|
||||
### 1. Active Learning: Scaling the "Tax"
|
||||
|
||||
During active learning, "Starters" and "Integrators" are pushed to their physical limits. The astrocyte ensures they don't "burn out" through two primary mechanisms:
|
||||
|
||||
- **The Lactate Shuttle (Emergency Fuel):** As "Starters" pump $Ca^{2+}$ out via ATP-dependent pumps (the Calcium Tax), they rapidly deplete local energy. The astrocyte senses this via glutamate spillover and converts its own glycogen stores into **lactate**, which it "shuttles" directly into the presynaptic terminal. This bypasses the slower process of glucose metabolism, providing an instant "high-octane" fuel for the pumps.
|
||||
- **The Glutamate-Glutamine Vacuum:** "Starters" also face a **Recycling Tax**. To prevent the neurotransmitter from lingering and causing "noise" (or toxicity), the astrocyte vacuums up glutamate, converts it into the "safe" molecule glutamine, and hands it back to the neuron to be re-packaged.
|
||||
|
||||
### 2. Sleep: The "Global Downscaling"
|
||||
|
||||
Your document mentions that $Ca^{2+}$ globally decreases during sleep to "downscale the noise." Theoretically, this is the brain’s **Maintenance Mode**.
|
||||
|
||||
- **Synaptic Scaling:** During sleep, the brain performs "Homeostatic Downscaling." It effectively lowers the "Master Volume" (Postsynaptic Receptors) and reduces the "Baseline Calcium" ($Ca^{2+}$ concentration).
|
||||
- **The Goal:** This resets the "Starters." By lowering the baseline calcium, it ensures that the "High $P_r$" identity is sharp for the next day. If the baseline calcium stayed high, the Starters would remain in a state of chronic fatigue/depletion, losing their ability to detect "Novelty."
|
||||
- **Astrocyte "Cleaning":** During this period, the astrocyte's role shifts from "Fueling" to "Cleaning" (the Glymphatic System). It flushes out the metabolic byproducts of a day's worth of "Calcium Taxes."
|
||||
|
||||
---
|
||||
|
||||
### Summary Table: Metabolic Scaling vs. State
|
||||
|
||||
| **Feature** | **Active Learning (High Gain)** | **Sleep (Downscaling/Reset)** |
|
||||
|----------------|----------------------------------------|---------------------------------------|
|
||||
| **Primary Goal** | Feature Extraction (Novelty/Patterns) | Signal-to-Noise Ratio (SNR) Reset |
|
||||
| **Calcium Status** | High flux, high "Tax" (Active pumping) | Low baseline, "Tax" relief |
|
||||
| **Vesicle Pool** | High turnover (Recycling Tax) | Replenishment and "Super-priming" |
|
||||
| **Astrocyte Role** | Providing Lactate & Clearing Glutamate | Waste Removal & Structural Insulation |
|
||||
|
||||
### Brain Fog
|
||||
|
||||
"Brain fog" is more than a feeling; it is a physical state of **synaptic congestion**. When you’ve been awake too long or over-caffeinated, your presynaptic terminals become like a factory where the assembly line has jammed.
|
||||
|
||||
Here is how the "synaptic crash" happens and how sleep acts as the ultimate maintenance crew.
|
||||
|
||||
#### The Presynaptic "Jam": Vesicle & ATP Depletion
|
||||
|
||||
During intense periods of focus or high (Release Probability), the presynaptic terminal is under immense stress.
|
||||
|
||||
- **Vesicle "Bottleneck":** Even if you have thousands of vesicles, the "docking bays" (Active Zones) can only reset so fast. Under constant demand, the rate of **endocytosis** (recycling used vesicles) cannot keep up with **exocytosis** (releasing them).
|
||||
- **Mitochondrial Stress:** Pumping out of the terminal after every spike is incredibly energy-intensive. When ATP levels drop, the "calcium pumps" slow down.
|
||||
- **The Result:** Residual calcium builds up uncontrollably. This creates **"Noise."** The synapse starts leaking neurotransmitters at the wrong times, blurring the lines between a "Starter" and an "Integrator." This is the molecular basis of **Brain Fog**: your filters are no longer crisp.
|
||||
|
||||
#### The Postsynaptic "Saturation": AMPA Receptor Overload
|
||||
|
||||
While the presynapse is jamming, the postsynapse is becoming **saturated**.
|
||||
|
||||
- **Synaptic Scaling:** According to the **Synaptic Homeostasis Hypothesis (SHY)**, as we learn throughout the day, our synapses globally strengthen (adding more AMPA receptors).
|
||||
- **The Ceiling Effect:** Eventually, your synapses hit a "ceiling." If every synapse is "loud," nothing is "clear." The signal-to-noise ratio collapses because the background hum of the brain is now as loud as the important thoughts.
|
||||
|
||||
#### How Sleep Restores the "Personalities"
|
||||
|
||||
Sleep is the period where the brain performs **Systemic Downscaling**. It resets the hardware so the software can run again the next morning.
|
||||
|
||||
##### A. The Presynaptic "Refill"
|
||||
|
||||
During NREM (Deep) sleep, the brain's firing rates drop significantly. This provides the "quiet time" necessary for:
|
||||
|
||||
- **Vesicle Re-pooling:** The terminal finally catches up on recycling, refilling the Readily Releasable Pool (RRP).
|
||||
- **Clearing Metabolites:** The Glymphatic system flushes out Adenosine and metabolic waste that was gunking up the calcium channels.
|
||||
|
||||
##### B. The Postsynaptic "Downscaling"
|
||||
|
||||
This is the most critical part of sleep. The brain selectively weakens synapses.
|
||||
|
||||
- **Trimming the Noise:** It removes excess AMPA receptors from the "noisy" background connections while preserving the ones you used most (the memories).
|
||||
- **The Result:** By lowering the "base volume" of the brain, it creates **headroom**. When you wake up, your "Starter" synapses have a full budget to spend, and your "Integrators" have a quiet background to listen against.
|
||||
|
||||
---
|
||||
|
||||
#### Summary: The Cycle of Clarity
|
||||
|
||||
| State | Presynaptic Status | Postsynaptic Status | Mental Experience |
|
||||
|---------------------|-------------------------------|----------------------------------|-------------------------------|
|
||||
| **Morning (Restored)** | Full Vesicle Pools; High ATP. | Low "Base" Noise; High Headroom. | Sharp, fast, clear filters. |
|
||||
| **Evening (Fatigued)** | Depleted RRP; High "Leaky" . | High Saturation; No Headroom. | Brain Fog; slow processing. |
|
||||
| **Sleep (Restoration)** | Recycling & Refilling. | Selective Downscaling (LTD). | Memory consolidation & reset. |
|
||||
|
||||
This explains why **"sleeping on it"** works. You aren't just resting; you are physically rebuilding the "Starter" and "Integrator" filters that allow you to perceive the world clearly.
|
||||
|
||||
It is a common misconception that the presynapse "sucks back up" the glutamate it just released. In reality, the labor is divided, but the **Astrocyte** does the overwhelming majority of the heavy lifting.
|
||||
|
||||
If the presynapse were to reuptake its own glutamate directly, it would interfere with its own **Temporal Logic**.
|
||||
|
||||
---
|
||||
|
||||
### Re-Uptake
|
||||
|
||||
#### 1. The 90/10 Rule: Astrocyte vs. Neuron
|
||||
|
||||
In the mammalian brain, approximately **90% of glutamate reuptake** is performed by astrocytes.1
|
||||
|
||||
- **The Astrocyte (The Primary Sink):** Astrocytes express extremely high levels of transporters called **EAAT1** and **EAAT2** (Excitatory Amino Acid Transporters).2 They act like high-speed vacuums that clear the synaptic cleft in milliseconds.
|
||||
- **The Presynapse (The Specialist):** The presynaptic terminal does have some transporters (EAAT2/3), but they are not designed for bulk clearance. Instead, they serve as "sensors" or "fine-tuners" to ensure the local concentration doesn't hit toxic levels.
|
||||
|
||||
#### 2. Why the Presynapse "Outsources" this Task
|
||||
|
||||
There are three theoretical reasons, based on your document's logic, why the presynapse avoids direct reuptake:
|
||||
|
||||
##### A. Preventing "Signal Echoes"
|
||||
|
||||
If the presynapse immediately pulled glutamate back in, it might accidentally re-trigger its own autoreceptors. By having the **Astrocyte** pull the glutamate *away* from the cleft, the "Starter" synapse ensures a clean "OFF" state. This is crucial for **Novelty Detection**—the synapse needs to be silent to hear the next "new" signal.
|
||||
|
||||
##### B. The Metabolic Tax Bypass
|
||||
|
||||
Reuptake is an active process that requires moving molecules against a concentration gradient (driven by sodium/potassium gradients).3
|
||||
|
||||
- As your document notes, the "Starter" is already paying a massive **Calcium Tax**.
|
||||
- If it also had to pay the **Reuptake Tax**, the energy demand would likely lead to "burnout."
|
||||
- By letting the astrocyte do it, the neuron "outsources" the energy cost.
|
||||
|
||||
##### C. The Glutamine Safety Buffer
|
||||
|
||||
Glutamate is "electrically live" and toxic in high doses.4 If the presynapse stored raw glutamate in its cytoplasm, it would be dangerous.
|
||||
|
||||
1. The **Astrocyte** takes the glutamate and converts it into **Glutamine** (which is electrically "inert" or "silent").
|
||||
2. The astrocyte then hands the Glutamine back to the neuron.
|
||||
3. The neuron only converts it back to Glutamate *inside* the vesicle or just before packaging. This is a "safety lock" on the system.
|
||||
|
||||
---
|
||||
|
||||
#### 3. Theoretical Hypothesis: The "Identity" Protection
|
||||
|
||||
If we look at the **Integrator** synapse, which relies on **Residual Calcium** to build up a signal, the astrocyte’s speed is vital. If reuptake were slow (or handled by the neuron), the glutamate from Spike 1 would linger and mix with Spike 2, turning the "Integrator" into a messy, blurred signal.
|
||||
|
||||
The Astrocyte's rapid reuptake ensures that the **Temporal Logic** remains sharp: each spike is a discrete event, and the "integration" happens through internal calcium, not through "leftover" glutamate in the cleft.
|
||||
|
||||
---
|
||||
|
||||
#### Summary of Roles
|
||||
|
||||
| **Feature** | **The Astrocyte** | **The Presynapse** |
|
||||
|----------------|--------------------------------------------|--------------------------------------------|
|
||||
| **Share of Work** | \~90% (Bulk Clearance) | \~10% (Fine Tuning) |
|
||||
| **Molecule Form** | Converts Glutamate $\\rightarrow$ Glutamine | Converts Glutamine $\\rightarrow$ Glutamate |
|
||||
| **Primary Goal** | Prevent toxicity; metabolic support. | Signal detection; vesicle refilling. |
|
||||
| **Metabolic Cost** | High (Paid by the Astrocyte) | Low (Outsourced) |
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
## **Readily Releasable Pool of synaptic vesicles**
|
||||
|
||||
**RRP stands for the Readily Releasable Pool of synaptic vesicles.**
|
||||
|
||||
It's the subset of synaptic vesicles that are **docked at the active zone, fully primed, and immediately available for release** when calcium enters during an action potential.
|
||||
|
||||
Think of it as the **"loaded gun" analogy**: These vesicles are **cocked and ready to fire** the instant the trigger (calcium) is pulled.
|
||||
|
||||
### **The Vesicle Hierarchy in Presynaptic Terminals**
|
||||
|
||||
```
|
||||
Total Vesicle Pool (~200-500 vesicles)
|
||||
├── **RRP: Readily Releasable Pool** (5-20 vesicles)
|
||||
│ ├── **State:** Docked + Primed
|
||||
│ ├── **Location:** At active zone, touching membrane
|
||||
│ ├── **SNARE status:** Fully assembled, "zippered"
|
||||
│ └── **Release latency:** <1 ms when calcium arrives
|
||||
│
|
||||
├── **Recycling Pool** (~50-100 vesicles)
|
||||
│ ├── **State:** Recently retrieved, being refilled
|
||||
│ ├── **Location:** Just behind active zone
|
||||
│ └── **Time to readiness:** Seconds to minutes
|
||||
│
|
||||
└── **Reserve Pool** (~100-400 vesicles)
|
||||
├── **State:** Tethered to cytoskeleton
|
||||
├── **Location:** Deeper in terminal
|
||||
└── **Mobilization:** Requires phosphorylation, energy
|
||||
```
|
||||
|
||||
### **Biological Details of RRP Vesicles**
|
||||
|
||||
#### **What Makes a Vesicle "Readily Releasable"**
|
||||
|
||||
1. **Physical Docking:**
|
||||
- Vesicle is physically attached to presynaptic membrane
|
||||
- Tethered by proteins like Munc18, Syntaxin clusters
|
||||
- Distance to calcium channels: 20-30 nm (critical!)
|
||||
2. **Biochemical Priming:**
|
||||
- **SNARE complex assembled:**
|
||||
- Synaptobrevin (on vesicle) + Syntaxin/SNAP-25 (on membrane)
|
||||
- **Complexin loaded:** "Clamps" the SNARE complex
|
||||
- **Synaptotagmin positioned:** Calcium sensor ready
|
||||
- Energy invested: ATP used to "spring-load" the system
|
||||
3. **Calcium Channel Coupling:**
|
||||
- VGCCs physically linked via RIM proteins
|
||||
- Creates "nanodomain" where [Ca²⁺] spikes to ~50 µM
|
||||
- Tight coupling ensures rapid calcium sensing
|
||||
|
||||
#### **The Lifecycle of an RRP Vesicle**
|
||||
|
||||
```
|
||||
New vesicle from Golgi
|
||||
↓
|
||||
Transport to terminal
|
||||
↓
|
||||
Docking at active zone (seconds)
|
||||
↓
|
||||
Priming via Munc13 (ATP required)
|
||||
↓
|
||||
**ENTER RRP** (ready for release)
|
||||
↓
|
||||
Action Potential → Ca²⁺ influx
|
||||
↓
|
||||
**FUSION** (if Pr conditions met)
|
||||
↓
|
||||
Endocytosis (clathrin-mediated, 1-10 sec)
|
||||
↓
|
||||
Endosome processing
|
||||
↓
|
||||
Refilling with neurotransmitter
|
||||
↓
|
||||
Redocking/Repriming
|
||||
↓
|
||||
**RETURN TO RRP** (10-30 seconds later)
|
||||
```
|
||||
|
||||
### **RRP Dynamics During Activity**
|
||||
|
||||
#### **Example: 10 Hz Spike Train**
|
||||
|
||||
```
|
||||
Time (ms) | RRP Size | Release Events
|
||||
----------|----------|---------------
|
||||
0 | 10 | -
|
||||
20 | 9 | Released 1 vesicle (Pr=0.3)
|
||||
40 | 8 | Released 1 vesicle (Pr=0.4)
|
||||
60 | 7 | Released 1 vesicle (Pr=0.5)
|
||||
80 | 6 | No release (Pr=0.6, but random failure)
|
||||
100 | 5 | Released 1 vesicle (Pr=0.6)
|
||||
...
|
||||
200 | 2 | RRP severely depleted
|
||||
...
|
||||
500 | 8 | Partial recovery via mobilization
|
||||
```
|
||||
|
||||
#### **RRP Recovery After Depletion**
|
||||
|
||||
```
|
||||
**Fast Recovery (100 ms - 1 sec):**
|
||||
- Local repriming of docked vesicles
|
||||
- Uses remaining ATP in terminal
|
||||
|
||||
**Medium Recovery (1-10 sec):**
|
||||
- Vesicle recycling (endocytosis + refilling)
|
||||
- Requires ATP from mitochondria
|
||||
|
||||
**Slow Recovery (10 sec - minutes):**
|
||||
- Reserve pool mobilization
|
||||
- Requires phosphorylation (CaMKII, PKA)
|
||||
- Energy-intensive process
|
||||
```
|
||||
|
||||
### **Why RRP Size Matters**
|
||||
|
||||
#### **1. Sets Maximum Release Rate:**
|
||||
|
||||
- **Maximum release rate = RRP size × Pr**
|
||||
- Example: RRP=10, Pr=0.3 → max 3 vesicles/spike initially
|
||||
- Limits information transmission bandwidth
|
||||
|
||||
#### **2. Determines Short-Term Plasticity:**
|
||||
|
||||
- **Facilitation:** RRP not depleted → successive spikes get more reliable release
|
||||
- **Depression:** RRP depleted → transmission fails despite high Pr
|
||||
- **Balance** between facilitation and depression creates complex filtering
|
||||
|
||||
#### **3. Influences Information Coding:**
|
||||
|
||||
- Small RRP (2-5 vesicles): More stochastic, good for coincidence detection
|
||||
- Large RRP (20-50 vesicles): More reliable, good for high-frequency transmission
|
||||
|
||||
### **Biological Regulation of RRP Size**
|
||||
|
||||
#### **Increasing RRP (LTP-like changes):**
|
||||
|
||||
```
|
||||
Retrograde signals (NO, BDNF)
|
||||
↓
|
||||
Activate kinases (PKA, PKC, CaMKII)
|
||||
↓
|
||||
Phosphorylate:
|
||||
1. **Synapsin:** Releases vesicles from reserve pool
|
||||
2. **Munc13:** Increases priming rate
|
||||
3. **RIM proteins:** Enhances docking
|
||||
↓
|
||||
**RRP size increases from 10 → 15 vesicles**
|
||||
```
|
||||
|
||||
#### **Decreasing RRP (Fatigue/Pathology):**
|
||||
|
||||
```
|
||||
Energy depletion (low ATP)
|
||||
↓
|
||||
1. Priming stops (Munc13 needs ATP)
|
||||
2. Synapsin dephosphorylated → vesicles locked in reserve
|
||||
3. Vesicle recycling slows
|
||||
↓
|
||||
**RRP size decreases from 10 → 3 vesicles**
|
||||
```
|
||||
|
||||
### **Synaptic Types Have Different RRP Properties**
|
||||
|
||||
| **Synapse Type** | **Typical RRP Size** | **Specialization** |
|
||||
|---------------------------|--------------------|--------------------------------|
|
||||
| **Cortical excitatory** | 5-15 vesicles | Small, high Pr variability |
|
||||
| **Hippocampal mossy fiber** | 20-50 vesicles | Large, facilitates strongly |
|
||||
| **Cerebellar parallel fiber** | 1-3 vesicles | Very small, high failure rate |
|
||||
| **Neuromuscular junction** | 50-200 vesicles | Huge, reliable (Pr ≈ 0.9) |
|
||||
| **Retinal ribbon synapse** | Continuous release | No true RRP, sustained release |
|
||||
|
||||
### **RRP in Learning and Memory**
|
||||
|
||||
#### **During LTP:**
|
||||
|
||||
```
|
||||
Postsynaptic retrograde signals
|
||||
↓
|
||||
Presynaptic changes:
|
||||
1. More vesicles docked (RRP↑)
|
||||
2. Faster priming (recovery↑)
|
||||
3. Better channel-vesicle coupling
|
||||
↓
|
||||
**Result:** Synapse can sustain higher-frequency transmission
|
||||
```
|
||||
|
||||
#### **During LTD:**
|
||||
|
||||
```
|
||||
Postsynaptic eCB release
|
||||
↓
|
||||
Presynaptic inhibition
|
||||
↓
|
||||
1. Fewer vesicles docked (RRP↓)
|
||||
2. Slower priming
|
||||
↓
|
||||
**Result:** Synapse fatigues quickly, transmits less reliably
|
||||
```
|
||||
|
||||
### **Key Takeaways**
|
||||
|
||||
1. **RRP is the "front line" of neurotransmission** - vesicles ready for immediate release
|
||||
2. **Size is dynamic** - changes with activity, energy, and plasticity
|
||||
3. **Determines synaptic reliability** - small RRP = more stochastic transmission
|
||||
4. **Subject to depletion** - causes short-term depression during sustained activity
|
||||
5. **Regulated by multiple kinases** - links to learning mechanisms
|
||||
|
||||
The RRP represents a **critical bottleneck** in synaptic transmission where molecular machinery, energy availability, and plasticity signals converge to determine whether and how strongly a presynaptic spike will be communicated to the postsynaptic neuron.
|
||||
|
||||
## ATP from SOMA and ASTRO
|
||||
|
||||
### 1. Internal Production (The Primary, Immediate Source)
|
||||
|
||||
The presynaptic terminal is an energy-intensive machine, and evolution has placed the power plants right at the site of demand.
|
||||
|
||||
- **Local Mitochondria:** Most presynaptic boutons, especially in central nervous system neurons, contain **one or several mitochondria**. These are strategically positioned near active zones and vesicle pools.
|
||||
- **Direct Coupling to Demand:** ATP production is tightly coupled to calcium influx.
|
||||
- **Activity → Ca²⁺ influx →** Mitochondrial uptake of Ca²⁺ **→** Stimulation of mitochondrial dehydrogenases **→** Increased ATP production via oxidative phosphorylation.
|
||||
- This creates an **on-demand, auto-regulatory power supply** that scales with synaptic activity in real-time.
|
||||
- **Critical for Superpriming:** The processes you asked about—Munc13 activation, vesicle priming (SNARE complex assembly), synapsin phosphorylation to mobilize reserve pools, and vesicle reloading with neurotransmitter—are all **ATP-dependent**. Local mitochondria provide the immediate, high-flux ATP needed to sustain this during a spike train.
|
||||
|
||||
### 2. Astrocytic Support (The Secondary, Sustaining Source)
|
||||
|
||||
Astrocytes form the "metabolic cradle" around synapses. They don't typically provide direct ATP to neurons but supply the *fuel* and perform *maintenance*.
|
||||
|
||||
- **The Lactate Shuttle (ANLSH):** The dominant model is the **Astrocyte-Neuron Lactate Shuttle**.
|
||||
1. During synaptic activity, glutamate released from the neuron is taken up by astrocytic transporters (a process that consumes astrocyte-derived ATP).
|
||||
2. This triggers glycolysis in the astrocyte, producing **lactate**.
|
||||
3. Lactate is exported to the extracellular space and taken up by the neuron.
|
||||
4. In the neuronal presynaptic terminal, lactate is converted to pyruvate and used in **mitochondria to produce more ATP** via oxidative phosphorylation.
|
||||
- **Role:** Astrocytic lactate is **not the primary fuel for burst activity** but is critical for:
|
||||
- **Recovery & Sustenance:** Replenishing neuronal energy stores *after* intense activity.
|
||||
- **Long-term Maintenance:** Supporting baseline metabolic needs.
|
||||
- **Glycogen Buffer:** Astrocytes store glycogen, which can be broken down to glucose and then lactate during periods of high demand or low blood glucose, acting as an emergency energy reserve for the brain.
|
||||
@@ -0,0 +1,383 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Tripartite Synapse Model</title>
|
||||
<script crossorigin src="https://unpkg.com/react@18/umd/react.production.min.js"></script>
|
||||
<script crossorigin src="https://unpkg.com/react-dom@18/umd/react-dom.production.min.js"></script>
|
||||
<script src="https://unpkg.com/@babel/standalone/babel.min.js"></script>
|
||||
<script src="https://cdn.tailwindcss.com"></script>
|
||||
</head>
|
||||
<body>
|
||||
<div id="root"></div>
|
||||
|
||||
<script type="text/babel">
|
||||
const { useState } = React;
|
||||
|
||||
// Simple icon components
|
||||
const Play = () => (
|
||||
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||
<polygon points="5 3 19 12 5 21 5 3"></polygon>
|
||||
</svg>
|
||||
);
|
||||
|
||||
const Pause = () => (
|
||||
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||
<rect x="6" y="4" width="4" height="16"></rect>
|
||||
<rect x="14" y="4" width="4" height="16"></rect>
|
||||
</svg>
|
||||
);
|
||||
|
||||
const RotateCcw = () => (
|
||||
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
|
||||
<polyline points="1 4 1 10 7 10"></polyline>
|
||||
<path d="M3.51 15a9 9 0 1 0 2.13-9.36L1 10"></path>
|
||||
</svg>
|
||||
);
|
||||
|
||||
const TripartiteSynapseModel = () => {
|
||||
const [timeScale, setTimeScale] = useState('milliseconds');
|
||||
const [isPlaying, setIsPlaying] = useState(false);
|
||||
const [time, setTime] = useState(0);
|
||||
const [synapseType, setSynapseType] = useState('starter');
|
||||
|
||||
const timeScales = [
|
||||
{ id: 'milliseconds', label: 'Milliseconds', duration: '1-100ms' },
|
||||
{ id: 'seconds', label: 'Seconds to Minutes', duration: '1s-10min' },
|
||||
{ id: 'hours', label: 'Hours to Days', duration: '1hr-24hr' },
|
||||
{ id: 'lifetime', label: 'Lifetime', duration: 'Weeks-Years' }
|
||||
];
|
||||
|
||||
const modelStates = {
|
||||
milliseconds: {
|
||||
starter: {
|
||||
presynapse: {
|
||||
title: "Short-Term Depression",
|
||||
variables: ["Ca²⁺ residual: HIGH → LOW", "RRP: FULL → DEPLETED", "Pr: 0.8 → 0.95 (spike 1) → 0.2 (spike 2)"],
|
||||
mechanism: "Nanodomain coupling + Vesicle depletion",
|
||||
behavior: "Spike 1: Strong release. Spike 2-10: Weak/Silent"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Receptor Response",
|
||||
variables: ["AMPA activation: STRONG → Weak", "Depolarization: +15mV → +2mV"],
|
||||
mechanism: "Reduced glutamate availability",
|
||||
behavior: "Strong initial response, rapid decay"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Glutamate Clearance",
|
||||
variables: ["EAAT1/2 activity: RAPID uptake", "Glutamate: 1mM → 1µM in <5ms"],
|
||||
mechanism: "High-speed vacuum (90% clearance)",
|
||||
behavior: "Prevents spillover, maintains temporal precision"
|
||||
}
|
||||
},
|
||||
integrator: {
|
||||
presynapse: {
|
||||
title: "Short-Term Facilitation",
|
||||
variables: ["Ca²⁺ residual: LOW → ACCUMULATING", "RRP: Full, untapped", "Pr: 0.1 → 0.3 → 0.7 (facilitation)"],
|
||||
mechanism: "Ca²⁺ buffer saturation + Microdomain coupling",
|
||||
behavior: "Spike 1: Fail. Spike 5-10: Massive release"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Integrative Response",
|
||||
variables: ["AMPA activation: Weak → STRONG", "NMDA: Mg²⁺ block removal"],
|
||||
mechanism: "Temporal summation + voltage relief",
|
||||
behavior: "Weak initially, explosive after pattern"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Pattern Recognition",
|
||||
variables: ["D-serine release: Increasing", "Ca²⁺ wave: Building"],
|
||||
mechanism: "Sensing sustained glutamate",
|
||||
behavior: "Primes NMDARs for integration"
|
||||
}
|
||||
}
|
||||
},
|
||||
seconds: {
|
||||
starter: {
|
||||
presynapse: {
|
||||
title: "Augmentation/Recovery",
|
||||
variables: ["Munc13 activity: ↑ (Calmodulin)", "RRP refill rate: ACCELERATED", "Reserve pool → RRP"],
|
||||
mechanism: "Ca²⁺-Calmodulin-Munc13 pathway",
|
||||
behavior: "Faster recovery during bursts, maintains starter identity"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Receptor Trafficking",
|
||||
variables: ["AMPA lateral diffusion", "Receptor stabilization at PSD"],
|
||||
mechanism: "CaMKII phosphorylation",
|
||||
behavior: "Fine-tuning gain without changing timing logic"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Lactate Shuttle",
|
||||
variables: ["Glycogen → Lactate", "ATP supply to terminal"],
|
||||
mechanism: "Metabolic support for Ca²⁺ pumps",
|
||||
behavior: "Prevents energy depletion, sustains high Pr"
|
||||
}
|
||||
},
|
||||
integrator: {
|
||||
presynapse: {
|
||||
title: "PTP (Post-Tetanic Potentiation)",
|
||||
variables: ["Reserve pool mobilization: ↑↑", "Pr: Sustained elevation", "VGCC phosphorylation"],
|
||||
mechanism: "PKC activation, enhanced Ca²⁺ sensitivity",
|
||||
behavior: "Remains integrator but with larger amplitude"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Early LTP Induction",
|
||||
variables: ["CaMKII activation", "AMPA insertion: Beginning", "Spine enlargement: +10-20%"],
|
||||
mechanism: "NMDAR-dependent Ca²⁺ signaling",
|
||||
behavior: "Gain increase, maintains integration logic"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Gliotransmitter Release",
|
||||
variables: ["D-serine, ATP release", "Ca²⁺ waves propagating"],
|
||||
mechanism: "Metabotropic glutamate sensing",
|
||||
behavior: "Amplifies synaptic strength regionally"
|
||||
}
|
||||
}
|
||||
},
|
||||
hours: {
|
||||
starter: {
|
||||
presynapse: {
|
||||
title: "Homeostatic Scaling",
|
||||
variables: ["Pr: Global adjustment", "Active zone proteins: Remodeling", "VGCC density: Fine-tuning"],
|
||||
mechanism: "Presynaptic homeostatic plasticity (PHP)",
|
||||
behavior: "Maintains starter personality despite activity changes"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Synaptic Downscaling",
|
||||
variables: ["AMPA receptors: ↓ 20-30%", "Spine size: Normalization"],
|
||||
mechanism: "Sleep-dependent homeostasis (SHY)",
|
||||
behavior: "Reduces background noise, resets dynamic range"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Glymphatic Clearance",
|
||||
variables: ["Adenosine accumulation → clearance", "Metabolite washout", "K⁺ buffering reset"],
|
||||
mechanism: "Sleep-enhanced extracellular space expansion",
|
||||
behavior: "System-wide metabolic reset, prevents fog"
|
||||
}
|
||||
},
|
||||
integrator: {
|
||||
presynapse: {
|
||||
title: "Vesicle Pool Expansion",
|
||||
variables: ["Reserve pool: +50-100%", "Synapsin scaffolding: ↑"],
|
||||
mechanism: "Activity-dependent protein synthesis",
|
||||
behavior: "Enhanced capacity for sustained signaling"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Late LTP Consolidation",
|
||||
variables: ["AMPA receptors: Stable ↑", "PSD size: +40-60%", "New protein synthesis"],
|
||||
mechanism: "CREB-dependent gene transcription",
|
||||
behavior: "Permanent gain increase, pattern memory solidified"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Structural Remodeling",
|
||||
variables: ["Process extension/retraction", "Synaptic coverage optimization"],
|
||||
mechanism: "Activity-dependent morphological plasticity",
|
||||
behavior: "Adjusts spatial filtering and metabolic support"
|
||||
}
|
||||
}
|
||||
},
|
||||
lifetime: {
|
||||
starter: {
|
||||
presynapse: {
|
||||
title: "Hard-Wired Identity",
|
||||
variables: ["Nanodomain coupling: LOCKED", "RIM/Bassoon scaffold: Stable", "VGCC clustering: Dense"],
|
||||
mechanism: "Developmental scaffolding proteins",
|
||||
behavior: "Permanent starter architecture, resists conversion"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Circuit Integration",
|
||||
variables: ["Receptor subunit composition: Stable", "Spine morphology: Mature"],
|
||||
mechanism: "Critical period closure",
|
||||
behavior: "Locked into functional role in circuit"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Territorial Establishment",
|
||||
variables: ["Domain boundaries: Fixed", "Transporter expression: Optimized"],
|
||||
mechanism: "Developmental tiling and competition",
|
||||
behavior: "Stable metabolic support infrastructure"
|
||||
}
|
||||
},
|
||||
integrator: {
|
||||
presynapse: {
|
||||
title: "Microdomain Architecture",
|
||||
variables: ["Loose VGCC-vesicle coupling: STABLE", "Large reserve pool: Maintained", "Ca²⁺ buffer density: High"],
|
||||
mechanism: "Synapsin/scaffolding configuration",
|
||||
behavior: "Permanent integrator identity, structural constraint"
|
||||
},
|
||||
postsynapse: {
|
||||
title: "Memory Substrate",
|
||||
variables: ["Enhanced PSD complexity", "Multi-synapse contacts"],
|
||||
mechanism: "Experience-dependent structural consolidation",
|
||||
behavior: "Encodes pattern memories in physical structure"
|
||||
},
|
||||
astrocyte: {
|
||||
title: "Metabolic Specialization",
|
||||
variables: ["Glycogen stores: Optimized", "Mitochondrial positioning"],
|
||||
mechanism: "Long-term metabolic adaptation",
|
||||
behavior: "Specialized support for high-demand synapses"
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const currentState = modelStates[timeScale][synapseType];
|
||||
|
||||
return (
|
||||
<div className="w-full max-w-6xl mx-auto p-6 bg-gradient-to-br from-slate-50 to-blue-50 rounded-lg">
|
||||
<div className="mb-8">
|
||||
<h1 className="text-3xl font-bold text-slate-800 mb-2">Tripartite Synapse Temporal Model</h1>
|
||||
<p className="text-slate-600">Exploring presynapse, postsynapse, and astrocyte behavior across timescales</p>
|
||||
</div>
|
||||
|
||||
<div className="grid grid-cols-1 md:grid-cols-2 gap-4 mb-8">
|
||||
<div>
|
||||
<label className="block text-sm font-semibold text-slate-700 mb-2">Synapse Type</label>
|
||||
<div className="flex gap-2">
|
||||
<button
|
||||
onClick={() => setSynapseType('starter')}
|
||||
className={`flex-1 px-4 py-2 rounded-lg font-medium transition-all ${
|
||||
synapseType === 'starter'
|
||||
? 'bg-orange-500 text-white shadow-lg'
|
||||
: 'bg-white text-slate-700 hover:bg-orange-50'
|
||||
}`}
|
||||
>
|
||||
Starter (High Pr)
|
||||
</button>
|
||||
<button
|
||||
onClick={() => setSynapseType('integrator')}
|
||||
className={`flex-1 px-4 py-2 rounded-lg font-medium transition-all ${
|
||||
synapseType === 'integrator'
|
||||
? 'bg-blue-500 text-white shadow-lg'
|
||||
: 'bg-white text-slate-700 hover:bg-blue-50'
|
||||
}`}
|
||||
>
|
||||
Integrator (Low Pr)
|
||||
</button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div>
|
||||
<label className="block text-sm font-semibold text-slate-700 mb-2">Time Scale</label>
|
||||
<select
|
||||
value={timeScale}
|
||||
onChange={(e) => setTimeScale(e.target.value)}
|
||||
className="w-full px-4 py-2 rounded-lg border-2 border-slate-200 bg-white text-slate-700 font-medium focus:border-blue-400 focus:outline-none"
|
||||
>
|
||||
{timeScales.map(scale => (
|
||||
<option key={scale.id} value={scale.id}>
|
||||
{scale.label} ({scale.duration})
|
||||
</option>
|
||||
))}
|
||||
</select>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div className="grid grid-cols-1 md:grid-cols-3 gap-6">
|
||||
<div className="bg-white rounded-xl shadow-lg p-6 border-t-4 border-orange-400">
|
||||
<div className="flex items-center gap-2 mb-4">
|
||||
<div className="w-3 h-3 bg-orange-400 rounded-full"></div>
|
||||
<h2 className="text-xl font-bold text-slate-800">Presynapse</h2>
|
||||
</div>
|
||||
|
||||
<h3 className="text-lg font-semibold text-orange-600 mb-3">
|
||||
{currentState.presynapse.title}
|
||||
</h3>
|
||||
|
||||
<div className="mb-4">
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Key Variables</p>
|
||||
<ul className="space-y-1">
|
||||
{currentState.presynapse.variables.map((v, i) => (
|
||||
<li key={i} className="text-sm text-slate-700">• {v}</li>
|
||||
))}
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div className="mb-4">
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Mechanism</p>
|
||||
<p className="text-sm text-slate-700">{currentState.presynapse.mechanism}</p>
|
||||
</div>
|
||||
|
||||
<div>
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Behavior</p>
|
||||
<p className="text-sm text-slate-700 italic">{currentState.presynapse.behavior}</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div className="bg-white rounded-xl shadow-lg p-6 border-t-4 border-blue-400">
|
||||
<div className="flex items-center gap-2 mb-4">
|
||||
<div className="w-3 h-3 bg-blue-400 rounded-full"></div>
|
||||
<h2 className="text-xl font-bold text-slate-800">Postsynapse</h2>
|
||||
</div>
|
||||
|
||||
<h3 className="text-lg font-semibold text-blue-600 mb-3">
|
||||
{currentState.postsynapse.title}
|
||||
</h3>
|
||||
|
||||
<div className="mb-4">
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Key Variables</p>
|
||||
<ul className="space-y-1">
|
||||
{currentState.postsynapse.variables.map((v, i) => (
|
||||
<li key={i} className="text-sm text-slate-700">• {v}</li>
|
||||
))}
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div className="mb-4">
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Mechanism</p>
|
||||
<p className="text-sm text-slate-700">{currentState.postsynapse.mechanism}</p>
|
||||
</div>
|
||||
|
||||
<div>
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Behavior</p>
|
||||
<p className="text-sm text-slate-700 italic">{currentState.postsynapse.behavior}</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div className="bg-white rounded-xl shadow-lg p-6 border-t-4 border-emerald-400">
|
||||
<div className="flex items-center gap-2 mb-4">
|
||||
<div className="w-3 h-3 bg-emerald-400 rounded-full"></div>
|
||||
<h2 className="text-xl font-bold text-slate-800">Astrocyte</h2>
|
||||
</div>
|
||||
|
||||
<h3 className="text-lg font-semibold text-emerald-600 mb-3">
|
||||
{currentState.astrocyte.title}
|
||||
</h3>
|
||||
|
||||
<div className="mb-4">
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Key Variables</p>
|
||||
<ul className="space-y-1">
|
||||
{currentState.astrocyte.variables.map((v, i) => (
|
||||
<li key={i} className="text-sm text-slate-700">• {v}</li>
|
||||
))}
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div className="mb-4">
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Mechanism</p>
|
||||
<p className="text-sm text-slate-700">{currentState.astrocyte.mechanism}</p>
|
||||
</div>
|
||||
|
||||
<div>
|
||||
<p className="text-xs font-semibold text-slate-500 uppercase mb-2">Behavior</p>
|
||||
<p className="text-sm text-slate-700 italic">{currentState.astrocyte.behavior}</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div className="mt-8 bg-gradient-to-r from-slate-700 to-slate-800 rounded-xl p-6 text-white">
|
||||
<h3 className="text-lg font-bold mb-3">Timescale Summary: {timeScales.find(s => s.id === timeScale)?.label}</h3>
|
||||
<p className="text-slate-200">
|
||||
{timeScale === 'milliseconds' && 'Fast temporal dynamics: Residual Ca²⁺ and vesicle depletion drive short-term plasticity. Astrocytes ensure temporal precision through rapid glutamate clearance.'}
|
||||
{timeScale === 'seconds' && 'Augmentation phase: Munc13 activation and metabolic support enable sustained activity. Astrocytes provide lactate shuttle and gliotransmitter modulation.'}
|
||||
{timeScale === 'hours' && 'Homeostatic regulation: Synaptic downscaling during sleep resets the system. Astrocytes perform glymphatic clearance to prevent metabolic fog.'}
|
||||
{timeScale === 'lifetime' && 'Structural consolidation: Scaffolding proteins lock synaptic identity. Developmental programs establish permanent nanodomain vs microdomain coupling.'}
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
);
|
||||
};
|
||||
|
||||
ReactDOM.render(<TripartiteSynapseModel />, document.getElementById('root'));
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,348 @@
|
||||
# Milliseconds Time Scale
|
||||
|
||||
## N-SPK
|
||||
|
||||
### Presynapse
|
||||
|
||||
#### 1 - Ca+ Clearance: \[AP\], \[Ca+\], \[CaFullnessTraces\], \[CaNotEmptyTraces\]
|
||||
|
||||
*Questa e’ una novita’ per evitare di fare controlli sempre. Invece viene attivato il contesto allo Spike, e invece di sparire alla fine dello spike, sparisce da solo (ContextSelf)*
|
||||
|
||||
- **RF**: 1
|
||||
- **InContext**: Action potential depolarization (to \~+30 mV)
|
||||
- **Context Self**
|
||||
- **Condition: IF** \[Ca+\] **FULLNESS**
|
||||
- **OutContext**: {Ca+ FULLNESS}
|
||||
- **Consequence:** Ca+ clearance fast
|
||||
- **Tracce:** \[CaFullnessTraces\]
|
||||
- **Condition: IF** \[Ca+\] **NOT EMPTY AND \[**Ca+\] **NOT FULLNESS**
|
||||
- **OutContext**: {Ca+ NOT EMPTY}
|
||||
- **Consequence:** Ca+ clearance slow
|
||||
- **Tracce:** \[CaNotEmptyTraces\]
|
||||
- **Condition: IF** \[Ca+\] **EMPTY**
|
||||
- **EndContext**: Self
|
||||
|
||||
#### 2 - VGCC open: \[AP\], \[Ca+\], \[CaFullnessTraces\]
|
||||
|
||||
- **RF**: 1
|
||||
- **InContext**: Action potential depolarization (to \~+30 mV)
|
||||
- **Consequence**: \[Ca+\] concentration increase
|
||||
- **Tracce**: Se Ca+ FULLNESS, lascio tracce di overflow per modulazione DOWN, da capire UP
|
||||
|
||||
#### 3 - Vescicle release: \[Ca+\], \[RRP\], \[NT\]
|
||||
|
||||
*Il rilascio di NT avviene solo se Ca+ FULLNESS? Ovviamente se ci sono Vesciche. O dipende da altro? Cioe’ cosi’ rilascerebbe tutte le vesciche se c’e’ fullness. Dovremmo mettere un tag, o una discesa improvvisa di Ca+ al release di una vescica. Perche’ potremmo avere il caso che i VGGC sia talmente tanti da far entrare tanto calcio da far si che la prima vescica consumi CA ma non abbastanza da andare sotto FULLNESS*
|
||||
|
||||
- **RF**: 1
|
||||
- **InContext**: Action potential depolarization (to \~+30 mV)
|
||||
- **Condition: IF** Ca+ **FULLNESS** **AND** RRP **NOT EMPTY (AND NOT** VES)
|
||||
- **Consequence**: Glutamate vescicle release.
|
||||
- **Consequence:** Si consumano i Ca+?
|
||||
- **Traces**: Lascio tracce di non possibilita’ per la modulazione UP, da capire DOWN
|
||||
|
||||
#### 4 - Lactate uptake
|
||||
|
||||
Il Lactate viene mandato da Astro che ha fatto re-uptake di Glutamate, trasformato in Glutamine e poi Lactate. Il Lactate serve a fare ATP
|
||||
|
||||
- **Timing**: > 10 ms
|
||||
|
||||
#### 5 - Vescicle moved to RRP
|
||||
|
||||
From **The Reserve Pool** and **Recently Endocytosed Vesicles**
|
||||
|
||||
- **For Presynaptic Strengthening (e.g., LTP):**
|
||||
- **Nitric Oxide (NO):** A gas that diffuses freely. During postsynaptic LTP induction (strong NMDAR activation), neuronal NO synthase (nNOS) is activated. NO diffuses into the presynaptic terminal and activates soluble guanylyl cyclase (sGC), raising cGMP levels. This enhances vesicle release via PKG, contributing to **presynaptic LTP**.
|
||||
- **Endocannabinoid-Mediated *LTP* (eLTP):** In some synapses, a **postsynaptic** depolarization triggers production of endocannabinoids (e.g., 2-AG). These bind to presynaptic **CB1 receptors**, but surprisingly, can initiate a signaling cascade (involving cAMP/PKA) that **increases Pr** for a long period.
|
||||
- **Neurotrophins (BDNF):** Released from the postsynapse in an activity-dependent manner. Presynaptic TrkB receptors activate pathways (PI3K, MAPK) that enhance vesicle docking and Pr.
|
||||
- **For Presynaptic Weakening (e.g., LTD):**
|
||||
- **Classical Endocannabinoid-Mediated LTD (eCB-LTD):** More common. Moderate postsynaptic activity (mGluR activation or moderate Ca²⁺ rise) triggers 2-AG release. 2-AG binds presynaptic CB1 receptors, which **inhibit VGCCs** and **directly inhibit the release machinery** via Gi/o protein signaling, reducing Pr for a long time.
|
||||
- **Other Lipid Mediators** (like LPA) can also act as retrograde signals for depression.
|
||||
|
||||
|
||||
- **Mechanism**:
|
||||
- **residual calcium →** The key sensor is **Calmodulin (CaM)**. When bound to calcium, its structure changes → This Ca²⁺/Calmodulin complex then binds to and activates **Munc13**, the master regulator of vesicle priming.
|
||||
- **Munc13** is the essential protein that "primes" vesicles, making them release-ready (part of the SNARE complex assembly).
|
||||
- In its activated state (by Ca²⁺/CaM), Munc13's activity increases dramatically—by an order of magnitude or more.
|
||||
- This turns the normal, slow "drip-feed" of vesicles into a **high-speed conveyor belt**.
|
||||
- Superpriming requires ATP for phosphorylation reactions and for molecular motors that move vesicles. If the reserve pool is depleted or ATP is low, the superpriming "conveyor belt" has nothing to feed into the RRP. (Astrocyte)
|
||||
- The **vesicle reserve pool is a strictly private, local resource of each individual presynaptic bouton.** What is shared between synapses on the same axon are **signals (neuromodulators)** and **metabolic resources (energy)**, but **not the synaptic vesicles themselves.** This ensures both independent computation and cooperative metabolic support within the axonal branch.
|
||||
- ATP mostly comes from lactate from Atrocyte
|
||||
- **Timing**: < 10 ms
|
||||
- **InContext**: Ca+ **NOT EMPTY**
|
||||
- **Condition: IF** ATP **NOT EMPTY** **AND** RP **NOT EMPTY**
|
||||
- **Consequence:** Vescicles moved slow
|
||||
- **Tracce**: se non c’e’ abbastanza ATP o non ci sono abbastanza RP, lascio tracce per la modulazione UP, devo capire modulazione DOWN
|
||||
- **InContext**: Ca+ **FULLNESS**
|
||||
- **Condition: IF** ATP **NOT EMPTY** **AND** RRP **NOT EMPTY**
|
||||
- **Consequence:** Vescicles moved fast
|
||||
- **Tracce**: se non c’e’ abbastanza ATP o non ci sono abbastanza RP, lascio tracce per la modulazione UP, devo capire modulazione DOWN
|
||||
|
||||
#### Observed 1 - Upregulation of Pr
|
||||
|
||||
- **Timing**: > 10 ms
|
||||
- **Upregulation (Facilitation):** Residual Ca²⁺ from previous spikes increases P_r for next release
|
||||
|
||||
#### Observed 2 - Downregulation of Pr
|
||||
|
||||
- **Timing**: > 10 ms
|
||||
- **Downregulation (Depression):** High-frequency firing depletes readily releasable vesicle pool, decreasing P_r
|
||||
|
||||
### Postsynapse
|
||||
|
||||
#### 1 - AMPA Opening
|
||||
|
||||
- **Timing**: < 1 ms
|
||||
- **InContext:** Glutamate > **FULLNESS**
|
||||
- **OutContext:** AMPA receptor opening
|
||||
|
||||
#### 2 - Ca+ influx by AMPA
|
||||
|
||||
- **Timing**: < 1 ms
|
||||
- **InContext:** AMPA receptor opened
|
||||
- **Consequence:** Na⁺ influx
|
||||
- **Consequence:** addition to local depolarization (EPSP) from AMPA activation
|
||||
|
||||
#### 3 - Limited Ca+ influx by NMDA
|
||||
|
||||
- **Timing**: > 1 ms
|
||||
|
||||
|
||||
- **InContext:** local depolarization (EPSP) **NOT** **FULLNESS** (requires depolarization > -40mV)
|
||||
- **Consequence:** Glutamate binding to NMDA receptors (Mg²⁺-blocked initially)
|
||||
- **Consequence:** limited NMDA receptor opening → Ca²⁺ influx
|
||||
- **Consequence:** limited addition to local depolarization (EPSP) from NMDA activation
|
||||
|
||||
#### 4 - Depolarization by bAP
|
||||
|
||||
- **Timing**: > 1 ms
|
||||
- **InContext:** bAP backpropagating action potential
|
||||
- **Consequence:** addition to local depolarization (EPSP) from bAP
|
||||
|
||||
#### 5 - Mg²⁺ NMDA unblock
|
||||
|
||||
- **Timing**: > 1 ms
|
||||
|
||||
|
||||
- **InContext:** local depolarization (EPSP) > **FULLNESS** (requires depolarization > -40mV)
|
||||
- **OutContext:** NMDA Mg²⁺ unblock
|
||||
|
||||
#### 6 - Full Ca+ influx by NDMA
|
||||
|
||||
- **Timing**: < 1 ms
|
||||
- **InContext:** NMDA Mg²⁺ unblock
|
||||
- **Consequence:** Na⁺ influx
|
||||
- **Consequence:** addition to local depolarization (EPSP) from Full NMDA activation
|
||||
|
||||
#### Observed 1 - Upregulation
|
||||
|
||||
- **Upregulation:** Depolarization relieves NMDA Mg²⁺ block → Ca²⁺ influx amplification
|
||||
|
||||
#### Observed 2 - Downregulation
|
||||
|
||||
- **Downregulation:** AMPA desensitization acts as low-pass filter
|
||||
|
||||
### Dendrite
|
||||
|
||||
### Soma
|
||||
|
||||
### AIS
|
||||
|
||||
# Seconds Time Scale
|
||||
|
||||
## N-CHAN - LTP/LTD
|
||||
|
||||
Qui si modulano i canali ionici, sia quelli voltage (PRE/POST) che quelli Neuro (POST). Non si creano o si distruggono, ma si rendono attivi disattivi quelli presenti.
|
||||
|
||||
### Presynapse
|
||||
|
||||
This is critical for **long-term** presynaptic changes. The postsynaptic cell, upon detecting specific activity patterns (like those for LTP/LTD), releases chemical signals that travel backwards to the presynaptic terminal, instructing it to change.
|
||||
|
||||
- **For Presynaptic Strengthening (e.g., LTP):**
|
||||
- **Nitric Oxide (NO):** A gas that diffuses freely. During postsynaptic LTP induction (strong NMDAR activation), neuronal NO synthase (nNOS) is activated. NO diffuses into the presynaptic terminal and activates soluble guanylyl cyclase (sGC), raising cGMP levels. This enhances vesicle release via PKG, contributing to **presynaptic LTP**.
|
||||
- **Endocannabinoid-Mediated *LTP* (eLTP):** In some synapses, a **postsynaptic** depolarization triggers production of endocannabinoids (e.g., 2-AG). These bind to presynaptic **CB1 receptors**, but surprisingly, can initiate a signaling cascade (involving cAMP/PKA) that **increases Pr** for a long period.
|
||||
- **Neurotrophins (BDNF):** Released from the postsynapse in an activity-dependent manner. Presynaptic TrkB receptors activate pathways (PI3K, MAPK) that enhance vesicle docking and Pr.
|
||||
- **For Presynaptic Weakening (e.g., LTD):**
|
||||
- **Classical Endocannabinoid-Mediated LTD (eCB-LTD):** More common. Moderate postsynaptic activity (mGluR activation or moderate Ca²⁺ rise) triggers 2-AG release. 2-AG binds presynaptic CB1 receptors, which **inhibit VGCCs** and **directly inhibit the release machinery** via Gi/o protein signaling, reducing Pr for a long time.
|
||||
- **Other Lipid Mediators** (like LPA) can also act as retrograde signals for depression.
|
||||
|
||||
#### 1 - **Augmentation:**
|
||||
|
||||
- Calcium-sensing proteins (Munc13) alter release probability (1-10s range)
|
||||
- Astrocyte gliotransmitters (ATP, D-serine, glutamate)
|
||||
- ATP and Vescicle production
|
||||
|
||||
Qui dobbiamo vedere su che scala temporale mettere questo comportamento
|
||||
- **Timing**: > 1s?
|
||||
|
||||
#### 2 - **Upregulation:**
|
||||
|
||||
- NO/BDNF activates cascades that increase P_r, promote synaptic growth (facilitates LTP)
|
||||
- VGCC modulation ??
|
||||
- Potassium channel modulation ??
|
||||
|
||||
#### 3 - **Downregulation:**
|
||||
|
||||
- eCBs bind CB1 receptors, inhibit VGCCs, activate K⁺ channels → profound decrease in P_r (DSE/DSI - depolarization-induced suppression)
|
||||
- CB1 receptor activation (by eCBs)
|
||||
|
||||
|
||||
- Retrograde BDNF (brain-derived neurotrophic factor)
|
||||
|
||||
####
|
||||
|
||||
### Postsynapse
|
||||
|
||||
#### 1 - NO Signalling
|
||||
|
||||
### Dendrite
|
||||
|
||||
### Soma
|
||||
|
||||
### AIS
|
||||
|
||||
# Hours/Day Time Scale
|
||||
|
||||
## N-Meta - Structural
|
||||
|
||||
Qui si modula la possibilita’ di potenza di fuoco, sia come nuovi recettori (voltage e neuro) sia come grandezza di RP, RRP e velocita’ di spostamento.
|
||||
|
||||
### Presynapse
|
||||
|
||||
Long-lasting presynaptic strengthening requires **new proteins**:
|
||||
|
||||
- More vesicles
|
||||
- More active zone proteins (e.g., RIM, Munc13)
|
||||
- More mitochondria (for energy)
|
||||
- More synaptic vesicle components (synaptobrevin, synaptotagmin)
|
||||
- More cytoskeletal elements for structure
|
||||
|
||||
The neuron must **detect a sustained need for strengthening at a specific synapse**, send a signal to its nucleus, transcribe genes, and then deliver the new proteins back to that specific presynaptic bouton.
|
||||
|
||||
1. **Detection:** Sustained high-frequency firing at the presynaptic terminal → elevated Ca²⁺ and/or neuromodulator release (dopamine, norepinephrine).
|
||||
2. **Signal to Nucleus:** Activation of kinases (PKA, CaMKIV) and retrograde importin signaling → **CREB phosphorylation** in the nucleus.
|
||||
3. **Transcriptional Program:** CREB induces expression of:
|
||||
- **Immediate Early Genes** (e.g., *c-Fos*, *Arc*) that regulate further transcription.
|
||||
- **Effector Genes:** Presynaptic proteins (synapsins, RIM, Munc13), BDNF, cytoskeletal proteins.
|
||||
4. **Delivery:** Newly synthesized mRNAs/proteins are actively transported down the axon, **targeted to the active synapses** that initiated the signal.
|
||||
5. **Local Implementation:**
|
||||
- Assembly of new active zones.
|
||||
- Expansion of vesicle pools.
|
||||
- Possible local translation.
|
||||
- Bouton enlargement or new bouton formation.
|
||||
6. **Stabilization:** Epigenetic modifications and continued autocrine/paracrine signaling (BDNF→TrkB) lock in the changes.
|
||||
|
||||
**In essence, the neuron "knows" to strengthen a presynapse long-term because the synapse's own sustained activity creates a biochemical signature that reaches the nucleus, triggering a gene program specifically designed to build a bigger, better release machine. This is a fundamental mechanism underlying long-term memory storage at the synaptic level.**
|
||||
|
||||
#### 1
|
||||
|
||||
- ATP-dependent vesicle cycling
|
||||
- **Metabolic veto:** Insufficient ATP prevents vesicle release despite adequate Ca²⁺
|
||||
|
||||
#### 2
|
||||
|
||||
- Glutamine→glutamate conversion (via glutaminase). Glutamine from astrocytes (glutamate-glutamine cycle)
|
||||
|
||||
#### 3
|
||||
|
||||
- Vesicle refilling with glutamate
|
||||
|
||||
#### 3
|
||||
|
||||
- Maintenance of ion gradients
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Astrocyte-supplied lactate (via monocarboxylate transporters)
|
||||
- Metabolic state indicators (ATP levels, NAD/NADH ratio)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Metabolic demand signals to astrocyte ??
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Lactate availability determines sustained release capacity during high activity ??
|
||||
|
||||
### Postsynapse
|
||||
|
||||
#### 1
|
||||
|
||||
#### 2
|
||||
|
||||
### Dendrite
|
||||
|
||||
### Soma
|
||||
|
||||
### AIS
|
||||
|
||||
## Astrocyte
|
||||
|
||||
- **Onset:** Astrocytic glutamate transporters (primarily GLT-1 and GLAST) start working **within milliseconds** of glutamate release into the synaptic cleft. They compete with postsynaptic receptors for binding glutamate.
|
||||
- **Clearance Duration:** The complete clearance of synaptically released glutamate typically takes:
|
||||
- **Tens to hundreds of milliseconds (\~20-100 ms)** at a single synapse after a single synaptic event.
|
||||
- **Up to several seconds** during and after a high-frequency spike train, as the total glutamate load is higher and transporters can become temporarily saturated.
|
||||
|
||||
#### 2. **Timing Relative to Spike Trains: During and Between**
|
||||
|
||||
- **During the Train:** With each pulse in a spike train, glutamate builds up in the cleft. Astrocytes begin uptake immediately with each release. However, during high-frequency stimulation (e.g., 50-100 Hz), release can temporarily outpace clearance, leading to **glutamate spillover** and activation of peri- or extrasynaptic receptors.
|
||||
- **Between Spikes (Inter-pulse Intervals):** This is a critical period for uptake. The \~10-20 ms between spikes in a high-frequency train is when transporters actively work to lower glutamate concentration before the next pulse arrives. This helps prevent excessive receptor desensitization and controls the temporal fidelity of synaptic transmission.
|
||||
- **After the Train:** Uptake continues for hundreds of milliseconds to seconds to fully clear the extracellular space, reset the synapse, and stop activation of extrasynaptic NMDA or metabotropic glutamate receptors (mGluRs).
|
||||
|
||||
### Milliseconds Time Scale
|
||||
|
||||
#### 1
|
||||
|
||||
#### 2
|
||||
|
||||
### Seconds Time Scale
|
||||
|
||||
#### 1
|
||||
|
||||
#### 2
|
||||
|
||||
### Minutes Time Scale
|
||||
|
||||
#### 1
|
||||
|
||||
#### 2
|
||||
|
||||
## N-SYN - Creation/destruction SYN
|
||||
|
||||
### Presynapse
|
||||
|
||||
#### 1
|
||||
|
||||
- Structural growth/retraction of presynaptic bouton. Terminal size increases/decreases (Questo lo fa con SYN del NETWORK)
|
||||
|
||||
#### 2
|
||||
|
||||
- Changes in active zone size. Development percui la PRE si specializza. Puo’ essere anche modulation senza cambiare tipo di PRE.
|
||||
|
||||
#### 3
|
||||
|
||||
- Alterations in vesicle pool size
|
||||
|
||||
**Incoming Signals??:**
|
||||
|
||||
- Retrograde trophic factors (BDNF, sustained)
|
||||
- Homeostatic scaling signals from soma
|
||||
|
||||
**Outgoing Signals??:**
|
||||
|
||||
- Modified synaptic strength through structural change
|
||||
|
||||
### Postsynapse
|
||||
|
||||
#### 1
|
||||
|
||||
#### 2
|
||||
|
||||
### Dendrite
|
||||
|
||||
### Soma
|
||||
|
||||
### Astrocyte
|
||||
|
||||
#### 1
|
||||
|
||||
#### 2
|
||||
@@ -0,0 +1,624 @@
|
||||
# Neuron Geneosophic Expression
|
||||
|
||||
*Qui la timescale la inseriamo per la verifica dei comportamenti. Ma quello che conta e’ RF, che rappresenta nella espressione G, la possibilita’ di verificare la timescale.*
|
||||
|
||||
# Spiking Neuron Behavior
|
||||
|
||||
```
|
||||
Container: N-SPK
|
||||
- Expands: 1 AXO, 1 SOMA, 3 DB
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
*Qui mettiamo i comportamenti che generalmente associamo al fare “diretto” neuronale. In [N-TUN-(MTP-MTD)]() e [N-MOD-(LTP-LTD)](https://cl.splindex.net/apps/files/files/1160115?dir=/code-server/G-notes/neuron&editing=false&openfile=true#h-n-mod-ltp-ltd) mettiamo le modulazioni di questi comportamenti.*
|
||||
|
||||
## Presynaptic Behavior
|
||||
|
||||
```
|
||||
Container: PRE
|
||||
Behavior: Presynaptic Behavior
|
||||
- ContainedBy: AXO
|
||||
- Expands: 10 VGCC
|
||||
- Modulability:
|
||||
- TUN: PRE # Possible <-> Actual, Synapting
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
*The **vesicle reserve pool is a strictly private, local resource of each individual presynaptic bouton.** What is shared between synapses on the same axon are **signals (neuromodulators)** and **metabolic resources (energy)**, but **not the synaptic vesicles themselves.** This ensures both independent computation and cooperative metabolic support within the axonal branch.*
|
||||
|
||||
### Milliseconds Time Scale
|
||||
|
||||
> AP Arrives
|
||||
> Time: t = 0 ms
|
||||
> Trigger: Depolarization from axon hillock
|
||||
> Mechanism: Na⁺/K⁺ voltage-gated channel cascade
|
||||
> State: Terminal depolarizes from -70 mV to +30 mV
|
||||
> Duration: \~1 ms
|
||||
|
||||
#### VGCC Open - Ca2+ Influx
|
||||
|
||||
```
|
||||
Container: VGCC
|
||||
Behavior: VGCC Open - Ca2+ Influx
|
||||
- ContainedBy: PRE
|
||||
- Tubs:
|
||||
- Source:
|
||||
- Ca+ #FULLNESS = 50 questo va messo nel Destination?
|
||||
- Yellow:
|
||||
- ATP #FULLNESS = 50
|
||||
- Context: AP
|
||||
- RF: 1
|
||||
- IF NOT (Ca+ FULLNESS) AND NOT (ATP EMPTY)
|
||||
- Consequence: (Ca+ increase)
|
||||
- Consequence: (ATP decrease)
|
||||
- Traces: # le tracce di CaFullnessTraces le lasciamo quando vediammo im contesti a RF piu' alto
|
||||
- Modulability:
|
||||
- TUN: VGCC # Possible <-> Actual, Postsynapsis channel tuning
|
||||
- DEV: VGCC # Possible increase/descrease
|
||||
```
|
||||
|
||||
*Auto-inhibition? Ca²⁺ binding to calmodulin on VGCC. 5-50 ms*
|
||||
|
||||
*SK Channels: non comprendiamo i K+ CHannels che si aprono quando entra Ca+ e servono a ripolazzare la presinapsi per chiudere i VGCC. Il tutto viene compreso come contestualizzazione AP.*
|
||||
|
||||
*Se Ca+FULLNESS, lascio tracce di overflow per modulazione DOWN, da capire UP*
|
||||
|
||||
> VGCC Open
|
||||
> Time: t = 0.2-0.5 ms after AP arrival
|
||||
> Trigger: Membrane depolarization > -40 mV
|
||||
> Open probability: \~0.3-0.8 during AP peak
|
||||
> Open duration: \~0.5-2 ms
|
||||
> Ca2+ Influx
|
||||
> Time: t = 0.3-1 ms after AP arrival
|
||||
> Ca²⁺ source: Extracellular (1.2 mM) → intracellular (50 nM baseline)
|
||||
> Influx rate: \~3000-10000 Ca²⁺ ions per VGCC per ms
|
||||
> Microdomain formation:
|
||||
> - Within 20 nm of VGCC: 10-100 µM
|
||||
> - At vesicle release site: 10-25 µM threshold for release
|
||||
> - Rise time: <100 µs
|
||||
> - Diffusion-limited spread: \~100-200 nm radius
|
||||
|
||||
#### Vesicle Release
|
||||
|
||||
```
|
||||
Behavior: Vesicle Release
|
||||
- ContainedBy: PRE
|
||||
- Tubs:
|
||||
- Source:
|
||||
- Ca+
|
||||
- RRP,
|
||||
- Yellow:
|
||||
- NT
|
||||
- ATP
|
||||
- TagRelease ?
|
||||
- InContext: CaFull
|
||||
- RF: 6
|
||||
- Condition: IF (Ca+ FULLNESS) AND NOT (RRP EMPTY) AND NOT (ATP EMPTY)
|
||||
- Consequence: (RRP decrease)
|
||||
- Consequence: (NT increase) # vedi nota sotto
|
||||
- Consequence: (Ca+ decrease) # ?
|
||||
- Consequence: (TagRelease increase) # check di rilascio fatto (pensiamo ad una sola vescica per AP?)
|
||||
- Consequence: (ATP decrease)
|
||||
- Traces: ?
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: RRP, (Ca+ FULLNESS) # increase/decrease RPP, increase/decrease level of (Ca+ FULLNESS)
|
||||
```
|
||||
|
||||
*Il rilascio di NT avviene solo se Ca+ FULLNESS? Ovviamente se ci sono Vesciche. O dipende da altro? Cioe’ cosi’ rilascerebbe tutte le vesciche se c’e’ fullness. Dovremmo mettere un tag, o una discesa improvvisa di Ca+ al release di una vescica. Perche’ potremmo avere il caso che i VGGC sia talmente tanti da far entrare tanto calcio da far si che la prima vescica consumi CA ma non abbastanza da andare sotto FULLNESS*
|
||||
|
||||
*Rilascio di NT: Geneosoficamente dovremmo aprire un nuovo contesto che rilascia ad un RF veloce un NT alla volta quando sei nel contesto di rilascio vescica, perche’ Geneosoficamente possiamo solo creare/distruggere blocco. Ma forse possiamo mettere un floor per efficienza: rilascio di una vescica == rilascio 1000 NT? Anche se poi l’Astrocita deve fare un uptake NT per NT?*
|
||||
|
||||
> Time: t = 0.4-1.5 ms after AP arrival
|
||||
> Decision:
|
||||
> 1. \[Ca²⁺\]microdomain > 10-25 µM
|
||||
> 2. Vesicle in RRP (docked & primed)
|
||||
> Release latency: 0.1-1.0 ms after Ca²⁺ threshold reached
|
||||
> Release synchrony: Multiple vesicles can release simultaneously
|
||||
|
||||
#### Ca+ Clearance
|
||||
|
||||
```
|
||||
Behavior: Ca+ Clearance
|
||||
- ContainedBy: PRE
|
||||
- Blocks: Ca+, ATP
|
||||
- InContext: CaMedium
|
||||
- RF: 6
|
||||
- Condition: IF NOT (Ca+ EMPTY) AND NOT (Ca+ FULLNESS) AND NOT (ATP EMPTY)
|
||||
- Consequence: (Ca+ decrease)
|
||||
- Consequence: (ATP decrease)
|
||||
- Tracce: None
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: RF
|
||||
- InContext: CaFull
|
||||
- RF: 1
|
||||
- Condition: IF (Ca+ FULLNESS)
|
||||
- Consequence: (Ca+ decrease)
|
||||
- Consequence: (ATP decrease)
|
||||
- Tracce: None
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: RF
|
||||
```
|
||||
|
||||
*Svuotiamo a due velocita’. Il context ([Check Ca+ concentration](https://cl.splindex.net/apps/files/files/1160115?dir=/code-server/G-notes/neuron&editing=false&openfile=true#h-4-check-ca-concentration)) e’ determinato a epoca piu’ lunga, tanto ci vuole qualche giro per fare entrare i primi Ca+*
|
||||
|
||||
> Time: t = 1-50 ms after influx
|
||||
> Clearance mechanisms (in order of speed):
|
||||
> 1. Fast buffers (calbindin, parvalbumin): <1 ms
|
||||
> 2. Plasma membrane Ca²⁺ ATPase (PMCA): 10-100 ms
|
||||
> 3. Na⁺/Ca²⁺ exchanger (NCX): 10-100 ms
|
||||
> 4. Mitochondrial uptake: 10-1000 ms
|
||||
> 5. Endoplasmic reticulum uptake: 100-1000 ms
|
||||
> Residual Ca²⁺: 0.1-0.5 µM persists for 10-1000 ms
|
||||
|
||||
#### Observed 1 - STP - Upregulation of Pr
|
||||
|
||||
> **Timing**: > 10 ms
|
||||
>
|
||||
> - **Upregulation (Facilitation):** Residual Ca²⁺ from previous spikes increases P_r for next release
|
||||
|
||||
#### Observed 2 - STD - Downregulation of Pr
|
||||
|
||||
> **Timing**: > 10 ms
|
||||
>
|
||||
> - **Downregulation (Depression):** High-frequency firing depletes readily releasable vesicle pool, decreasing P_r
|
||||
|
||||
### Tens-ms to seconds Time Scale
|
||||
|
||||
#### Vescicles Recycling
|
||||
|
||||
> Time: t = 10 ms - 10 s (depending on activity)
|
||||
> Sequential steps:
|
||||
> 1. Endocytosis (clathrin-mediated, kiss-and-run, bulk)
|
||||
> 2. Vesicle re-acidification (v-ATPase)
|
||||
> 3. Neurotransmitter reloading (vesicular transporters)
|
||||
> 4. Priming (SNARE assembly, docking)
|
||||
> 5. Return to RRP
|
||||
> Recycling rate: Limited by ATP availability
|
||||
|
||||
#### Vescicle from RP to RRP
|
||||
|
||||
```
|
||||
Behavior: Vescicle from RP to RRP
|
||||
- ContainedBy: PRE
|
||||
- Blocks: RP, RRP, Ca+, ATP
|
||||
- InContext: CaEmpty
|
||||
- RF: 30
|
||||
- Condition: IF NOT (ATP EMPTY) AND NOT (RP EMPTY)
|
||||
- Consequence: (RP decrease) # moved VERY slow
|
||||
- Consequence: (RRP increase) # moved VERY slow
|
||||
- Consequence: (ATP decrease) # Very low ATP consumption
|
||||
- Tracce: ? # se non c’e’ abbastanza ATP o non ci sono abbastanza RP, lascio tracce per la modulazione UP, devo capire modulazione DOWN
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: RF
|
||||
- InContext: CaMedium
|
||||
- RF: 15
|
||||
- Condition: IF NOT (ATP EMPTY) AND NOT (RP EMPTY)
|
||||
- Consequence: (RP decrease) # moved slow
|
||||
- Consequence: (RRP increease) # moved slow
|
||||
- Consequence: (ATP decrease) # low ATP consumption
|
||||
- Tracce: ? # se non c’e’ abbastanza ATP o non ci sono abbastanza RP, lascio tracce per la modulazione UP, devo capire modulazione DOWN
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: RF
|
||||
- InContext: CaFull
|
||||
- # Superpriming requires ATP for phosphorylation reactions and for molecular motors that move vesicles. If the reserve pool is depleted or ATP is low, the superpriming "conveyor belt" has nothing to feed into the RRP. (Astrocyte)
|
||||
- RF: 5
|
||||
- Condition: IF NOT (ATP EMPTY) AND NOT (RP EMPTY)
|
||||
- Consequence: (RP decrease) # moved fast
|
||||
- Consequence: (RRP increease) # moved fast
|
||||
- Consequence: (ATP decrease) # fast ATP consumption
|
||||
- Tracce: ? # se non c’e’ abbastanza ATP o non ci sono abbastanza RP, lascio tracce per la modulazione UP, devo capire modulazione DOWN
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: RF
|
||||
```
|
||||
|
||||
*From The Reserve Pool and Recently Endocytosed Vesicles*
|
||||
|
||||
#### Check Ca+ Concentration
|
||||
|
||||
```
|
||||
Behavior: Check Ca+ Concentration
|
||||
- ContainedBy: PRE
|
||||
- Blocks: Ca+, Ca+MediumTraces, Ca+HighTraces
|
||||
- Context-fixed
|
||||
- RF: 60
|
||||
- Condition: IF (Ca+ EMPTY)
|
||||
- OutContext: CaEmpty
|
||||
- Consequence: None
|
||||
- Traces: None
|
||||
- Condition: IF (NOT Ca+ EMPTY) AND (NOT Ca+ FULLNESS)
|
||||
- OutContext: CaMedium
|
||||
- Consequence: None
|
||||
- Traces: (Ca+MediumTraces increase) # Add to traces Ca+Medium (Questo per la modulazione, quanti giri e’ rimasto in questa condizione)
|
||||
- Condition: IF (Ca+ FULLNESS)
|
||||
- OutContext: CaFull
|
||||
- Consequence: None
|
||||
- Traces: (Ca+HighTraces increase) # Add to traces Ca+Medium (Questo per la modulazione, quanti giri e’ rimasto in questa condizione)
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: (Ca+ FULLNESS)
|
||||
```
|
||||
|
||||
*Il controllo su Ca+ viene fatto anche nel contesto spike, ma li e’ con RF1. Qui lo facciamo sempre ma con RF50 o maggiore, per limitare check e comunque siamo in un timescale molto piu’ alta.*
|
||||
|
||||
*Non deve andare in overlap con Action Potential*
|
||||
|
||||
### Seconds-Minutes Time Scale
|
||||
|
||||
*Questi comportamenti si possono fare anche controllando che non ci sia alta concentrazione di Ca+ per essere sicuri che il neurone sia in un momento di calma. Quindi devo cambiare e mettere context fixed?*
|
||||
|
||||
#### Vesicles Filling RP ?
|
||||
|
||||
```
|
||||
Behavior: Vesicles Filling RP ?
|
||||
- ContainedBy: PRE
|
||||
- Blocks: Vescicle, ATP
|
||||
- InContext: Fixed
|
||||
- RF: 300
|
||||
-
|
||||
-
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None (credo vada con DEV di RP)
|
||||
```
|
||||
|
||||
*Qui riempiamo le vesciche. Fino ad un numero massimo, che viene modulato in DEV*
|
||||
|
||||
#### Lactate-ATP
|
||||
|
||||
```
|
||||
Behavior: Lactate-ATP
|
||||
- ContainedBy: PRE
|
||||
- Blocks: Lactate, ATP, Ca+
|
||||
- InContext: Fixed
|
||||
- RF: 300
|
||||
- Condition: ??? IF NOT (Ca+ FULLNESS) AND NOT EMPTY AND IF AstroLactate NOT EMPTY AND ATP NOT FULL
|
||||
- Consequence: get Lactate
|
||||
- Consequence: Increase ATP
|
||||
- Tracce:
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: RF
|
||||
```
|
||||
|
||||
*Il Lactate viene mandato da Astro che ha fatto re-uptake di Glutamate, trasformato in Glutamine e poi Lactate. Il Lactate serve a fare ATP. Astrocyte gliotransmitters (ATP, D-serine, glutamate).*
|
||||
|
||||
## Postsynaptic behavior
|
||||
|
||||
```
|
||||
Container: POST
|
||||
- ContainedBy: BD
|
||||
- Expands: 100 POST-CHAN
|
||||
- Modulability:
|
||||
- TUN: # POST Possible <-> Actual, Synapting
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
### Milliseconds Time Scale
|
||||
|
||||
#### AMPA Opening
|
||||
|
||||
- **Timing**: < 1 ms
|
||||
- **InContext:** Glutamate > **FULLNESS**
|
||||
- **OutContext:** AMPA receptor opening
|
||||
|
||||
#### Ca+ influx by AMPA
|
||||
|
||||
- **Timing**: < 1 ms
|
||||
- **InContext:** AMPA receptor opened
|
||||
- **Consequence:** Na⁺ influx
|
||||
- **Consequence:** addition to local depolarization (EPSP) from AMPA activation
|
||||
|
||||
#### Limited Ca+ influx by NMDA
|
||||
|
||||
- **Timing**: > 1 ms
|
||||
|
||||
|
||||
- **InContext:** local depolarization (EPSP) **NOT** **FULLNESS** (requires depolarization > -40mV)
|
||||
- **Consequence:** Glutamate binding to NMDA receptors (Mg²⁺-blocked initially)
|
||||
- **Consequence:** limited NMDA receptor opening → Ca²⁺ influx
|
||||
- **Consequence:** limited addition to local depolarization (EPSP) from NMDA activation
|
||||
|
||||
#### Depolarization by bAP
|
||||
|
||||
- **Timing**: > 1 ms
|
||||
- **InContext:** bAP backpropagating action potential
|
||||
- **Consequence:** addition to local depolarization (EPSP) from bAP
|
||||
|
||||
#### Mg²⁺ NMDA unblock
|
||||
|
||||
- **Timing**: > 1 ms
|
||||
|
||||
|
||||
- **InContext:** local depolarization (EPSP) > **FULLNESS** (requires depolarization > -40mV)
|
||||
- **OutContext:** NMDA Mg²⁺ unblock
|
||||
|
||||
#### Full Ca+ influx by NDMA
|
||||
|
||||
- **Timing**: < 1 ms
|
||||
- **InContext:** NMDA Mg²⁺ unblock
|
||||
- **Consequence:** Na⁺ influx
|
||||
- **Consequence:** addition to local depolarization (EPSP) from Full NMDA activation
|
||||
|
||||
#### Observed 1 - Upregulation
|
||||
|
||||
- **Upregulation:** Depolarization relieves NMDA Mg²⁺ block → Ca²⁺ influx amplification
|
||||
|
||||
#### Observed 2 - Downregulation
|
||||
|
||||
- **Downregulation:** AMPA desensitization acts as low-pass filter
|
||||
|
||||
## Dendritic behavior
|
||||
|
||||
```
|
||||
Container: BD
|
||||
- ContainedBy: N-SPK
|
||||
- Expands: 100 POST
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
## Somatic behavior
|
||||
|
||||
```
|
||||
Container: SO
|
||||
- ContainedBy: N-SPK
|
||||
- Expands: 20 SO-CHAN
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
## AIS behavior
|
||||
|
||||
```
|
||||
Container: AXO
|
||||
- ContainedBy: N-SPK
|
||||
- Expands: 30 PRE
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
# Tuning - MTP-MTD Behavior
|
||||
|
||||
```
|
||||
Container: N-TUN
|
||||
- Expands: None
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
*Qui si modulano i canali ionici, sia quelli voltage (PRE/POST/SO/altro?) che quelli Neuro (POST/SO(inibitori)). Non si creano o si distruggono (lo si fa in Developing), ma si rendono attivi disattivi quelli presenti. Ovviamente potremmo aggiungere anche altri comportamenti di tuning che riguardano altri tipi di modulazione (RF?).*
|
||||
|
||||
## Presynaptic Behavior Tuning
|
||||
|
||||
### Seconds Time Scale
|
||||
|
||||
#### VCGG Channel Tuning
|
||||
|
||||
```
|
||||
- ContainedBy: N-TUN
|
||||
- Tubs:
|
||||
- Source:
|
||||
-
|
||||
- Yellow:
|
||||
-
|
||||
- Context: ?
|
||||
- RF: 1
|
||||
- IF NOT
|
||||
- Consequence: ()
|
||||
- Consequence: ()
|
||||
- Traces: #
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
*Lo possiamo fare sia con alterazione di RF che del volume Tub, di sicuro per Ca+ poi altro non so.*
|
||||
|
||||
*Inoltre devo vedere se farlo alla fine di spiketrain, quando il neurone e’ in rest stateM*
|
||||
|
||||
*This is critical for **long-term** presynaptic changes. The postsynaptic cell, upon detecting specific activity patterns (like those for LTP/LTD), releases chemical signals that travel backwards to the presynaptic terminal, instructing it to change.*
|
||||
|
||||
- ***For Presynaptic Strengthening (e.g., LTP):***
|
||||
- ***Nitric Oxide (NO):**** A gas that diffuses freely. During postsynaptic LTP induction (strong NMDAR activation), neuronal NO synthase (nNOS) is activated. NO diffuses into the presynaptic terminal and activates soluble guanylyl cyclase (sGC), raising cGMP levels. This enhances vesicle release via PKG, contributing to **presynaptic LTP**.*
|
||||
- ***Endocannabinoid-Mediated LTP (eLTP):**** In some synapses, a **postsynaptic** depolarization triggers production of endocannabinoids (e.g., 2-AG). These bind to presynaptic **CB1 receptors**, but surprisingly, can initiate a signaling cascade (involving cAMP/PKA) that **increases Pr** for a long period.*
|
||||
- ***Neurotrophins (BDNF):**** Released from the postsynapse in an activity-dependent manner. Presynaptic TrkB receptors activate pathways (PI3K, MAPK) that enhance vesicle docking and Pr.*
|
||||
- ***For Presynaptic Weakening (e.g., LTD):***
|
||||
- ***Classical Endocannabinoid-Mediated LTD (eCB-LTD):**** More common. Moderate postsynaptic activity (mGluR activation or moderate Ca²⁺ rise) triggers 2-AG release. 2-AG binds presynaptic CB1 receptors, which **inhibit VGCCs** and **directly inhibit the release machinery** via Gi/o protein signaling, reducing Pr for a long time.*
|
||||
- ***Other Lipid Mediators**** (like LPA) can also act as retrograde signals for depression.*
|
||||
|
||||
##### Augmentation:
|
||||
|
||||
- Calcium-sensing proteins (Munc13) alter release probability (1-10s range). How?
|
||||
|
||||
##### Upregulation:
|
||||
|
||||
- NO/BDNF activates cascades that increase P_r, promote synaptic growth (facilitates LTP). How?
|
||||
- VGCC TUN
|
||||
- Potassium channel modulation ??
|
||||
|
||||
##### Downregulation:
|
||||
|
||||
- eCBs bind CB1 receptors, inhibit VGCCs, activate K⁺ channels → profound decrease in P_r (DSE/DSI - depolarization-induced suppression)
|
||||
- CB1 receptor activation (by eCBs)
|
||||
|
||||
|
||||
- Retrograde BDNF (brain-derived neurotrophic factor)
|
||||
|
||||
## Postynaptic behavior Tuning
|
||||
|
||||
### Seconds Time Scale
|
||||
|
||||
#### Postsynapsis channel tuning
|
||||
|
||||
```
|
||||
- ContainedBy: N-TUN
|
||||
- Tubs:
|
||||
- Source:
|
||||
-
|
||||
- Yellow:
|
||||
-
|
||||
- Context: ?
|
||||
- RF: 1
|
||||
- IF NOT
|
||||
- Consequence: ()
|
||||
- Consequence: ()
|
||||
- Traces: #
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
## Dendritic-branch behavior Tuning
|
||||
|
||||
## Soma behavior Tuning
|
||||
|
||||
### Seconds Time Scale
|
||||
|
||||
#### SO Channel tuning
|
||||
|
||||
```
|
||||
- ContainedBy: N-TUN
|
||||
- Tubs:
|
||||
- Source:
|
||||
-
|
||||
- Yellow:
|
||||
-
|
||||
- Context: ?
|
||||
- RF: 1
|
||||
- IF NOT
|
||||
- Consequence: ()
|
||||
- Consequence: ()
|
||||
- Traces: #
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
####
|
||||
|
||||
## AIS behavior Tuning
|
||||
|
||||
# Development - LTP-LTD Behavior
|
||||
|
||||
```
|
||||
Container: N-DEV
|
||||
- Expands: None
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
*Attivazione/disattivazione di possibilita’*
|
||||
|
||||
*Qui si incrementa/decrementa:*
|
||||
|
||||
- *Il numero possibile di canali ionici.*
|
||||
- *la capacita’ di Vescice in RP e RPP*
|
||||
- *la capacita’ di spostare vesciche da RP a RPP*
|
||||
- *la capacita’ di riempire vesciche*
|
||||
|
||||
## Presynaptic behavior Development
|
||||
|
||||
### Day Time Scale
|
||||
|
||||
*Qui si modula la possibilita’ di potenza di fuoco, sia come nuovi recettori (voltage e neuro) sia come grandezza di RP, RRP e velocita’ di spostamento.*
|
||||
|
||||
*Long-lasting presynaptic strengthening requires **new proteins**:*
|
||||
|
||||
- *More vesicles*
|
||||
- *More active zone proteins (e.g., RIM, Munc13)*
|
||||
- *More mitochondria (for energy)*
|
||||
- *More synaptic vesicle components (synaptobrevin, synaptotagmin)*
|
||||
- *More cytoskeletal elements for structure*
|
||||
|
||||
*The neuron must **detect a sustained need for strengthening at a specific synapse**, send a signal to its nucleus, transcribe genes, and then deliver the new proteins back to that specific presynaptic bouton.*
|
||||
|
||||
1. ***Detection:**** Sustained high-frequency firing at the presynaptic terminal → elevated Ca²⁺ and/or neuromodulator release (dopamine, norepinephrine).*
|
||||
2. ***Signal to Nucleus:**** Activation of kinases (PKA, CaMKIV) and retrograde importin signaling → **CREB phosphorylation** in the nucleus.*
|
||||
3. ***Transcriptional Program:**** CREB induces expression of:*
|
||||
- ***Immediate Early Genes**** (e.g., c-Fos, Arc) that regulate further transcription.*
|
||||
- ***Effector Genes:**** Presynaptic proteins (synapsins, RIM, Munc13), BDNF, cytoskeletal proteins.*
|
||||
4. ***Delivery:**** Newly synthesized mRNAs/proteins are actively transported down the axon, **targeted to the active synapses** that initiated the signal.*
|
||||
5. ***Local Implementation:***
|
||||
- *Assembly of new active zones.*
|
||||
- *Expansion of vesicle pools.*
|
||||
- *Possible local translation.*
|
||||
- *Bouton enlargement or new bouton formation.*
|
||||
6. ***Stabilization:**** Epigenetic modifications and continued autocrine/paracrine signaling (BDNF→TrkB) lock in the changes.*
|
||||
|
||||
***In essence, the neuron "knows" to strengthen a presynapse long-term because the synapse's own sustained activity creates a biochemical signature that reaches the nucleus, triggering a gene program specifically designed to build a bigger, better release machine. This is a fundamental mechanism underlying long-term memory storage at the synaptic level.***
|
||||
|
||||
- ATP-dependent vesicle cycling
|
||||
- **Metabolic veto:** Insufficient ATP prevents vesicle release despite adequate Ca²⁺
|
||||
|
||||
|
||||
- Glutamine→glutamate conversion (via glutaminase). Glutamine from astrocytes (glutamate-glutamine cycle)
|
||||
|
||||
|
||||
- Vesicle refilling with glutamate
|
||||
|
||||
|
||||
- Maintenance of ion gradients
|
||||
|
||||
**Incoming Signals:**
|
||||
|
||||
- Astrocyte-supplied lactate (via monocarboxylate transporters)
|
||||
- Metabolic state indicators (ATP levels, NAD/NADH ratio)
|
||||
|
||||
**Outgoing Signals:**
|
||||
|
||||
- Metabolic demand signals to astrocyte ??
|
||||
|
||||
**Modulation:**
|
||||
|
||||
- Lactate availability determines sustained release capacity during high activity ??
|
||||
|
||||
#### VCGG channel development
|
||||
|
||||
```
|
||||
- ContainedBy: N-DEV
|
||||
- Tubs:
|
||||
- Source:
|
||||
-
|
||||
- Yellow:
|
||||
-
|
||||
- Context: ?
|
||||
- RF: 1
|
||||
- IF NOT
|
||||
- Consequence: ()
|
||||
- Consequence: ()
|
||||
- Traces: #
|
||||
- Modulability:
|
||||
- TUN: None
|
||||
- DEV: None
|
||||
```
|
||||
|
||||
#### RRP development
|
||||
|
||||
#### Ca+ FULLNESS
|
||||
|
||||
#### Ca+ Clearance RF
|
||||
|
||||
#### RP to RPP RF
|
||||
|
||||
#### Lactate to ATP RF
|
||||
|
||||
## Postynaptic Behavior Development
|
||||
|
||||
## Dentric-branch Behavior Development
|
||||
|
||||
## Soma Behavior Development
|
||||
|
||||
## AIS Behavior Development
|
||||
@@ -0,0 +1,75 @@
|
||||
Excellent question that gets to the core of how synaptic transmission works. Yes, it's fundamentally based on **concentration**, but with a critical biological twist: the concept of **saturation**.
|
||||
|
||||
Let's walk through the logic:
|
||||
|
||||
---
|
||||
|
||||
### **1. The Concentration Argument (Simplified View)**
|
||||
|
||||
You are correct. Neurotransmitter molecules (e.g., glutamate) diffuse across the synaptic cleft and bind to receptors (e.g., AMPA receptors) on the postsynaptic density (PSD).
|
||||
|
||||
* **5000 molecules** create a certain concentration in the cleft.
|
||||
* **Fewer molecules** (e.g., 2500 from a depleted second spike) create a **lower concentration**.
|
||||
* According to the law of mass action, a lower concentration of ligand (neurotransmitter) results in **fewer receptors being bound at any given moment**.
|
||||
* Fewer bound receptors mean **fewer open ion channels**, leading to a **smaller net ionic current** (EPSC), and thus a **smaller EPSP**.
|
||||
|
||||
So, at first glance, it seems purely a concentration-driven, dose-response relationship: **more transmitter → more receptor binding → bigger response.**
|
||||
|
||||
---
|
||||
|
||||
### **2. The Critical Biological Reality: Receptor Saturation**
|
||||
|
||||
Here's where it gets interesting. For a typical fast excitatory synapse, the **cleft is extremely narrow** (~20-40 nm), and the **postsynaptic density is packed with receptors** (thousands of AMPA receptors per PSD).
|
||||
|
||||
**During a single vesicle release event, the local neurotransmitter concentration in the cleft skyrockets to a very high level (mM range) for about 1 ms before diffusion and uptake clear it.**
|
||||
|
||||
This leads to a key phenomenon: **The receptors under the release site are often temporarily saturated.**
|
||||
|
||||
* **What is Saturation?** It means that at the peak of the release event, **virtually all available receptors are bound by neurotransmitter**. Adding more neurotransmitter molecules (e.g., from a second, simultaneous release at the same site) **cannot open more channels** because they're already all in use.
|
||||
* **Implication:** Under saturated conditions, the size of the postsynaptic response is **not linearly proportional to the number of transmitter molecules**. Instead, it's determined by the **number of postsynaptic receptors**, not the amount of transmitter beyond what's needed to saturate them.
|
||||
|
||||
---
|
||||
|
||||
### **3. So Why Does Reducing Vesicle Release Reduce the EPSP?**
|
||||
|
||||
Given receptor saturation, why does releasing fewer vesicles (during short-term depression) still cause a smaller EPSP? There are two main reasons:
|
||||
|
||||
**A. Saturation is Local and Incomplete**
|
||||
While receptors directly under a vesicle fusion site may be saturated, **neurotransmitter diffuses**. A single release event activates receptors in the **immediate vicinity**. If a second vesicle is released from a **different release site** within the same active zone (or if the first release is from a site with fewer local receptors), its glutamate diffuses to activate a **spatially distinct, non-saturated population of receptors**. Therefore:
|
||||
|
||||
* **First Spike:** Vesicle from Site A saturates Receptor Cluster A. Vesicle from Site B saturates Receptor Cluster B. **Total Response = A + B.**
|
||||
* **Second Spike (Depressed):** Only Vesicle from Site A releases. It saturates Receptor Cluster A. **Total Response = A only.** The EPSP is smaller because it's missing the contribution from the **spatially separate receptor cluster B**.
|
||||
|
||||
**B. The Role of Multi-Vesicular Release (MVR) and Transmitter Spillover**
|
||||
At many synapses, a single action potential can cause the fusion of **more than one vesicle** (Multi-Vesicular Release). The glutamate from these multiple vesicles can **summate in the cleft**, increasing the concentration duration and potentially activating **extra- or peri-synaptic receptors** (like NMDA receptors or metabotropic receptors) that have lower affinity or are located farther away.
|
||||
|
||||
* **First Spike:** High Pr → MVR (e.g., 3 vesicles) → Very high, prolonged [Glutamate] → Activates **local AMPARs + distal/extrasynaptic NMDARs/mGluRs**.
|
||||
* **Second Spike (Low Pr):** Low Pr → Single vesicle release → Lower, shorter [Glutamate] → Activates **only local AMPARs** (and maybe saturates them). The loss of this **spillover component** to more distant receptors contributes to the amplitude decrease.
|
||||
|
||||
---
|
||||
|
||||
### **The Integrated Picture: It's About the "Volume" of Activated Receptors**
|
||||
|
||||
Think of it not as "5000 vs. 2500 molecules," but as **"activating 200 receptors vs. activating 100 receptors."**
|
||||
|
||||
1. **Number of Release Sites & Vesicles:** Determines the **spatial pattern and concentration profile** of neurotransmitter in the cleft.
|
||||
2. **Diffusion & Uptake:** Determine how far that neurotransmitter spreads and how long it lasts.
|
||||
3. **Receptor Distribution & Affinity:** Determine how many receptors are recruited by that spatial/chemical profile.
|
||||
|
||||
**During short-term depression:**
|
||||
|
||||
* **Fewer vesicles are released** → The "cloud" of neurotransmitter is **smaller and/or originates from fewer points**.
|
||||
* This smaller cloud **activates a smaller total volume of the postsynaptic membrane** (or activates the same volume but with a lower, non-saturating concentration).
|
||||
* **Result:** **Fewer receptor channels open overall**, producing a smaller summed postsynaptic current and a smaller EPSP.
|
||||
|
||||
---
|
||||
|
||||
### **Summary: Why Less Neurotransmitter = Smaller EPSP**
|
||||
|
||||
| Cause of Reduced Release | Effect on Neurotransmitter Profile | Effect on Postsynaptic Receptors | Final Effect on EPSP |
|
||||
|:------------------------------------------------------------|:-------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|
|
||||
| **Vesicle Depletion** (fewer vesicles released) | Lower peak concentration, less spatial spread. | **Fewer total receptors are activated** (spatially restricted). A smaller area of the PSD is engaged. | **Amplitude decreases.** |
|
||||
| **Lower Release Probability** (e.g., from G-protein inhibition) | Same as above. | Same as above. | **Amplitude decreases.** |
|
||||
| **Receptor Saturation** (for a single vesicle) | Limits the effect of adding more transmitter *at the exact same location*. | Makes the synapse's response to a *single release site* **binary** (on/off). | Makes the synapse's output depend on **the number of independent release sites activated**, not the raw molecule count. |
|
||||
|
||||
**So, you are right—it is based on concentration.** But because of the tiny, structured environment of the synapse, the critical concentration is the **local concentration at each receptor cluster**, which dictates **how many *clusters* are activated**, not just how many molecules are floating around. Reducing the number of released vesicles reduces the **spatial extent and intensity** of the neurotransmitter signal, thereby recruiting fewer postsynaptic receptors and generating a smaller EPSP.
|
||||
@@ -0,0 +1,70 @@
|
||||
This is a profound and sophisticated question that gets to the heart of **computation within neural circuits**. You are absolutely correct: the distinction between what we might call a "starter" synapse (driving an action potential) and an "integrator" synapse (modulating the likelihood of one) is crucial, and the modulation mechanisms are **fundamentally different** at the biophysical and functional levels.
|
||||
|
||||
This maps directly onto the concepts of **detonator synapses vs. modulator synapses**, or more formally, **driver vs. modulatory inputs**.
|
||||
|
||||
Let's break down the key differences in their modulation.
|
||||
|
||||
---
|
||||
|
||||
### 1. The Functional Distinction
|
||||
|
||||
* **Starter / Driver / Detonator Synapse:**
|
||||
* **Role:** Directly and reliably triggers an **action potential (AP)** in the postsynaptic neuron.
|
||||
* **Location:** Typically on or near the **soma** or the **axon initial segment (AIS)**. This is where the neuron's decision to fire is made.
|
||||
* **Mechanism:** Uses **ionotropic receptors** (AMPA, NMDA) to cause a large, fast, **depolarizing excitatory postsynaptic potential (EPSP)**. These EPSPs summate directly to cross the voltage threshold for the AP.
|
||||
* **Analogy:** The **gas pedal** – pressing it hard makes the car (neuron) go.
|
||||
* **Integrator / Modulator Synapse:**
|
||||
* **Role:** Modulates the **probability** that the postsynaptic neuron will fire an AP in response to *other inputs*. It sets the "gain" or "mood" of the neuron.
|
||||
* **Location:** Often on **dendrites**, sometimes specifically on distal dendrites.
|
||||
* **Mechanism:** Often uses **metabotropic receptors** (mGluRs, GABAʙ, neuromodulator receptors like dopamine D1/D2). Their effects are slower, longer-lasting, and involve **G-protein-coupled cascades** that alter:
|
||||
* **Membrane potential** (e.g., subtle depolarization or hyperpolarization).
|
||||
* **Input resistance** (affecting how much a given EPSP "counts").
|
||||
* **Intrinsic excitability** (e.g., by modulating potassium channels).
|
||||
* **The strength of *other* synapses** (via heterosynaptic plasticity).
|
||||
* **Analogy:** The **engine tune-up** or the **road conditions** – they don't make the car go by themselves, but they dramatically affect how responsive it is to the gas pedal.
|
||||
|
||||
---
|
||||
|
||||
### 2. How Modulation Differs: Core Mechanisms
|
||||
|
||||
The differences arise from their **location, receptor types, and the spatiotemporal scale of their signals.**
|
||||
|
||||
| Feature | **Starter / Driver Synapse** | **Integrator / Modulator Synapse** |
|
||||
|:------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| **Primary Goal of Modulation** | **Change the *efficacy* of its own direct signal.** To make each presynaptic spike more or less likely to contribute to triggering an AP. | **Change the *integration properties* of the entire dendritic compartment or neuron.** To alter how the neuron responds to *all* inputs. |
|
||||
| **Key Modulatory Target** | **The synapse itself (homosynaptic plasticity).**<br />1. **Postsynaptic:** AMPAR number/conductance (LTP/LTD).<br />2. **Presynaptic:** Release probability (Pr) via retrograde signals (NO, eCBs, BDNF). | **The neuronal *milieu* (heterosynaptic & intrinsic plasticity).**<br />1. **Dendritic excitability:** Modulating voltage-gated ion channels (e.g., HCN, K⁺).<br />2. **Global Ca²⁺ signaling:** Altering backpropagating AP efficacy or dendritic spike thresholds.<br />3. **Other synapses:** Inducing heterosynaptic LTP/LTD. |
|
||||
| **Retrograde Signal Specificity** | **High spatial specificity.** Signals like NO have a very short diffusion range, ensuring feedback is primarily to the **active presynaptic terminal itself**. This is **synapse-specific learning**. | **Lower spatial specificity.** Signals like **endocannabinoids (eCBs)** or **neurotrophins (BDNF)** can diffuse further, affecting **multiple nearby presynaptic terminals** (volume transmission). This allows one integrator synapse to **orchestrate plasticity** in a local dendritic region. |
|
||||
| **Temporal Domain** | **Milliseconds to seconds** for induction (phasic). Must be tightly coupled to the presynaptic spike (spike-timing-dependent plasticity, STDP). | **Seconds to hours** (tonic). Can be sustained by ongoing neuromodulator release (dopamine, acetylcholine) reflecting behavioral states (attention, arousal, reward). |
|
||||
| **Example** | A thalamic input to a layer 4 cortical neuron. Its strength is modified via **NMDAR-dependent LTP/LTD**. | A cholinergic input from the basal forebrain to a cortical pyramidal cell. It doesn't cause firing but **suppresses adaptation currents**, enabling sustained firing to driver inputs. |
|
||||
|
||||
---
|
||||
|
||||
### 3. The Critical Interplay: How an Integrator Synapse Modulates a Starter Synapse
|
||||
|
||||
This is where the magic of neural computation happens. An integrator synapse can powerfully control a starter synapse **without directly triggering an AP itself.**
|
||||
|
||||
**Mechanisms of Cross-Modulation:**
|
||||
|
||||
1. **Shunting Inhibition:** A nearby GABAergic (integrator) synapse can open Cl⁻ channels. This **lowers the input resistance** of the dendrite, causing the EPSP from the starter synapse to be smaller and faster ("shunted"), making it less likely to reach threshold.
|
||||
2. **Modulation of Dendritic Voltage-Gated Channels:**
|
||||
* **Example:** Dopamine (via D1 receptors) can **reduce the activity of HCN channels** (which carry the hyperpolarization-activated current, Iₕ). Iₕ normally dampens distal EPSPs as they travel to the soma. By reducing Iₕ, the dopamine input **boosts the strength of distal driver EPSPs**, effectively bringing them "closer" to the soma in electrical terms.
|
||||
3. **Priming for Plasticity (Metaplasticity):**
|
||||
* A modulatory signal (e.g., noradrenaline during stress/arousal) can **prime the molecular machinery** of a starter synapse. It might raise intracellular Ca²⁺ levels or activate kinases (PKA) to lower the threshold for inducing LTP when the strong driver input arrives moments later. This is "**gating**" of plasticity.
|
||||
4. **Heterosynaptic Plasticity via Volume Transmission:**
|
||||
* When a strong driver synapse induces LTP, it often releases **retrograde signals (eCBs, BDNF)** that spill over. These can induce **LTD at nearby, less-active integrator synapses**. This is a form of **competitive plasticity**, ensuring the driver synapse "wins" and becomes the dominant input, while silent integrators are weakened.
|
||||
|
||||
---
|
||||
|
||||
### 4. Summary: A Hierarchical Control System
|
||||
|
||||
Think of it as a **two-layer control system**:
|
||||
|
||||
* **Layer 1 (Starter Synapses):** The **content**-carrying signals. *"What"* is being represented. Their plasticity is about **refining specific connections** (Hebbian learning: "cells that fire together, wire together").
|
||||
* **Layer 2 (Integrator Synapses):** The **context**-setting signals. *"How importantly* should the neuron treat the incoming content?" Their plasticity is about **setting global parameters**—gain, plasticity thresholds, metabolic state—based on neuromodulators (dopamine for reward, acetylcholine for attention, serotonin for mood).
|
||||
|
||||
**Conclusion:** The modulation mechanisms are **not the same**. They are specialized for entirely different computational tasks:
|
||||
|
||||
* **Starter synapse modulation** is **synapse-specific, fast, and Hebbian**. It's about **efficacy**.
|
||||
* **Integrator synapse modulation** is **diffuse, slow, and state-dependent**. It's about **context and control**.
|
||||
|
||||
The breathtaking complexity of the brain arises from the dense interweaving of these two layers, allowing a neuron to be both a **specific feature detector** (shaped by its driver inputs) and an **adaptive processor** whose very interpretation rules are dynamically tuned by its modulatory inputs. Your insight perfectly identifies this fundamental architectural principle.
|
||||
@@ -0,0 +1,684 @@
|
||||
# VARIABLES
|
||||
|
||||
## **MILLISECOND SCALE (Action Potential → Release)**
|
||||
|
||||
| Variable | Direct Behavior/Effect | Modulated By (Same Scale) | Modulated By (Other Scales) |
|
||||
|-------------------|------------------------------------------------------------------------------|-------------------------------------------------------------|-----------------------------------------------------------------------------------------------------|
|
||||
| **V_mem** | • AP depolarization<br />• K⁺-mediated repolarization | • **KChannels** activation<br />• Na⁺ channel inactivation | • **ATP** (seconds) - powers Na⁺/K⁺ pump<br />• **K+** accumulation (tens-ms) |
|
||||
| **VGCC** | • Ca²⁺ influx triggered by depolarization<br />• Ca²⁺-dependent inactivation | • **V_mem** (depolarization)<br />• **Ca+** microdomain (feedback) | • **VGCC invagination** (hours) - reduces surface expression<br />• **BDNF** (hours) - increases expression |
|
||||
| **Ca+** (microdomain) | • Rapid spike near VGCCs (~10-100 μM)<br />• Triggers vesicle fusion | • **VGCC** opening kinetics<br />• Endogenous buffers | • **CaChannels** density (hours)<br />• **NO** (seconds) - modulates channel opening |
|
||||
| **Vesicles** (fusion) | • SNARE-mediated fusion with membrane<br />• Release probability (Pr) varies | • **Ca+** concentration⁴<br />• **RRP** position/docking | • **ATP** (seconds) - fuels priming<br />• **eCB** (seconds) - inhibits release |
|
||||
| **K+** (efflux) | • Repolarization via KChannels<br />• Clears AP | • **V_mem** (depolarization)<br />• **Ca+** (activates SK channels) | • **KChannels** modulation (minutes) |
|
||||
| **KChannels** | • Voltage-gated opening<br />• Ca²⁺-activated (SK) | • **V_mem**<br />• **Ca+** microdomain | • **Phosphorylation** (minutes)<br />• **BDNF** (hours) - modulates expression |
|
||||
|
||||
## **TENS-HUNDREDS OF MILLISECONDS SCALE (Short-term Dynamics)**
|
||||
|
||||
| Variable | Direct Behavior/Effect | Modulated By (Same Scale) | Modulated By (Other Scales) |
|
||||
|-------------------------|--------------------------------------------------------------------------------------|---------------------------------------------------------------|------------------------------------------------------------------------------------------------------|
|
||||
| **Ca+** (global) | • Bulk terminal increase (~0.5-2 μM)<br />• Activates mobilization | • Diffusion from microdomains<br />• PMCA/NCX pumps | • **ATP** (seconds) - fuels pumps<br />• **Lactate** (seconds) - supports mitochondrial uptake |
|
||||
| **Vesicles** (mobilization) | • Movement from **RP** → **RRP**<br />• Docked vesicles become release-ready | • **Ca+** global concentration<br />• **RRP** depletion state | • **Mobilization rate** (hours) - structural adaptation<br />• **ATP** (seconds) - fuels transport |
|
||||
| **RRP** | • Immediate release pool (~5-15 vesicles)<br />• Depletes with high-frequency firing | • **Vesicles** release (ms)<br />• **Vesicles** mobilization into RRP | • **RP** size (minutes)<br />• **BDNF** (hours) - increases docking sites |
|
||||
| **K+** (cleft accumulation) | • Extracellular K⁺ rises to ~8-12 mM<br />• Affects resting potential | • **KChannels** activity (ms)<br />• Astrocyte/glia uptake | • **Activity history** (minutes) - astrocyte adaptation |
|
||||
| **eCB** | • Retrograde diffusion to presynapse<br />• Binds CB1 receptors (~100-500 ms) | • Postsynaptic Ca²⁺ rise (ms)<br />• mGluR activation | • **Activity patterns** (minutes) - regulates production<br />• **NO** (seconds) - can enhance eCB synthesis |
|
||||
|
||||
## **SECONDS-MINUTES SCALE (Metabolic & Signaling)**
|
||||
|
||||
| Variable | Direct Behavior/Effect | Modulated By (Same Scale) | Modulated By (Other Scales) |
|
||||
|------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------|-------------------------------------------------------------------------------------------|
|
||||
| **ATP** | • Fuels: pumps, vesicle cycling, protein phosphorylation<br />• Depletes with high activity | • **Lactate** conversion<br />• Mitochondrial respiration | • **Activity demand** (ms scale)<br />• **BDNF** (hours) - enhances mitochondrial function |
|
||||
| **Lactate** | • Astrocyte→neuron shuttle<br />• Converted to pyruvate for ATP | • Glutamate uptake by astrocytes<br />• Glycogen breakdown | • **Activity level** (ms-min)<br />• **NO** (seconds) - regulates blood flow |
|
||||
| **NO** | • Retrograde diffusion from postsynapse<br />• Activates presynaptic cGMP pathways | • Postsynaptic NOS activation by Ca²⁺<br />• NMDA receptor activity | • **Activity patterns** (minutes)<br />• **BDNF** (hours) - regulates NOS expression |
|
||||
| **RP** | • Reserve vesicle pool (~100-500 vesicles)<br />• Slowly replenishes RRP | • **Vesicles** recycling<br />• **Vesicles** mobilization out of RP | • **RP capacity** (hours) - structural changes<br />• **ATP** (seconds) - fuels vesicle refilling |
|
||||
| **BDNF** | • Retrograde transport (slow)<br />• Activates TrkB receptors | • Activity-dependent release from postsynapse<br />• Local translation | • **Ca+** integration (minutes)<br />• **eCB** (minutes) - can modulate release |
|
||||
| **eCB** (persistent) | • Long-term depression (LTD) induction<br />• Alters release probability | • Sustained postsynaptic activity<br />• DAG lipase activation | • **NO** (seconds) - synergistic effects<br />• **BDNF** (hours) - can counteract eCB-LTD |
|
||||
|
||||
## **SECONDS-HOURS-DAYS SCALE (Structural Modulation)**
|
||||
|
||||
| Variable | Modulatory Behavior | Influenced By | Effects on Faster Scales |
|
||||
|------------------------------|------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------|
|
||||
| **VGCC** (invagination) | • Internalization of channels<br />• Reduces release probability | • **Ca+** integral (minutes of activity)<br />• **BDNF** (trophic support)<br />• **eCB** (chronic signaling) | • ↓ **Ca+** influx (ms)<br />• ↓ **Vesicles** release probability (ms) |
|
||||
| **CaChannels** (density) | • Changes in VGCC number at active zone | • **BDNF**-TrkB signaling (hours)<br />• Homeostatic scaling (days)<br />• Activity history (integrated **Ca+**) | • Alters **Ca+** microdomain (ms)<br />• Changes short-term plasticity (tens-ms) |
|
||||
| **RP** (pool size) | • Structural changes in vesicle reserves | • **BDNF** (enhances)<br />• Chronic **eCB** (reduces)<br />• Metabolic capacity (**ATP/Lactate** supply) | • Changes **RRP** refilling rate (tens-ms)<br />• Alters sustained release (seconds) |
|
||||
| **Vesicles** (mobilization rate) | • Faster/slower RP→RRP trafficking | • **BDNF**-cytoskeletal remodeling<br />• Synapsin phosphorylation state (**Ca+** history) | • Alters short-term facilitation/depression (tens-ms) |
|
||||
| **KChannels** (expression) | • Changes in Kv channel density | • Activity-dependent gene regulation<br />• **BDNF** modulation<br />• **K+** homeostasis needs | • Alters AP waveform and duration (ms)<br />• Changes firing frequency adaptation |
|
||||
|
||||
## **CROSS-VARIABLE FEEDBACK LOOPS**
|
||||
|
||||
### **Fast Release → Metabolic Support Loop**
|
||||
|
||||
```
|
||||
V_mem (AP) → VGCC opening → Ca+ influx → Vesicles release
|
||||
↓
|
||||
Glutamate release → Astrocyte activation → Lactate production
|
||||
↓
|
||||
Lactate → ATP synthesis → Fuels: VGCC recycling, Vesicles priming, Ca+ pumps
|
||||
```
|
||||
|
||||
### **Activity → Structural Adaptation Loop**
|
||||
|
||||
```
|
||||
High activity → Ca+ accumulation → BDNF release (post→pre)
|
||||
↓
|
||||
BDNF → ↑ VGCC expression, ↑ RP size, ↑ mobilization rate
|
||||
↓
|
||||
Enhanced release capacity → Changes Ca+ dynamics → Homeostatic adjustment
|
||||
```
|
||||
|
||||
### **Retrograde Modulation Network**
|
||||
|
||||
```
|
||||
Postsynaptic: Ca+ → NO production → Presynaptic: cGMP → Modulates VGCC
|
||||
↓ ↓
|
||||
Postsynaptic: Ca+ → eCB production → Presynaptic: CB1 → Inhibits VGCC, ↓ release
|
||||
↓
|
||||
Postsynaptic: Ca+ → BDNF synthesis → Presynaptic: TrkB → ↑ VGCC, ↑ RP
|
||||
```
|
||||
|
||||
### **Energy-Redistribution Loop**
|
||||
|
||||
```
|
||||
High activity → ATP depletion → Activates AMPK → ↑ Lactate uptake
|
||||
↓ ↓
|
||||
Reduced release probability ↑ Mitochondrial biogenesis (days)
|
||||
↓ ↓
|
||||
Lower Ca+ demand Enhanced ATP production
|
||||
```
|
||||
|
||||
## **KEY VARIABLE INTERDEPENDENCIES**
|
||||
|
||||
1. **VGCC** ↔ **Ca+** (bidirectional):
|
||||
- VGCC opening → Ca+ influx
|
||||
- Ca+ accumulation → VGCC modulation (inactivation/adaptation)
|
||||
2. **ATP** as universal modulator:
|
||||
- Required for: V_mem maintenance, Ca+ clearance, Vesicles cycling, RP refilling
|
||||
- Limited ATP → affects all faster processes
|
||||
3. **BDNF** as structural organizer:
|
||||
- Coordinates: VGCC expression, RP size, KChannels density, metabolic capacity
|
||||
4. **Ca+** as integration signal:
|
||||
- Fast: triggers Vesicles release (ms)
|
||||
- Medium: regulates Vesicles mobilization (tens-ms)
|
||||
- Slow: drives structural changes via BDNF/NO (minutes-hours)
|
||||
5. **K+**/**KChannels** as activity brakes:
|
||||
- Regulate AP duration and frequency
|
||||
- Homeostatically adjusted based on activity history
|
||||
|
||||
This framework shows how your specified variables interact across timescales, with each variable playing multiple roles depending on the temporal context.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **ATP: The Multiscale Energy Integrator**
|
||||
|
||||
## **ATP's Roles Across Temporal Scales**
|
||||
|
||||
### **1. MILLISECOND SCALE (Emergency Power)**
|
||||
|
||||
**Direct Behaviors Enabled:**
|
||||
|
||||
- **VGCC recovery**: Rapid phosphorylation/dephosphorylation cycles
|
||||
- **SNARE priming**: ATP hydrolysis by NSF for vesicle fusion competence
|
||||
- **Na⁺/K⁺ pump**: Immediate AP recovery (3 Na⁺ out, 2 K⁺ in per ATP)
|
||||
|
||||
**Influences on Other Variables:**
|
||||
|
||||
- ↓ **ATP** → Slower **V_mem** repolarization (K⁺ pump impaired)
|
||||
- ↓ **ATP** → Reduced **VGCC** recovery from inactivation
|
||||
- ↓ **ATP** → Impaired **Vesicles** priming → ↓ release probability
|
||||
|
||||
**Critical Threshold:** <0.1s depletion → immediate release failure
|
||||
|
||||
### **2. TENS-HUNDREDS OF MS SCALE (Short-term Energy Buffer)**
|
||||
|
||||
**Direct Behaviors Enabled:**
|
||||
|
||||
- **Ca²⁺ clearance**: PMCA pumps (1 Ca²⁺ out per ATP)
|
||||
- **Vesicle mobilization**: Myosin/kinesin ATPases for RP→RRP movement
|
||||
- **Endocytosis initiation**: Clathrin coat assembly (early phase)
|
||||
|
||||
**Energy Dynamics:**
|
||||
|
||||
- **Activity spike**: 1 AP → ~20,000 ATP molecules consumed
|
||||
- **Buffer capacity**: ~10⁸ ATP molecules in terminal → supports ~500 APs
|
||||
- **Recovery rate**: ~5 ATP/ms production at maximum mitochondrial output
|
||||
|
||||
**Cross-scale Coupling:**
|
||||
|
||||
- High **Ca+** influx → ↑ mitochondrial Ca²⁺ uptake → ↑ ATP production (seconds)
|
||||
- **K+** accumulation → activates Na⁺/K⁺ pump → ↑ ATP demand
|
||||
- **Lactate** conversion → ~15 ATP per lactate (delayed supply)
|
||||
|
||||
### **3. SECOND-MINUTE SCALE (Metabolic Regulation Hub)**
|
||||
|
||||
**Direct Behaviors Enabled:**
|
||||
|
||||
- **Vesicle recycling**: Complete endocytosis-exocytosis cycle (~30 ATP/vesicle)
|
||||
- **Neurotransmitter reloading**: Vacuolar H⁺-ATPase (2 H⁺/ATP) → glutamate uptake
|
||||
- **RP refilling**: New vesicle synthesis and transport
|
||||
|
||||
**Regulatory Functions:**
|
||||
|
||||
- **ATP/ADP ratio** as metabolic sensor:
|
||||
- High ATP: AMPK inactive → growth/maintenance
|
||||
- Low ATP: AMPK active → emergency response, ↓ protein synthesis
|
||||
- **Glycogen shunt**: Terminal glycogen → lactate (backup, seconds)
|
||||
- **Mitochondrial positioning**: ATP gradients guide movement to active zones
|
||||
|
||||
**Modulation by Other Variables:**
|
||||
|
||||
- **BDNF** → ↑ mitochondrial biogenesis → ↑ ATP capacity (hours)
|
||||
- **NO** → regulates cytochrome c oxidase → modulates ATP production
|
||||
- **eCB** → CB1 receptors inhibit adenylate cyclase → ↓ ATP synthesis
|
||||
|
||||
### **4. HOURS-DAYS SCALE (Structural Energy Budget)**
|
||||
|
||||
**Direct Behaviors Enabled:**
|
||||
|
||||
- **Protein synthesis**: ~4 ATP per peptide bond → VGCCs, vesicle proteins
|
||||
- **Organelle biogenesis**: Mitochondria, ER, vesicle pools
|
||||
- **Axonal transport**: Kinesin/dynein motors (1 ATP/8 nm step)
|
||||
|
||||
**Long-term ATP Allocation Decisions:**
|
||||
|
||||
```
|
||||
High activity + Adequate ATP → Investment in:
|
||||
1. More VGCCs (increased Ca²⁺ capacity)
|
||||
2. Larger RP (more vesicles)
|
||||
3. Additional mitochondria (future capacity)
|
||||
|
||||
High activity + Limited ATP → Conservation mode:
|
||||
1. VGCC invagination (lower Pr, save energy)
|
||||
2. Reduced RP size (lower maintenance cost)
|
||||
3. Enhanced lactate uptake (external energy)
|
||||
```
|
||||
|
||||
**BDNF-ATP Synergy:**
|
||||
|
||||
- **BDNF** signals "importance" → allocates ATP to structural growth
|
||||
- **ATP** availability determines BDNF effect magnitude
|
||||
- **Negative feedback**: Low ATP → ↓ TrkB trafficking → ↓ BDNF sensitivity
|
||||
|
||||
## **ATP as Cross-Scale Communication Channel**
|
||||
|
||||
### **Energy Status Signaling:**
|
||||
|
||||
```
|
||||
Fast signal (ms): ATP/ADP ratio at active zone → immediate release probability
|
||||
Medium signal (s): AMPK activation → mobilize energy reserves
|
||||
Slow signal (hours): PGC-1α activation → mitochondrial biogenesis
|
||||
```
|
||||
|
||||
### **Activity-Energy Feedback Loops:**
|
||||
|
||||
**Positive Feedback (Dangerous):**
|
||||
|
||||
```
|
||||
High activity → Ca²⁺ overload → mitochondrial damage → ↓ ATP
|
||||
↓ ATP → impaired Ca²⁺ clearance → more Ca²⁺ overload → more damage
|
||||
↓ ATP → reduced Na⁺/K⁺ pump → depolarization → more VGCC opening
|
||||
Result: Excitotoxicity
|
||||
```
|
||||
|
||||
**Negative Feedback (Protective):**
|
||||
|
||||
```
|
||||
High activity → ATP depletion → AMPK activation
|
||||
AMPK → ↓ protein synthesis (conserves ATP)
|
||||
AMPK → ↑ glucose transporters (enhances supply)
|
||||
AMPK → ↓ VGCC expression (reduces demand)
|
||||
Result: Homeostasis
|
||||
```
|
||||
|
||||
### **ATP-Dependent Plasticity Gates:**
|
||||
|
||||
**"Energy Checkpoint" for Structural Changes:**
|
||||
|
||||
```
|
||||
Question: Should synapse grow?
|
||||
Inputs: BDNF signal (importance) + Ca²⁺ history (activity) + ATP availability
|
||||
Decision rule:
|
||||
IF (BDNF high AND ATP adequate) → GROW
|
||||
IF (BDNF high AND ATP low) → INVAGINATE (save energy)
|
||||
IF (BDNF low AND ATP high) → MAINTAIN
|
||||
IF (BDNF low AND ATP low) → SHRINK
|
||||
```
|
||||
|
||||
## **Specific ATP ↔ Variable Interactions**
|
||||
|
||||
### **ATP ↔ Lactate (Critical Partnership)**
|
||||
|
||||
- **Astrocyte lactate** → neuron → pyruvate → 15 ATP via TCA cycle
|
||||
- **Activity-dependent coupling**: Glutamate uptake → astrocyte glycolysis → lactate export
|
||||
- **Timescale**: Seconds for lactate transport, minutes for glycogen mobilization
|
||||
|
||||
### **ATP ↔ VGCC (Bidirectional)**
|
||||
|
||||
- **ATP → VGCC**: Phosphorylation modulates opening kinetics (ms)
|
||||
- **VGCC → ATP demand**: Each Ca²⁺ ion requires 1 ATP for extrusion
|
||||
- **Homeostatic setpoint**: VGCC density adjusted to match ATP production capacity
|
||||
|
||||
### **ATP ↔ RP Size (Energy Budget)**
|
||||
|
||||
- **Storage cost**: ~100 ATP/day per vesicle (maintenance + turnover)
|
||||
- **Allocation decision**: ATP surplus → more vesicles; deficit → fewer vesicles
|
||||
- **Dynamic adjustment**: RP shrinks within hours of ATP shortage
|
||||
|
||||
### **ATP ↔ K⁺/KChannels (Stability Control)**
|
||||
|
||||
- **Na⁺/K⁺ pump**: 1 ATP clears 3 Na⁺, brings 2 K⁺
|
||||
- **K⁺ accumulation** without ATP → depolarization → runaway excitation
|
||||
- **KChannels** require ATP for phosphorylation-dependent modulation
|
||||
|
||||
## **Clinical/Experimental Implications**
|
||||
|
||||
**Energy-Limited Plasticity:**
|
||||
|
||||
- Learning under low ATP (sleep deprivation, metabolic stress) → less structural change
|
||||
- High ATP + BDNF → optimal plasticity window
|
||||
|
||||
**Therapeutic Targets:**
|
||||
|
||||
- Enhance lactate shuttle → support ATP during high demand
|
||||
- Modulate AMPK → shift energy allocation decisions
|
||||
- Mitochondrial support → increase ATP capacity for structural changes
|
||||
|
||||
**Measurement Approaches:**
|
||||
|
||||
- **FRET ATP sensors**: Real-time ATP dynamics (seconds)
|
||||
- **ATP/ADP ratio**: Metabolic status (minutes)
|
||||
- **Mitochondrial density**: ATP capacity (hours-days)
|
||||
|
||||
## **Summary: ATP as Presynaptic "Bank Account"**
|
||||
|
||||
```
|
||||
Quick cash (ms): ATP at active zone → immediate transactions
|
||||
Checking account (100ms): Cytosolic ATP → short-term operations
|
||||
Savings account (seconds): Mitochondrial/phosphocreatine → buffer
|
||||
Investment portfolio (hours): Structural changes → long-term capacity
|
||||
Credit line (emergency): Lactate shuttle → external support
|
||||
```
|
||||
|
||||
The presynaptic terminal's ATP management strategy determines:
|
||||
|
||||
- **Release fidelity** (ms scale)
|
||||
- **Short-term plasticity** (100ms scale)
|
||||
- **Sustained transmission** (second scale)
|
||||
- **Structural adaptation** (hour-day scale)
|
||||
|
||||
Every plasticity decision is fundamentally an energy allocation decision, with ATP serving as both the currency and the accountant.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# **Ca²⁺: The Universal Presynaptic Signal**
|
||||
|
||||
## **Ca²⁺ Across Temporal Scales**
|
||||
|
||||
### **1. MILLISECOND SCALE (Nano/Submicrodomain Ca²⁺)**
|
||||
|
||||
**Direct Behaviors Triggered:**
|
||||
|
||||
- **Vesicle fusion**: Cooperative binding to synaptotagmin (n~4)
|
||||
- **KChannel activation**: SK channels open → fast afterhyperpolarization
|
||||
- **VGCC feedback**: Ca²⁺-dependent inactivation (CDI)
|
||||
|
||||
**Dynamics:**
|
||||
|
||||
- **Rise time**: <100 μs to peak
|
||||
- **Decay time constant**: 200-500 μs (fast buffers)
|
||||
- **Diffusion coefficient**: ~200 μm²/s (buffered)
|
||||
|
||||
**Influences on Other Variables:**
|
||||
|
||||
```
|
||||
Ca²⁺ (ms) → Vesicles release: Exponential dependence (EC₅₀ ~ 10-25 μM)
|
||||
Ca²⁺ (ms) → KChannels (SK): Fast AHP → modulates next AP
|
||||
Ca²⁺ (ms) → VGCC: CDI reduces subsequent Ca²⁺ influx
|
||||
```
|
||||
|
||||
### **2. TENS-HUNDREDS OF MS SCALE (Global Terminal Ca²⁺)**
|
||||
|
||||
**Spatial Integration:**
|
||||
|
||||
- **Bulk concentration**: 0.2-2 μM throughout terminal
|
||||
- **Residual Ca²⁺**: 0.1-0.5 μM between APs
|
||||
|
||||
**Direct Behaviors Enabled:**
|
||||
|
||||
- **Vesicle mobilization**: Ca²⁺-dependent phosphatase activation (calcineurin)
|
||||
- **Short-term plasticity**:
|
||||
- **Facilitation**: Residual Ca²⁺ binds to synaptotagmin priming
|
||||
- **Augmentation**: Sustained Ca²⁺ activates CaMKII
|
||||
- **Metabolic coupling**: Mitochondrial Ca²⁺ uptake initiation
|
||||
|
||||
**Cross-scale Interactions:**
|
||||
|
||||
```
|
||||
Ca²⁺ (100ms) → NO production: Activates postsynaptic NOS → retrograde signal
|
||||
Ca²⁺ (100ms) → eCB synthesis: Postsynaptic DAG lipase activation
|
||||
Ca²⁺ (100ms) → RP→RRP: Calcineurin dephosphorylates synapsin
|
||||
Ca²⁺ (100ms) → ATP demand: Each Ca²⁺ extruded requires 1 ATP
|
||||
```
|
||||
|
||||
**Mathematical Representation:**
|
||||
|
||||
```
|
||||
d[Ca²⁺]_global/dt = J_influx - J_pump - J_mitochondria - J_diffusion
|
||||
where:
|
||||
J_influx ∝ Σ(VGCC_open) over recent APs
|
||||
J_pump = V_max·[Ca²⁺]/(K_m + [Ca²⁺]) (ATP-dependent)
|
||||
J_mitochondria = k_m·[Ca²⁺]·(ΔΨ_m - threshold)
|
||||
```
|
||||
|
||||
### **3. SECOND-MINUTE SCALE (Signaling Ca²⁺)**
|
||||
|
||||
**Direct Behaviors Enabled:**
|
||||
|
||||
- **Gene expression**: Nuclear Ca²⁺ → CREB phosphorylation
|
||||
- **Metabolic regulation**: Mitochondrial matrix Ca²⁺ → TCA cycle enzymes
|
||||
- **Structural tagging**: Local Ca²⁺ waves mark active synapses
|
||||
|
||||
**Signal Integration Mechanisms:**
|
||||
|
||||
- **Frequency decoding**: Ca²⁺ spikes → NFAT activation
|
||||
- **Amplitude decoding**: High Ca²⁺ → CamKII autophosphorylation
|
||||
- **Duration decoding**: Sustained Ca²⁺ → MAPK pathway activation
|
||||
|
||||
**Modulation by Other Variables:**
|
||||
|
||||
```
|
||||
ATP ↓ → Reduced Ca²⁺ clearance → Elevated baseline Ca²⁺
|
||||
BDNF → Enhances Ca²⁺ signals via PLCγ→IP₃→ER release
|
||||
NO → cGMP → PKG → modulates Ca²⁺ channels and pumps
|
||||
Lactate → Supports mitochondrial Ca²⁺ uptake via ATP
|
||||
```
|
||||
|
||||
### **4. HOURS-DAYS SCALE (Ca²⁺ as Structural Organizer)**
|
||||
|
||||
**Direct Behaviors Enabled:**
|
||||
|
||||
- **Synapse growth/shrinkage**: Ca²⁺-dependent gene expression programs
|
||||
- **Homeostatic scaling**: Chronic Ca²⁺ levels set VGCC density
|
||||
- **Metaplasticity**: Ca²⁺ history determines future plasticity rules
|
||||
|
||||
**Ca²⁺ Setpoints and Homeostasis:**
|
||||
|
||||
- **Target baseline**: 50-100 nM (resting)
|
||||
- **Activity setpoint**: Integrated over hours determines structural changes
|
||||
- **Memory window**: Ca²⁺ history of last 24-48 hours influences current state
|
||||
|
||||
## **Ca²⁺ as Information Encoder**
|
||||
|
||||
### **Temporal Coding by Ca²⁺:**
|
||||
|
||||
**Amplitude Encoding:**
|
||||
|
||||
- Single AP: ~0.5 μM global Ca²⁺
|
||||
- 10 Hz train: ~1.5 μM global Ca²⁺
|
||||
- 100 Hz burst: >5 μM global Ca²⁺
|
||||
|
||||
**Frequency Encoding:**
|
||||
|
||||
- Low frequency (<1 Hz): Discrete Ca²⁺ transients
|
||||
- Theta (4-8 Hz): Partial summation
|
||||
- Gamma (30-100 Hz): Sustained elevation
|
||||
|
||||
**Duration Encoding:**
|
||||
|
||||
- Brief (<100 ms): Fast signaling only
|
||||
- Medium (1-10 s): Activates kinases
|
||||
- Long (>1 min): Triggers gene expression
|
||||
|
||||
### **Spatial Coding by Ca²⁺:**
|
||||
|
||||
**Microdomain vs Global Signals:**
|
||||
|
||||
```
|
||||
VGCC cluster 1 → Ca²⁺ microdomain 1 → Vesicles 1-3
|
||||
VGCC cluster 2 → Ca²⁺ microdomain 2 → Vesicles 4-6
|
||||
Diffusion → Global Ca²⁺ → Mobilization, metabolic signals
|
||||
```
|
||||
|
||||
**Compartmentalization:**
|
||||
|
||||
- **Active zone**: Release-triggering (fast)
|
||||
- **Vesicle pools**: Mobilization (medium)
|
||||
- **Mitochondria**: Metabolic coupling (slow)
|
||||
- **Nucleus**: Gene regulation (very slow)
|
||||
|
||||
## **Ca²⁺ ↔ Specific Variable Interactions**
|
||||
|
||||
### **Ca²⁺ ↔ VGCC (Bidirectional Control)**
|
||||
|
||||
```
|
||||
Fast (ms): Ca²⁺-dependent inactivation (CDI) - negative feedback
|
||||
Medium (s): Ca²⁺-dependent facilitation (CDF) - positive feedback
|
||||
Slow (hours): Ca²⁺-dependent VGCC expression - homeostatic
|
||||
```
|
||||
|
||||
### **Ca²⁺ ↔ ATP (Energy-Coupling)**
|
||||
|
||||
- **Ca²⁺ → ATP demand**: Each Ca²⁺ ion requires 1 ATP for extrusion
|
||||
- **Ca²⁺ → ATP production**: Mitochondrial Ca²⁺ stimulates TCA cycle
|
||||
- **ATP → Ca²⁺ handling**: ATP fuels pumps, buffers, organelle uptake
|
||||
|
||||
### **Ca²⁺ ↔ BDNF (Trophic Loop)**
|
||||
|
||||
```
|
||||
Presynaptic: Ca²⁺ influx → Vesicle release → Glutamate
|
||||
Postsynaptic: Glutamate → NMDA → Ca²⁺ → BDNF synthesis
|
||||
Retrograde: BDNF → Presynaptic TrkB → Enhanced Ca²⁺ signals
|
||||
```
|
||||
|
||||
### **Ca²⁺ ↔ eCB (Retrograde Modulation)**
|
||||
|
||||
```
|
||||
Postsynaptic: Ca²⁺ + mGluR → DAG → 2-AG synthesis
|
||||
Retrograde: eCB → Presynaptic CB1 → Inhibits VGCC
|
||||
Feedback: Reduced Ca²⁺ → Less glutamate → Less eCB
|
||||
```
|
||||
|
||||
### **Ca²⁺ ↔ Lactate (Metabolic Feedback)**
|
||||
|
||||
```
|
||||
Presynaptic Ca²⁺ → Glutamate release → Astrocyte uptake
|
||||
Astrocyte: Glutamate → Na⁺ influx → Glycolysis → Lactate
|
||||
Lactate → Presynaptic → ATP → Supports Ca²⁺ handling
|
||||
```
|
||||
|
||||
### **Ca²⁺ ↔ K⁺/KChannels (Excitability Control)**
|
||||
|
||||
```
|
||||
Ca²⁺ → SK channels → K⁺ efflux → Fast AHP → Limits firing
|
||||
K⁺ accumulation → Depolarization → More VGCC opening → More Ca²⁺
|
||||
Ca²⁺ → BK channels → Faster repolarization → Shorter AP
|
||||
```
|
||||
|
||||
## **Ca²⁺-Dependent Plasticity Rules**
|
||||
|
||||
### **Short-term Rules (ms-s):**
|
||||
|
||||
```
|
||||
Residual Ca²⁺ model: RRP release ∝ [Ca²⁺]_residual^n
|
||||
Facilitation: PPR = 1 + ([Ca²⁺]_residual/EC₅₀)
|
||||
Depression: Vesicle depletion rate ∝ [Ca²⁺]_peak
|
||||
```
|
||||
|
||||
### **Long-term Rules (min-days):**
|
||||
|
||||
```
|
||||
BCM-like rule:
|
||||
if [Ca²⁺]_avg < θ₁ → Downscale (LTD)
|
||||
if θ₁ < [Ca²⁺]_avg < θ₂ → No change
|
||||
if [Ca²⁺]_avg > θ₂ → Upscale (LTP)
|
||||
|
||||
θ₁ and θ₂ adjust based on Ca²⁺ history (metaplasticity)
|
||||
```
|
||||
|
||||
### **Structural Rules:**
|
||||
|
||||
```
|
||||
VGCC expression rate = k₁·[Ca²⁺]_integral - k₂·[VGCC]
|
||||
RP size = k₃·BDNF·[Ca²⁺]_avg - k₄·[RP]
|
||||
Where BDNF itself depends on Ca²⁺ history
|
||||
```
|
||||
|
||||
## **Clinical/Experimental Implications**
|
||||
|
||||
### **Ca²⁺ Dysregulation Pathologies:**
|
||||
|
||||
- **Excitotoxicity**: Chronic high Ca²⁺ → mitochondrial failure → cell death
|
||||
- **Synaptic fatigue**: Impaired Ca²⁺ clearance → reduced dynamic range
|
||||
- **Plasticity disorders**: Altered Ca²⁺ setpoints → LTP/LTD imbalance
|
||||
|
||||
### **Measurement Approaches:**
|
||||
|
||||
- **Fast dyes (Fluo-4FF)**: Microdomain Ca²⁺ (ms)
|
||||
- **GCaMP variants**: Global Ca²⁺ (10-100 ms resolution)
|
||||
- **Ca²⁺ integrators (CaMKII)**: History over minutes
|
||||
- **Structural readouts**: VGCC clustering, vesicle pools (hours-days)
|
||||
|
||||
### **Therapeutic Targets:**
|
||||
|
||||
- **VGCC blockers**: Reduce pathological Ca²⁺ influx
|
||||
- **Ca²⁺ buffer enhancers**: Improve clearance
|
||||
- **Mitochondrial Ca²⁺ uptake**: Protect against excitotoxicity
|
||||
- **Ca²⁺ setpoint modulators**: Restore homeostatic balance
|
||||
|
||||
## **Summary: Ca²⁺ as Multiscale Integrator**
|
||||
|
||||
**Microscale (ms):** Release trigger → Digital signal (vesicle fusion/no fusion)
|
||||
**Mesoscale (100ms):** Plasticity mediator → Analog signal (facilitation/depression)
|
||||
**Macroscale (min):** Metabolic regulator → Energy allocation signal
|
||||
**Macroscale (hours):** Structural organizer → Growth/retraction signal
|
||||
|
||||
**Key Principles:**
|
||||
|
||||
1. **Dual signaling**: Microdomain (fast, local) vs Global (slow, integrative)
|
||||
2. **Timescale-specific effectors**: Different targets at different Ca²⁺ durations
|
||||
3. **Bidirectional coupling**: Ca²⁺ influences everything, everything influences Ca²⁺
|
||||
4. **Setpoint homeostasis**: Systems maintain optimal Ca²⁺ levels across timescales
|
||||
5. **Memory encoding**: Ca²⁺ history changes future Ca²⁺ handling
|
||||
|
||||
**The Ca²⁺ Paradox:**
|
||||
The same ion that triggers millisecond release also organizes day-scale structural changes, with no contradiction because:
|
||||
|
||||
- Different **concentrations** activate different effectors
|
||||
- Different **durations** engage different signaling pathways
|
||||
- Different **localizations** communicate different information
|
||||
- Different **frequencies** encode different messages
|
||||
|
||||
Ca²⁺ is not just a signal—it's the alphabet of presynaptic communication, with its timing, amplitude, and location forming words, sentences, and stories across timescales.
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
# CDI
|
||||
|
||||
**Ca²⁺-dependent inactivation** is a rapid negative feedback mechanism where **VGCCs self-regulate** by closing more quickly when **Ca²⁺ ions** bind to specific sites on the channel itself. This happens within **milliseconds** of channel opening.
|
||||
|
||||
## **Sequence of Events:**
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
1. VGCC opens → Ca²⁺ influx through pore
|
||||
2. Ca²⁺ binds to CaM already tethered to channel (microdomain Ca²⁺ ~10-100 μM)
|
||||
3. Ca²⁺/CaM complex conformation change
|
||||
4. Ca²⁺/CaM binds to IQ domain
|
||||
5. Channel pore undergoes conformational change → CLOSES
|
||||
6. Channel enters inactivated state (refractory to reopening)
|
||||
```
|
||||
|
||||
**Timing:**
|
||||
|
||||
- **Onset**: Within 5-50 ms of channel opening
|
||||
- **Full inactivation**: 100-300 ms
|
||||
- **Recovery**: 100-1000 ms (requires Ca²⁺ unbinding)
|
||||
|
||||
## **Functional Significance in Presynapse**
|
||||
|
||||
### **Millisecond Timescale Effects:**
|
||||
|
||||
| Effect | Consequence |
|
||||
|----------------------------------|----------------------------------------|
|
||||
| **Shortens Ca²⁺ influx duration** | Limits total Ca²⁺ per action potential |
|
||||
| **Prevents Ca²⁺ overload** | Protects against excitotoxicity |
|
||||
| **Filters high-frequency firing** | Channels inactivate during trains |
|
||||
| **Shapes AP-evoked Ca²⁺ transients** | Determines Ca²⁺ waveform |
|
||||
|
||||
### **Impact on Vesicle Release:**
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
Without CDI: Sustained Ca²⁺ influx → higher Pr, more vesicles released
|
||||
With CDI: Brief Ca²⁺ influx → lower Pr, fewer vesicles released
|
||||
CDI modulation: Alters release probability dynamically
|
||||
```
|
||||
|
||||
### **Short-term Plasticity Implications:**
|
||||
|
||||
- **High-frequency trains**: CDI accumulates → less Ca²⁺ per AP → depression
|
||||
- **Recovery between bursts**: CDI relief → restored Ca²⁺ influx → facilitation
|
||||
- **Frequency filtering**: CDI acts as low-pass filter for presynaptic Ca²⁺ signals
|
||||
|
||||
## **CDI vs Other Inactivation Mechanisms**
|
||||
|
||||
### **Three Types of VGCC Inactivation:**
|
||||
|
||||
1. **Ca²⁺-dependent (CDI)** - Fast, Ca²⁺-mediated (\~50 ms)
|
||||
2. **Voltage-dependent (VDI)** - Slower, voltage-sensor mediated (\~100-500 ms)
|
||||
3. **G-protein mediated** - Slower, neurotransmitter modulation (\~100-1000 ms)
|
||||
|
||||
### **Presynaptic Dominance:**
|
||||
|
||||
- **Calcium channels in presynapse**: Primarily **CaV2.1 (P/Q-type)** and **CaV2.2 (N-type)**
|
||||
- **CDI strength**: CaV2.1 > CaV2.2
|
||||
- **Location specificity**: Active zone channels show strongest CDI
|
||||
|
||||
## **Modulation of CDI by other factors**
|
||||
|
||||
### **BDNF Modulation:**
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
BDNF → TrkB → PLCγ → DAG → PKC → phosphorylates VGCC
|
||||
Result: ↓ CDI → prolonged Ca²⁺ influx → enhanced release
|
||||
```
|
||||
|
||||
### **NO Modulation:**
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
NO → sGC → cGMP → PKG → phosphorylates CaM or VGCC
|
||||
Result: ↑ CDI → shorter Ca²⁺ influx → reduced release
|
||||
```
|
||||
|
||||
### **eCB Modulation:**
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
eCB → CB1 → Gβγ → binds VGCC directly
|
||||
Result: Channel inhibition + ↑ CDI → strong suppression
|
||||
```
|
||||
|
||||
### **ATP/Energy Status:**
|
||||
|
||||
text
|
||||
|
||||
```
|
||||
Low ATP → impaired Ca²⁺ pumps → elevated resting Ca²⁺
|
||||
Result: CaM partially occupied → reduced CDI dynamic range
|
||||
```
|
||||
@@ -0,0 +1,300 @@
|
||||
# **Presynaptic Release Model: Sequence of Events & Multi-Timescale Modulations**
|
||||
|
||||
## **CORE RELEASE SEQUENCE (Milliseconds)**
|
||||
|
||||
### **Event 1: Action Potential Arrival**
|
||||
|
||||
```
|
||||
Time: t = 0 ms
|
||||
Trigger: Depolarization from axon hillock
|
||||
Mechanism: Na⁺/K⁺ voltage-gated channel cascade
|
||||
State: Terminal depolarizes from -70 mV to +30 mV
|
||||
Duration: ~1 ms
|
||||
```
|
||||
|
||||
### **Event 2: VGCC Opening**
|
||||
|
||||
```
|
||||
Time: t = 0.2-0.5 ms after AP arrival
|
||||
Trigger: Membrane depolarization > -40 mV
|
||||
Types: CaV2.1 (P/Q-type), CaV2.2 (N-type) at active zone
|
||||
Mechanism: Voltage sensor movement → pore opening
|
||||
Open probability: ~0.3-0.8 during AP peak
|
||||
Open duration: ~0.5-2 ms
|
||||
```
|
||||
|
||||
### **Event 3: Ca²⁺ Influx & Microdomain Formation**
|
||||
|
||||
```
|
||||
Time: t = 0.3-1 ms after AP arrival
|
||||
Ca²⁺ source: Extracellular (1.2 mM) → intracellular (50 nM baseline)
|
||||
Influx rate: ~3000-10000 Ca²⁺ ions per VGCC per ms
|
||||
Microdomain formation:
|
||||
- Within 20 nm of VGCC: 10-100 µM
|
||||
- At vesicle release site: 10-25 µM threshold for release
|
||||
- Rise time: <100 µs
|
||||
- Diffusion-limited spread: ~100-200 nm radius
|
||||
```
|
||||
|
||||
### **Event 4: Vesicle Release Decision**
|
||||
|
||||
```
|
||||
Time: t = 0.4-1.5 ms after AP arrival
|
||||
Decision conditions (AND logic):
|
||||
1. [Ca²⁺]microdomain > 10-25 µM
|
||||
2. Vesicle in RRP (docked & primed)
|
||||
3. SNARE complex in primed state
|
||||
4. Synaptotagmin Ca²⁺ binding sites occupied
|
||||
Mechanism:
|
||||
- Ca²⁺ binds synaptotagmin (4+ cooperative sites)
|
||||
- Synaptotagmin displaces complexin clamp
|
||||
- SNARE complex completes zippering
|
||||
- Vesicle membrane fuses with presynaptic membrane
|
||||
Release latency: 0.1-1.0 ms after Ca²⁺ threshold reached
|
||||
Release synchrony: Multiple vesicles can release simultaneously
|
||||
```
|
||||
|
||||
### **Event 5: Ca²⁺ Clearance**
|
||||
|
||||
```
|
||||
Time: t = 1-50 ms after influx
|
||||
Clearance mechanisms (in order of speed):
|
||||
1. Fast buffers (calbindin, parvalbumin): <1 ms
|
||||
2. Plasma membrane Ca²⁺ ATPase (PMCA): 10-100 ms
|
||||
3. Na⁺/Ca²⁺ exchanger (NCX): 10-100 ms
|
||||
4. Mitochondrial uptake: 10-1000 ms
|
||||
5. Endoplasmic reticulum uptake: 100-1000 ms
|
||||
Residual Ca²⁺: 0.1-0.5 µM persists for 10-1000 ms
|
||||
```
|
||||
|
||||
### **Event 6: Vesicle Recycling**
|
||||
|
||||
```
|
||||
Time: t = 10 ms - 10 s (depending on activity)
|
||||
Sequential steps:
|
||||
1. Endocytosis (clathrin-mediated, kiss-and-run, bulk)
|
||||
2. Vesicle re-acidification (v-ATPase)
|
||||
3. Neurotransmitter reloading (vesicular transporters)
|
||||
4. Priming (SNARE assembly, docking)
|
||||
5. Return to RRP
|
||||
Recycling rate: Limited by ATP availability
|
||||
```
|
||||
|
||||
## **MODULATION MATRIX ACROSS TIMESCALES**
|
||||
|
||||
### **MODULATION LEVEL 1: MILLISECONDS (Immediate Signal Processing)**
|
||||
|
||||
| Event | Modulator | Effect | Mechanism | Timescale |
|
||||
|------------------|-----------------------------------|----------------------------------------|---------------------------------------------|---------------------|
|
||||
| **VGCC Opening** | Voltage waveform | AP width/duration affects open time | K⁺ channel activation shapes repolarization | During AP (1 ms) |
|
||||
| **VGCC Opening** | Ca²⁺-dependent inactivation (CDI) | Auto-inhibition | Ca²⁺ binding to calmodulin on VGCC | 5-50 ms |
|
||||
| **Ca²⁺ Microdomain** | Endogenous buffers | Shapes [Ca²⁺] spatial/temporal profile | Calbindin, parvalbumin binding | <1 ms |
|
||||
| **Release Decision** | Synaptotagmin isoforms | Different Ca²⁺ sensitivity | Cooperative binding sites vary | During Ca²⁺ binding |
|
||||
| **Release Decision** | SNARE complex state | Priming level determines speed | Munc13 activity, NSF disassembly | <1 ms |
|
||||
| **Ca²⁺ Clearance** | Fast buffers | Immediate Ca²⁺ binding | High-affinity Ca²⁺ binding proteins | <1 ms |
|
||||
|
||||
### **MODULATION LEVEL 2: TENS-HUNDREDS OF MILLISECONDS (Short-term Plasticity)**
|
||||
|
||||
| Event | Modulator | Effect | Mechanism | Timescale |
|
||||
|---------------------|----------------------|-------------------------------|-----------------------------------------------------|---------------|
|
||||
| **VGCC Opening** | Residual Ca²⁺ | Ca²⁺-dependent facilitation | Ca²⁺/CaM binding to VGCC β-subunit | 10-1000 ms |
|
||||
| **VGCC Opening** | eCB (CB1 activation) | Direct inhibition | Gβγ subunit blocks pore | 100-2000 ms |
|
||||
| **Ca²⁺ Microdomain** | Mitochondrial uptake | Buffer capacity changes | Uniporter activity with Ca²⁺ buildup | 10-1000 ms |
|
||||
| **RRP Replenishment** | Residual Ca²⁺ | Enhanced mobilization | Calcineurin activation → synapsin dephosphorylation | 10-1000 ms |
|
||||
| **RRP Replenishment** | ATP availability | Limits priming rate | NSF, v-ATPase, priming ATPases | Continuous |
|
||||
| **Release Probability** | mGluR autoreceptors | Activity-dependent inhibition | Gi/o → ↓cAMP → ↓PKA → ↓VGCC | 50-500 ms |
|
||||
| **Ca²⁺ Clearance** | PMCA/NCX pumps | Activity-dependent saturation | Limited pump capacity during high frequency | 10-1000 ms |
|
||||
| **Vesicle Recycling** | Activity level | Different endocytosis modes | High activity → bulk endocytosis | 100 ms - 10 s |
|
||||
|
||||
### **MODULATION LEVEL 3: SECONDS-MINUTES (Metabolic & Signaling)**
|
||||
|
||||
| Event | Modulator | Effect | Mechanism | Timescale |
|
||||
|-------------------|-----------------------------|----------------------------|-----------------------------------------|--------------|
|
||||
| **VGCC Density** | Surface expression | More/fewer channels | Phosphorylation-dependent trafficking | 30 s - 5 min |
|
||||
| **VGCC Function** | Kinase phosphorylation | Changed open probability | PKA, PKC, CaMKII phosphorylation | 1-10 min |
|
||||
| **Ca²⁺ Dynamics** | NO (cGMP pathway) | Altered pump activity | PKG phosphorylation of PMCA | 1-10 min |
|
||||
| **Vesicle Pools** | Mobilization rate | RP→RRP speed changes | Synapsin phosphorylation state | 1-10 min |
|
||||
| **ATP Production** | Lactate shuttle | Enhanced ATP supply | Astrocyte-neuron metabolic coupling | 1-10 min |
|
||||
| **Release Machinery** | BDNF (acute) | Enhanced priming & docking | TrkB → PLCγ → PKC activation | 1-10 min |
|
||||
| **Autoreceptor** | mGluR desensitization | Reduced autoinhibition | β-arrestin recruitment, internalization | 1-10 min |
|
||||
| **CB1 Receptor** | eCB-induced desensitization | Reduced inhibition | GRK phosphorylation, internalization | 1-10 min |
|
||||
| **Ca²⁺ Clearance** | Mitochondrial adaptation | Increased capacity | Matrix Ca²⁺ activates dehydrogenases | 1-10 min |
|
||||
|
||||
### **MODULATION LEVEL 4: MINUTES-HOURS (Structural & Transcriptional)**
|
||||
|
||||
| Event | Modulator | Effect | Mechanism | Timescale |
|
||||
|-----------------------|--------------------|-------------------------------|----------------------------------------------|---------------|
|
||||
| **VGCC Expression** | BDNF (chronic) | Increased channel synthesis | TrkB → MAPK → CREB → gene expression | 30 min - 6 hr |
|
||||
| **VGCC Expression** | Activity-dependent | Homeostatic scaling | Ca²⁺ → NFAT/CREB → VGCC genes | 1-24 hr |
|
||||
| **Active Zone Size** | BDNF, activity | More release sites | Structural proteins (RIM, Bassoon) synthesis | 1-12 hr |
|
||||
| **Vesicle Pool Size** | BDNF, activity | Larger RP/RRP | Synaptic vesicle protein synthesis | 1-12 hr |
|
||||
| **SNARE Machinery** | Local translation | More fusion complexes | mTOR-dependent protein synthesis | 30 min - 3 hr |
|
||||
| **Mitochondrial Density** | BDNF, activity | Increased ATP capacity | PGC-1α activation → biogenesis | 3-24 hr |
|
||||
| **Metabolic Pathways** | Activity patterns | Enhanced glycolysis/oxidation | HIF-1α, AMPK pathway activation | 1-6 hr |
|
||||
| **Receptor Expression** | Chronic modulation | mGluR, CB1 level changes | Transcriptional regulation | 3-12 hr |
|
||||
| **Buffer Expression** | Ca²⁺ history | Calbindin/parvalbumin levels | Ca²⁺-dependent gene regulation | 3-12 hr |
|
||||
|
||||
### **MODULATION LEVEL 5: HOURS-DAYS (Metaplasticity & Structural Remodeling)**
|
||||
|
||||
| Event | Modulator | Effect | Mechanism | Timescale |
|
||||
|---------------------------|-----------------------|-------------------------------------|--------------------------------------------|-----------|
|
||||
| **Synapse Size** | Chronic activity | Growth/shrinkage | Cytoskeletal reorganization | 6-48 hr |
|
||||
| **VGCC Distribution** | Activity patterns | Clustering changes | Scaffold protein (Homer, Shank) expression | 12-72 hr |
|
||||
| **Release Site Organization** | BDNF, activity | Active zone architecture | Piccolo, Bassoon, RIM expression | 12-72 hr |
|
||||
| **Vesicle Recycling** | Chronic patterns | Efficiency changes | Endocytosis machinery expression | 12-48 hr |
|
||||
| **Metaplasticity Rules** | Activity history | Altered LTP/LTD thresholds | Kinase/phosphatase expression changes | 24-72 hr |
|
||||
| **Energy Allocation** | Chronic demand | Mitochondrial positioning | Motor protein (kinesin, dynein) adaptation | 12-48 hr |
|
||||
| **Network Integration** | System-level activity | Presynaptic inhibition/facilitation | Interneuron connectivity changes | 24-96 hr |
|
||||
|
||||
## **MODULATION CASCADES (How Signals Propagate Through Events)**
|
||||
|
||||
### **Example 1: High-Frequency Activity Cascade**
|
||||
|
||||
```
|
||||
Event Timeline:
|
||||
t = 0 ms: First AP → Release (high Pr)
|
||||
t = 10 ms: Second AP → Enhanced release (residual Ca²⁺ facilitation)
|
||||
t = 100 ms: Tenth AP → Depressed release (RRP depletion, eCB inhibition)
|
||||
|
||||
Modulation Cascade:
|
||||
Milliseconds: CDI develops, buffers saturate
|
||||
Seconds: mGluR autoinhibition builds, ATP depletes
|
||||
Minutes: BDNF synthesis begins, pumps adapt
|
||||
Hours: VGCC expression increases, active zone grows
|
||||
Days: Synapse strengthens, metaplasticity changes
|
||||
```
|
||||
|
||||
### **Example 2: BDNF-Mediated Potentiation Cascade**
|
||||
|
||||
```
|
||||
Event Timeline:
|
||||
t = 0-5 min: BDNF binds TrkB receptors
|
||||
t = 5-30 min: Kinase cascades activate
|
||||
t = 30-120 min: Local protein synthesis
|
||||
t = 3-24 hr: Structural changes
|
||||
|
||||
Modulation Cascade:
|
||||
Milliseconds: Immediate VGCC phosphorylation (↑ open probability)
|
||||
Seconds: Enhanced vesicle priming (↑ RRP replenishment)
|
||||
Minutes: More SNARE complexes synthesized (↑ release sites)
|
||||
Hours: Additional VGCCs inserted (↑ Ca²⁺ influx capacity)
|
||||
Days: Active zone expansion (↑ number of release sites)
|
||||
```
|
||||
|
||||
### **Example 3: eCB-Mediated Depression Cascade**
|
||||
|
||||
```
|
||||
Event Timeline:
|
||||
t = 100 ms: eCB produced postsynaptically
|
||||
t = 200 ms: CB1 activation inhibits VGCCs
|
||||
t = 1-10 min: β-arrestin recruitment, CB1 internalization
|
||||
t = 1-24 hr: CB1 downregulation, structural changes
|
||||
|
||||
Modulation Cascade:
|
||||
Milliseconds: Direct VGCC block (↓ Ca²⁺ influx)
|
||||
Seconds: Reduced cAMP → ↓ PKA → ↓ vesicle priming
|
||||
Minutes: CB1 internalization → reduced inhibition
|
||||
Hours: CB1 downregulation → reduced modulatory capacity
|
||||
Days: Synaptic downscaling → smaller active zone
|
||||
```
|
||||
|
||||
## **CROSS-EVENT MODULATION PATTERNS**
|
||||
|
||||
### **Feedforward Loops:**
|
||||
|
||||
```
|
||||
Positive:
|
||||
AP → Ca²⁺ influx → CaMKII activation → ↑ VGCC phosphorylation → ↑ Ca²⁺ influx
|
||||
|
||||
Negative:
|
||||
AP → Glutamate release → mGluR activation → ↓ VGCC opening → ↓ Ca²⁺ influx
|
||||
```
|
||||
|
||||
### **Feedback Loops:**
|
||||
|
||||
```
|
||||
Homeostatic:
|
||||
High activity → Ca²⁺ buildup → gene expression → more buffers/pumps → ↓ Ca²⁺ buildup
|
||||
|
||||
Trophic:
|
||||
Activity → BDNF release → structural growth → more release sites → more activity
|
||||
```
|
||||
|
||||
### **Energy Management Loops:**
|
||||
|
||||
```
|
||||
Energy Conservation:
|
||||
ATP depletion → AMPK activation → ↓ protein synthesis → ↓ energy consumption
|
||||
|
||||
Energy Investment:
|
||||
BDNF + adequate ATP → mTOR activation → protein synthesis → structural growth
|
||||
```
|
||||
|
||||
## **INTEGRATED TIMELINE OF A RELEASE EVENT WITH MODULATIONS**
|
||||
|
||||
### **t = 0-1 ms (AP to Release)**
|
||||
|
||||
```
|
||||
Primary events: AP → VGCC open → Ca²⁺ influx → Release
|
||||
Modulations active:
|
||||
- AP shape from previous activity (K⁺ channel adaptation)
|
||||
- VGCDI from recent Ca²⁺ history
|
||||
- SNARE priming from recent ATP availability
|
||||
- Buffer capacity from expression levels
|
||||
```
|
||||
|
||||
### **t = 1-100 ms (Immediate Aftermath)**
|
||||
|
||||
```
|
||||
Primary events: Ca²⁺ clearance, vesicle recycling initiation
|
||||
Modulations active:
|
||||
- Residual Ca²⁺ facilitating next release
|
||||
- mGluR autoinhibition building
|
||||
- eCB production if postsynaptic Ca²⁺ high
|
||||
- ATP consumption for pumps and recycling
|
||||
```
|
||||
|
||||
### **t = 100 ms - 1 min (Short-term Adaptation)**
|
||||
|
||||
```
|
||||
Primary events: RRP replenishment, metabolic adjustments
|
||||
Modulations active:
|
||||
- Kinase/phosphatase balance shifting
|
||||
- NO production if sustained activity
|
||||
- BDNF release if activity pattern significant
|
||||
- Mitochondrial Ca²⁺ uptake affecting ATP
|
||||
```
|
||||
|
||||
### **t = 1 min - 1 hr (Medium-term Plasticity)**
|
||||
|
||||
```
|
||||
Primary events: Protein synthesis, trafficking changes
|
||||
Modulations active:
|
||||
- Local translation of VGCCs, SNAREs
|
||||
- Receptor trafficking to/from surface
|
||||
- Mitochondrial positioning changes
|
||||
- Metabolic pathway adjustments
|
||||
```
|
||||
|
||||
### **t = 1 hr - days (Long-term Restructuring)**
|
||||
|
||||
```
|
||||
Primary events: Structural changes, gene expression
|
||||
Modulations active:
|
||||
- Nuclear signaling for gene expression
|
||||
- Cytoskeletal reorganization
|
||||
- Synapse growth/shrinkage
|
||||
- Metaplasticity rule changes
|
||||
```
|
||||
|
||||
## **MODELING PRINCIPLES**
|
||||
|
||||
1. **Hierarchical Modulation**: Faster events constrain slower adaptations
|
||||
2. **Bidirectional Coupling**: Every modulation affects and is affected by release events
|
||||
3. **Energy Constraints**: ATP availability gates all processes
|
||||
4. **History Dependence**: Past activity patterns determine current modulation states
|
||||
5. **Context Specificity**: Same modulator can have opposite effects depending on timing/context
|
||||
6. **Redundancy**: Multiple pathways can achieve similar outcomes
|
||||
7. **Trade-offs**: Every enhancement has costs (energy, stability, flexibility)
|
||||
|
||||
This model shows how a simple millisecond release event sits at the center of a rich, multi-timescale regulatory network where each release both responds to and influences modulations across seconds to days, creating a dynamic, self-tuning system for synaptic transmission.
|
||||
@@ -0,0 +1,319 @@
|
||||
# **ATP-Lactate Dynamics: The Ultimate Constraint System**
|
||||
|
||||
## Non modello ATP production al SOMA
|
||||
|
||||
### **The Dual-Source ATP System**
|
||||
|
||||
Neurons have **two complementary ATP production systems** that operate at different timescales:
|
||||
|
||||
#### **1. LOCAL ATP PRODUCTION (Presynaptic Terminal)**
|
||||
|
||||
**Primary Source:** **Mitochondria** within the terminal
|
||||
**Capacity:** Limited (often 1-5 mitochondria per terminal)
|
||||
**Timescale:** Seconds to minutes
|
||||
|
||||
#### **2. DISTAL ATP PRODUCTION (Soma & Axon)**
|
||||
|
||||
**Primary Source:** **Somatic mitochondria** (more abundant)
|
||||
**Transport:** Axonal transport of ATP or ATP precursors
|
||||
**Timescale:** Hours (slow transport)
|
||||
|
||||
You've identified the **fundamental constraint hierarchy**:
|
||||
|
||||
```
|
||||
ATP availability ← Lactate production ← Astrocyte coordination ← Network activity
|
||||
```
|
||||
|
||||
This creates a **energy-based modulation cascade** that constrains everything else.
|
||||
|
||||
## **The Energy Constraint Hierarchy**
|
||||
|
||||
### **Level 1: Millisecond ATP Consumption (Ground Reality)**
|
||||
|
||||
```
|
||||
Processes consuming ATP:
|
||||
- Na⁺/K⁺ pump (40-60% of ATP per AP)
|
||||
- Ca²⁺ pumps (PMCA: ~1 ATP per Ca²⁺)
|
||||
- Vesicle priming (SNARE assembly, NSF ATPase)
|
||||
- Neurotransmitter reloading (v-ATPase)
|
||||
|
||||
ATP consumption per AP: ~20,000 ATP molecules
|
||||
Terminal ATP store: ~10⁸ ATP molecules → ~500 APs until depletion
|
||||
```
|
||||
|
||||
### **Level 2: Second-Minute Lactate Supply (Immediate Energy Politics)**
|
||||
|
||||
```
|
||||
Astrocyte lactate production:
|
||||
- Glutamate uptake → Na⁺ influx → Glycolysis → Lactate
|
||||
- Glycogen breakdown → Lactate
|
||||
- One astrocyte serves ~100,000 synapses
|
||||
|
||||
Lactate transport:
|
||||
- MCT2 transporters on presynaptic terminal
|
||||
- Conversion: Lactate → Pyruvate → ~15 ATP via TCA cycle
|
||||
- Timescale: Seconds for transport, minutes for metabolism
|
||||
```
|
||||
|
||||
### **Level 3: Minute-Hour Network Competition (Energy Economics)**
|
||||
|
||||
```
|
||||
Shared resource problem:
|
||||
- Multiple synapses compete for astrocyte lactate
|
||||
- Active synapses get priority (activity-dependent coupling)
|
||||
- "Energy-rich get richer" feedback
|
||||
|
||||
Astrocyte decision:
|
||||
IF (synapse active AND lactate available) → Supply
|
||||
IF (synapse inactive OR lactate limited) → Reduce supply
|
||||
```
|
||||
|
||||
### **Level 4: Hour-Day Metabolic Adaptation (Energy Infrastructure)**
|
||||
|
||||
```
|
||||
Long-term investments:
|
||||
- More mitochondria at active synapses
|
||||
- Enhanced MCT transporter expression
|
||||
- Astrocyte process extension toward active synapses
|
||||
```
|
||||
|
||||
## **ATP as the Universal Modulator**
|
||||
|
||||
### **ATP Availability Gates ALL Processes:**
|
||||
|
||||
```
|
||||
IF ATP > threshold_X:
|
||||
Process_Y allowed
|
||||
ELSE:
|
||||
Process_Y inhibited or delayed
|
||||
```
|
||||
|
||||
### **Specific ATP Thresholds:**
|
||||
|
||||
```
|
||||
1. High ATP (>80% of max):
|
||||
- All processes operational
|
||||
- Structural growth allowed
|
||||
- High release probability maintained
|
||||
|
||||
2. Medium ATP (30-80%):
|
||||
- Core release functions maintained
|
||||
- Energy-intensive processes limited
|
||||
- No structural growth
|
||||
|
||||
3. Low ATP (<30%):
|
||||
- Release probability decreases
|
||||
- Ca²⁺ clearance impaired
|
||||
- Vesicle recycling slows
|
||||
- Emergency conservation mode
|
||||
```
|
||||
|
||||
## **Simplified ATP-Lactate Model**
|
||||
|
||||
### **Variables:**
|
||||
|
||||
```
|
||||
1. ATP(t): Energy currency at presynapse
|
||||
2. Lactate_ext(t): Extracellular lactate from astrocyte
|
||||
3. Activity_level(t): Recent firing rate
|
||||
4. Neighbor_activity(t): Activity of nearby synapses
|
||||
```
|
||||
|
||||
### **Dynamics:**
|
||||
|
||||
```
|
||||
d(ATP)/dt = Production - Consumption
|
||||
|
||||
Production = k_prod × Lactate_ext × (1 - ATP/ATP_max)
|
||||
Consumption = k_cons × Activity_level + k_baseline
|
||||
|
||||
d(Lactate_ext)/dt = Supply - Uptake - Diffusion
|
||||
|
||||
Supply = k_supply × (Activity_level + α × Neighbor_activity)
|
||||
Uptake = k_uptake × ATP_deficit × Lactate_ext
|
||||
Diffusion = k_diff × (Lactate_ext - Lactate_background)
|
||||
```
|
||||
|
||||
### **The Constraint Equations:**
|
||||
|
||||
```
|
||||
For any process X with ATP requirement R_X:
|
||||
|
||||
IF (ATP > R_X) THEN Process_X proceeds at normal rate
|
||||
ELSE Process_X rate = normal_rate × (ATP/R_X)
|
||||
```
|
||||
|
||||
## **The Critical Insight: Energy-Based Competition**
|
||||
|
||||
### **Within a Single Presynapse:**
|
||||
|
||||
```
|
||||
Processes compete for ATP:
|
||||
- Release vs Clearance vs Recycling vs Growth
|
||||
|
||||
Energy allocation strategy:
|
||||
1. Maintenance first (pumps, basic functions)
|
||||
2. Release second (core mission)
|
||||
3. Recycling third (future capacity)
|
||||
4. Growth last (long-term investment)
|
||||
|
||||
During ATP shortage: Growth → Recycling → Release → Maintenance
|
||||
```
|
||||
|
||||
### **Between Synapses (via Astrocyte):**
|
||||
|
||||
```
|
||||
Synapses compete for lactate:
|
||||
- More active synapses → More glutamate uptake → More lactate production
|
||||
- But: Astrocyte lactate production limited by glucose/glycogen
|
||||
- And: Lactate diffusion favors nearby synapses
|
||||
|
||||
Result: Local "energy hotspots" and "energy deserts"
|
||||
```
|
||||
|
||||
## **Modeling Recommendations**
|
||||
|
||||
### **Option A: Simple ATP Buffer Model**
|
||||
|
||||
```
|
||||
ATP_level = ATP_max × (1 - exp(-t/τ_replenish)) during rest
|
||||
ATP_consumed_per_AP = constant
|
||||
IF ATP_level < threshold: Scale down all energy-intensive processes
|
||||
```
|
||||
|
||||
### **Option B: Lactate-Limited Model**
|
||||
|
||||
```
|
||||
ATP_production_rate = f(Lactate_available)
|
||||
Lactate_available = g(Astrocyte_response, Neighbor_activity)
|
||||
Astrocyte_response = h(Glutamate_uptake, Glycogen_level)
|
||||
```
|
||||
|
||||
### **Option C: Full Energy Competition Model**
|
||||
|
||||
```
|
||||
For each synapse i:
|
||||
dATP_i/dt = Production_i - Consumption_i
|
||||
Production_i = f(Lactate_i, Mitochondria_i)
|
||||
Lactate_i = Shared_pool × (Activity_i / ΣActivity_j)
|
||||
Shared_pool = Astrocyte_output - Total_uptake
|
||||
```
|
||||
|
||||
## **Implications for Plasticity**
|
||||
|
||||
### **The "Energy Check" for Structural Changes:**
|
||||
|
||||
```
|
||||
BDNF says: "Grow this synapse!"
|
||||
Energy system checks:
|
||||
1. Current ATP level?
|
||||
2. Lactate supply reliability?
|
||||
3. Competing energy demands?
|
||||
|
||||
Only if energy sufficient: Growth proceeds
|
||||
If energy marginal: Partial growth or delay
|
||||
If energy insufficient: Growth blocked
|
||||
```
|
||||
|
||||
### **Metaplasticity Rule:**
|
||||
|
||||
```
|
||||
Synapses that consistently receive:
|
||||
- High activity + Adequate lactate → Strengthen (LTP, growth)
|
||||
- High activity + Inadequate lactate → Weaken (LTD, shrinkage)
|
||||
- Low activity + Adequate lactate → Maintain
|
||||
- Low activity + Inadequate lactate → Weaken faster
|
||||
```
|
||||
|
||||
## **Experimental Predictions**
|
||||
|
||||
### **From This Model:**
|
||||
|
||||
1. **Lactate deprivation** should cause:
|
||||
- Faster synaptic depression during trains
|
||||
- Reduced long-term potentiation
|
||||
- Impaired structural plasticity
|
||||
2. **Astrocyte uncoupling** should cause:
|
||||
- Uncoordinated synaptic fatigue
|
||||
- Winner-take-all dynamics between nearby synapses
|
||||
- Impaired network synchronization
|
||||
3. **Metabolic stress** should cause:
|
||||
- Prioritization of inhibitory synapses (energy conservation)
|
||||
- Homeostatic downscaling of excitatory synapses
|
||||
- Altered metaplasticity thresholds
|
||||
|
||||
## **Simplest Implementation for Your Model**
|
||||
|
||||
### **Add These Variables:**
|
||||
|
||||
```python
|
||||
ATP = 1.0 # Normalized ATP level (0 to 1)
|
||||
lactate = 0.5 # Normalized lactate availability (0 to 1)
|
||||
neighbor_activity = 0.0 # Average activity of nearby synapses
|
||||
```
|
||||
|
||||
### **Update Rules:**
|
||||
|
||||
```python
|
||||
def update_energy(dt, activity, neighbor_avg_activity):
|
||||
# Lactate supply depends on local and neighbor activity
|
||||
lactate_supply = 0.1 * (activity + 0.3 * neighbor_avg_activity)
|
||||
lactate = min(1.0, lactate + lactate_supply * dt)
|
||||
|
||||
# ATP production from lactate
|
||||
ATP_production = 0.05 * lactate * (1 - ATP)
|
||||
|
||||
# ATP consumption from activity
|
||||
ATP_consumption = 0.02 * activity
|
||||
|
||||
ATP = max(0, ATP + (ATP_production - ATP_consumption) * dt)
|
||||
|
||||
# Constraint factor for other processes
|
||||
energy_factor = ATP**2 # Square to make low ATP more restrictive
|
||||
|
||||
return ATP, lactate, energy_factor
|
||||
```
|
||||
|
||||
### **Apply Energy Constraints:**
|
||||
|
||||
```python
|
||||
def process_AP_with_energy(Ca_microdomain, RRP_count, ATP):
|
||||
if Ca_microdomain > threshold and RRP_count > 0:
|
||||
# Energy limits release probability
|
||||
P_release_effective = P_release * ATP
|
||||
|
||||
# Energy limits replenishment rate
|
||||
k_replenish_effective = k_replenish * ATP
|
||||
|
||||
# Calculate release...
|
||||
```
|
||||
|
||||
## **The Ultimate Insight**
|
||||
|
||||
**ATP is the ultimate vote in the presynaptic democracy.** It says:
|
||||
|
||||
```
|
||||
"I'm the universal currency. Every process needs me.
|
||||
My availability determines what's possible.
|
||||
My production depends on lactate.
|
||||
Lactate depends on astrocyte coordination.
|
||||
Astrocytes coordinate based on network activity.
|
||||
|
||||
Thus, network-level activity patterns -> Astrocyte lactate distribution ->
|
||||
Presynaptic ATP levels -> Constrain all release decisions and plasticity."
|
||||
```
|
||||
|
||||
This creates a beautiful **circular causality**:
|
||||
|
||||
```
|
||||
Release events → Glutamate → Astrocyte activation → Lactate → ATP →
|
||||
Enable more release events → ...
|
||||
|
||||
BUT with constraints:
|
||||
- Limited astrocyte capacity
|
||||
- Competition between synapses
|
||||
- ATP consumption rates
|
||||
- Lactate diffusion limits
|
||||
```
|
||||
|
||||
Your model now has a **physical grounding** in energy metabolism, which explains why synapses can't just "decide" to be strong - they need the **energy infrastructure** to support that strength. This makes the model both more realistic and more constrained, which paradoxically makes it more powerful for understanding real synaptic function.
|
||||
@@ -0,0 +1,251 @@
|
||||
# **Hierarchical Modulation: Faster Events Constrain Slower Adaptations**
|
||||
|
||||
## **The Core Concept**
|
||||
|
||||
**Hierarchical modulation** means that processes at **faster timescales** (milliseconds to seconds) create **boundaries and constraints** within which slower processes (minutes to days) must operate.
|
||||
|
||||
Think of it like this:
|
||||
|
||||
- **Fast events** (release, Ca²⁺ influx) are the **reality on the ground**
|
||||
- **Slow adaptations** (structural changes, gene expression) are **long-term planning**
|
||||
- **Planning must respect reality** - you can't build a plan that ignores current physical constraints
|
||||
|
||||
## **Concrete Examples**
|
||||
|
||||
### **Example 1: ATP Availability Hierarchy**
|
||||
|
||||
```
|
||||
Fast constraint (ms-s):
|
||||
AP firing → ATP consumption for pumps and priming → ATP depletes
|
||||
|
||||
Slow adaptation (min-days):
|
||||
BDNF says "build more release sites!" (requires ATP for protein synthesis)
|
||||
|
||||
CONSTRAINT:
|
||||
If ATP is depleted from fast events, slow adaptation CANNOT proceed
|
||||
Even if BDNF says "grow," the cell says "I have no energy to build"
|
||||
|
||||
Hierarchy: Energy reality (fast) > Growth plan (slow)
|
||||
```
|
||||
|
||||
### **Example 2: Ca²⁺ Signaling Hierarchy**
|
||||
|
||||
```
|
||||
Fast event (ms):
|
||||
AP → VGCC open → Ca²⁺ influx → Vesicle release
|
||||
|
||||
Slow adaptation (hr):
|
||||
Gene expression program says "make more VGCCs because activity is high"
|
||||
|
||||
CONSTRAINT:
|
||||
The Ca²⁺ signal that triggers gene expression ITSELF depends on current VGCCs
|
||||
No VGCCs now → No Ca²⁺ signal → No trigger for making more VGCCs
|
||||
|
||||
Hierarchy: Current machinery (fast) > Future machinery planning (slow)
|
||||
```
|
||||
|
||||
### **Example 3: Vesicle Pool Hierarchy**
|
||||
|
||||
```
|
||||
Fast depletion (10-100 ms):
|
||||
High-frequency firing → RRP empties → Release stops
|
||||
|
||||
Slow adaptation (hr):
|
||||
Activity pattern says "we need bigger vesicle pools"
|
||||
|
||||
CONSTRAINT:
|
||||
While pools are being enlarged (slow), release is limited by CURRENT pool size (fast)
|
||||
The system cannot release vesicles that don't exist yet
|
||||
|
||||
Hierarchy: Current supply (fast) > Future supply planning (slow)
|
||||
```
|
||||
|
||||
## **Why This Hierarchy Exists**
|
||||
|
||||
### **Physical Constraints:**
|
||||
|
||||
1. **Causality**: You cannot use tomorrow's proteins today
|
||||
2. **Energy**: Future plans require current energy investment
|
||||
3. **Information**: Slow systems need fast events to provide data
|
||||
4. **Safety**: Fast systems must prevent damage while slow systems adapt
|
||||
|
||||
### **Temporal Asymmetries:**
|
||||
|
||||
```
|
||||
Building (slow) >> Using (fast)
|
||||
Example: It takes hours to make a new VGCC, but milliseconds to use it
|
||||
Therefore: Current usage patterns constrain future building plans
|
||||
```
|
||||
|
||||
## **The Constraint Pyramid**
|
||||
|
||||
```
|
||||
LEVEL 4: DAYS (Architectural planning)
|
||||
"We should redesign the entire synapse structure"
|
||||
↳ Constrained by ↓
|
||||
|
||||
LEVEL 3: HOURS (Construction projects)
|
||||
"Let's build more VGCCs and vesicles"
|
||||
↳ Constrained by ↓
|
||||
|
||||
LEVEL 2: MINUTES (Resource allocation)
|
||||
"We need more ATP and proteins"
|
||||
↳ Constrained by ↓
|
||||
|
||||
LEVEL 1: SECONDS (Immediate operations)
|
||||
"We're depleting ATP and vesicles now!"
|
||||
↳ Constrained by ↓
|
||||
|
||||
GROUND LEVEL: MILLISECONDS (Reality)
|
||||
"Current AP firing requires X ATP, releases Y vesicles"
|
||||
```
|
||||
|
||||
## **How Constraints Propagate Upward**
|
||||
|
||||
### **Constraint Chain: Energy Example**
|
||||
|
||||
```
|
||||
GROUND (ms): AP fires → consumes ATP
|
||||
LEVEL 1 (s): ATP depletes → AMPK activates
|
||||
LEVEL 2 (min): AMPK says "stop non-essential processes"
|
||||
LEVEL 3 (hr): Protein synthesis slows → no new VGCCs
|
||||
LEVEL 4 (days): Structural growth postponed
|
||||
|
||||
Result: Fast energy consumption constrains slow growth
|
||||
```
|
||||
|
||||
### **Constraint Chain: Ca²⁺ Example**
|
||||
|
||||
```
|
||||
GROUND (ms): AP → Ca²⁺ influx → buffers saturate
|
||||
LEVEL 1 (s): Ca²⁺ accumulates → pumps overwhelmed
|
||||
LEVEL 2 (min): High Ca²⁺ → calcineurin activation
|
||||
LEVEL 3 (hr): Calcineurin → NFAT → gene expression changes
|
||||
LEVEL 4 (days): Synaptic scaling adjusts
|
||||
|
||||
Result: Fast Ca²⁺ dynamics constrain slow transcriptional responses
|
||||
```
|
||||
|
||||
## **The Two-Way Street (With Traffic Lights)**
|
||||
|
||||
While fast events constrain slow adaptations, there's also **reverse influence**, but with a **delay**:
|
||||
|
||||
### **Forward Constraint (Fast → Slow):**
|
||||
|
||||
- **Speed**: Immediate
|
||||
- **Strength**: Strong (physical reality)
|
||||
- **Example**: No ATP now → No growth now
|
||||
|
||||
### **Reverse Influence (Slow → Fast):**
|
||||
|
||||
- **Speed**: Delayed (hours to days)
|
||||
- **Strength**: Gradual (changes parameters)
|
||||
- **Example**: BDNF yesterday → More VGCCs today → More Ca²⁺ now
|
||||
|
||||
### **The Asymmetry:**
|
||||
|
||||
```
|
||||
Fast events can VETO slow plans immediately
|
||||
Slow plans can only SUGGEST future fast events
|
||||
```
|
||||
|
||||
## **Implications for the Model**
|
||||
|
||||
### **For Each Release Event:**
|
||||
|
||||
1. **The event occurs** within current constraints (VGCCs available, vesicles primed, ATP present)
|
||||
2. **The event generates signals** (Ca²⁺, glutamate, ATP consumption)
|
||||
3. **These signals constrain** what slow adaptations can occur
|
||||
4. **But they also inform** what slow adaptations should occur
|
||||
|
||||
### **Modeling Rule:**
|
||||
|
||||
When simulating, you must check:
|
||||
|
||||
```
|
||||
IF (slow adaptation requires resource X)
|
||||
THEN (current level of X must support it)
|
||||
ELSE (adaptation delayed until X available)
|
||||
```
|
||||
|
||||
## **Practical Examples in Our Model**
|
||||
|
||||
### **VGCC Expression Increase (Slow) Constrained by:**
|
||||
|
||||
1. **Current VGCC function** (fast): If all VGCCs are internalized, no Ca²⁺ signal to trigger expression
|
||||
2. **ATP availability** (medium): Protein synthesis requires ATP
|
||||
3. **Protein synthesis capacity** (medium): Ribosomes, tRNA availability
|
||||
4. **Trafficking machinery** (medium): Can new VGCCs reach membrane?
|
||||
|
||||
### **RP Pool Expansion (Slow) Constrained by:**
|
||||
|
||||
1. **Current vesicle recycling** (fast): Are vesicles being recycled to feed current demand?
|
||||
2. **Membrane availability** (medium): Adding vesicles requires membrane
|
||||
3. **Neurotransmitter synthesis** (medium): Can we fill new vesicles?
|
||||
4. **Docking site availability** (slow): New vesicles need places to dock
|
||||
|
||||
### **Mitochondrial Biogenesis (Slow) Constrained by:**
|
||||
|
||||
1. **Current ATP/ADP ratio** (fast): Energy status determines if biogenesis can proceed
|
||||
2. **Current mitochondrial function** (medium): Dysfunctional mitochondria can't replicate well
|
||||
3. **Oxidative stress** (medium): ROS can damage mitochondrial DNA
|
||||
4. **Building blocks** (medium): Lipids, proteins for new mitochondria
|
||||
|
||||
## **The "Reality Check" Principle**
|
||||
|
||||
Every slow adaptation plan gets a **reality check** from fast events:
|
||||
|
||||
```
|
||||
Slow plan: "Let's make this synapse stronger!"
|
||||
Reality checks:
|
||||
1. Fast: "Do we have ATP for synthesis?" (energy check)
|
||||
2. Fast: "Is Ca²⁺ signaling intact?" (information check)
|
||||
3. Fast: "Are vesicles being released?" (function check)
|
||||
4. Fast: "Is the terminal healthy?" (safety check)
|
||||
|
||||
Only if all checks pass → Slow plan proceeds
|
||||
```
|
||||
|
||||
## **Why This Design is Optimal**
|
||||
|
||||
### **Biological Wisdom:**
|
||||
|
||||
1. **Prevents overcommitment**: Don't build if you can't maintain
|
||||
2. **Ensures relevance**: Adapt only to real, measured needs
|
||||
3. **Maintains stability**: Fast systems keep things running while slow systems plan
|
||||
4. **Optimizes resources**: Invest only when conditions are right
|
||||
|
||||
### **Evolutionary Advantage:**
|
||||
|
||||
- **Energy efficiency**: Don't waste energy on unnecessary adaptations
|
||||
- **Robustness**: Fast systems handle immediate threats
|
||||
- **Adaptability**: Slow systems can still change things fundamentally
|
||||
- **Balance**: Neither fast nor slow dominates completely
|
||||
|
||||
## **Summary: The Temporal Chain of Command**
|
||||
|
||||
In the presynapse:
|
||||
|
||||
**Fast events (ms-s) are like front-line soldiers:**
|
||||
|
||||
- They face immediate reality
|
||||
- They have limited resources
|
||||
- They must make instant decisions
|
||||
- Their situation dictates what headquarters can plan
|
||||
|
||||
**Slow adaptations (min-days) are like military headquarters:**
|
||||
|
||||
- They make long-term plans
|
||||
- They allocate resources
|
||||
- They build infrastructure
|
||||
- But they can only plan within what front-line reports as possible
|
||||
|
||||
**The hierarchy is:**
|
||||
|
||||
1. **Immediate survival** (fast) comes first
|
||||
2. **Medium-term optimization** comes second
|
||||
3. **Long-term restructuring** comes third
|
||||
|
||||
**But crucially:** Good slow adaptations can improve future fast events, creating a positive upward spiral when conditions allow.
|
||||
|
||||
This is why in our model, we must always ask: **"Given what's happening NOW at millisecond scale, what CAN we change at hour scale?"** The answer is always constrained by current reality.
|
||||
@@ -0,0 +1,129 @@
|
||||
Yes — and this is actually the most important calcium process on the postsynaptic side, because it is the mechanism behind **synaptic plasticity** (LTP and LTD). You are pointing at something that is missing from the current postsynaptic model entirely.
|
||||
|
||||
---
|
||||
|
||||
**What is happening biologically**
|
||||
|
||||
The postsynapse has its own calcium dynamics, completely separate from the presynapse. The key player is the **NMDA receptor** — a special type of glutamate receptor that is both ligand-gated (requires NT to bind) AND voltage-gated (requires the membrane to be depolarised to remove a magnesium block). This dual requirement makes it a **coincidence detector**: it only opens fully when NT arrives AND the postsynaptic membrane is already depolarised.
|
||||
|
||||
The depolarisation can come from two sources:
|
||||
|
||||
**Forward signal** — NT from the presynapse depolarises V_post via AMPA receptors, which then unblocks NMDA receptors and lets Ca²⁺ in.
|
||||
|
||||
**Backpropagating AP (bAP)** — when the postsynaptic neuron fires its own action potential, that signal travels not only forward down the axon but also backward up the dendrites. When this bAP arrives at the synapse at the same time as presynaptic NT, the NMDA receptor sees both conditions simultaneously and opens maximally.
|
||||
|
||||
---
|
||||
|
||||
**The coincidence detection logic**
|
||||
|
||||
```
|
||||
NT arrives (presynapse fires) → AMPA opens → V_post rises
|
||||
bAP arrives (postsynapse fires) → membrane depolarised
|
||||
Both together at the same time → NMDA fully open → Ca2+_post large surge
|
||||
NT alone, no bAP → NMDA partially open → Ca2+_post small
|
||||
bAP alone, no NT → NMDA blocked (no NT) → Ca2+_post minimal
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**What Ca²⁺ level in the postsynapse controls**
|
||||
|
||||
Postsynaptic Ca²⁺ (`Ca_post`) drives three things depending on its level:
|
||||
|
||||
| Ca_post level | Outcome | Mechanism |
|
||||
|---------------|---------------------|----------------------------------------------------|
|
||||
| low | LTD (weakening) | activates phosphatases that remove AMPA receptors |
|
||||
| medium | no change | neither pathway threshold crossed |
|
||||
| high | LTP (strengthening) | activates kinases (CaMKII) that add AMPA receptors |
|
||||
| very high | eCB synthesis | triggers retrograde suppression of presynapse |
|
||||
|
||||
The current model already has the eCB branch (very high Ca_post → eCB). What is missing is the Ca_post variable itself and the LTP/LTD branches.
|
||||
|
||||
---
|
||||
|
||||
**Proposed variables to add**
|
||||
|
||||
```python
|
||||
# -----------------------------------------------------------------------
|
||||
# POSTSYNAPTIC Ca2+ DYNAMICS
|
||||
# -----------------------------------------------------------------------
|
||||
|
||||
# -- NMDA receptor --
|
||||
k_NMDA_bind = 0.03 # /ms - NMDA conductance per unit NT when unblocked
|
||||
Mg_block = 1.0 # magnesium block factor (0=fully blocked, 1=fully open)
|
||||
# removed by V_post depolarisation and bAP
|
||||
V_NMDA_threshold = 0.3 # V_post level at which Mg block begins to lift
|
||||
# below this NMDA is nearly fully blocked
|
||||
|
||||
# -- bAP --
|
||||
bAP_active = False # flag: postsynaptic neuron has fired (set externally)
|
||||
bAP_amplitude = 1.0 # normalised bAP depolarisation contribution
|
||||
tau_bAP = 3.0 # ms - bAP decay time constant at the synapse
|
||||
# bAP attenuates as it travels up the dendrite
|
||||
bAP_state = 0.0 # continuous bAP depolarisation (mirrors V_pre_state)
|
||||
|
||||
# -- Postsynaptic Ca2+ --
|
||||
Ca_post = 0.0 # free Ca2+ in postsynaptic spine
|
||||
# driven by NMDA opening and bAP
|
||||
k_Ca_post_decay = 0.05 # /ms - Ca_post clearance rate
|
||||
# postsynapse has its own pumps (PMCA, NCX equivalents)
|
||||
|
||||
# -- Plasticity thresholds --
|
||||
Ca_post_LTD = 0.3 # Ca_post below this → LTD if sustained
|
||||
Ca_post_LTP = 0.7 # Ca_post above this → LTP if sustained
|
||||
Ca_post_eCB = 0.9 # Ca_post above this → eCB synthesis
|
||||
|
||||
# -- Plasticity state --
|
||||
AMPA_density = 1.0 # normalised AMPA receptor density (0 -> 2)
|
||||
# LTP increases this, LTD decreases it
|
||||
# feeds back into receptor_conductance
|
||||
tau_plasticity = 30_000.0 # ms - plasticity integration window (~30 s)
|
||||
Ca_post_trace = 0.0 # slow integrator of Ca_post, drives plasticity
|
||||
# analogous to Tr_Ca on the presynaptic side
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Proposed behaviors**
|
||||
|
||||
```
|
||||
— ms (postsynapse, additions):
|
||||
|
||||
- bAP arrives → bAP_state jumps to bAP_amplitude, decays with tau_bAP
|
||||
(mirrors V_pre_state / V_pre_peak on the presynaptic side)
|
||||
|
||||
- Mg block removal: Mg_block = f(V_post + bAP_state)
|
||||
low voltage → Mg_block ≈ 1 (fully blocked, no Ca2+ entry)
|
||||
high voltage → Mg_block ≈ 0 (fully open, maximal Ca2+ entry)
|
||||
|
||||
- NMDA conductance: NMDA_conductance = k_NMDA_bind * NT_cleft * (1 - Mg_block)
|
||||
requires BOTH NT (ligand gate) AND depolarisation (voltage gate)
|
||||
this is the coincidence detection step
|
||||
|
||||
- Ca_post rises with NMDA_conductance each ms
|
||||
- Ca_post decays with k_Ca_post_decay each ms (postsynaptic pumps)
|
||||
|
||||
- Ca_post_trace integrates Ca_post (slow, analogous to Tr_Ca)
|
||||
|
||||
— seconds (postsynapse, additions):
|
||||
|
||||
- eCB synthesis now driven by Ca_post_trace > Ca_post_eCB
|
||||
(replaces V_post_history as the eCB trigger — more accurate biologically
|
||||
because it is Ca2+ in the spine that actually synthesises eCB,
|
||||
not voltage per se)
|
||||
|
||||
— mins (postsynapse, additions):
|
||||
|
||||
- if Ca_post_trace sustained below Ca_post_LTD → AMPA_density decreases (LTD)
|
||||
- if Ca_post_trace sustained above Ca_post_LTP → AMPA_density increases (LTP)
|
||||
- AMPA_density feeds back into receptor_conductance ceiling:
|
||||
effective receptor_conductance max = N_receptors * AMPA_density
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Why this closes an important loop**
|
||||
|
||||
Without postsynaptic Ca²⁺ the model has no plasticity — the synapse behaves identically after 10 minutes of activity as it did at the start. Adding `Ca_post` with the coincidence detection logic means the synapse now has a **history** in the biological sense: repeated co-activation of pre and post strengthens it (LTP), one-sided activity weakens it (LTD). This is the postsynaptic equivalent of the presynaptic metabolic cascade — a slow, activity-dependent recalibration of the synapse's operating point, but driven by learning rather than protection.
|
||||
|
||||
The bAP is also what makes the eCB synthesis biologically accurate. Currently eCB is triggered by V_post (voltage). But the actual synthesis of endocannabinoids in the spine is triggered by high Ca²⁺ in the spine, which requires NMDA opening, which requires coincidence. So by adding `Ca_post`, the eCB trigger becomes mechanistically correct: it is not just "the postsynapse is depolarised" but "the postsynapse is receiving coordinated pre and post activity", which is a much more specific and meaningful signal for the presynapse to receive.
|
||||
@@ -0,0 +1,97 @@
|
||||
Looking at what we have just specified, the postsynapse also has three loops — but they are organised around different problems than the presynapse.
|
||||
|
||||
---
|
||||
|
||||
**The NT detection loop**
|
||||
|
||||
This is the direct counterpart of the presynaptic NT loop, but from the receiving side. NT arrives in the cleft, binds AMPA receptors, generates V_post, and V_post drives the postsynaptic response. The loop closes through desensitization: sustained NT exposure progressively silences the receptors, reducing the response to further NT even while it is still present. When NT clears (presynapse goes quiet), desensitization recovers and receptors become available again. The timescale is milliseconds to seconds — fast enough to track individual spikes, slow enough to integrate burst activity. This loop is entirely local to the postsynapse and requires no signal from outside except NT_cleft.
|
||||
|
||||
---
|
||||
|
||||
**The Ca²⁺ coincidence loop**
|
||||
|
||||
This is the postsynaptic equivalent of the presynaptic Ca²⁺ loop, but with a fundamentally different trigger. Presynaptic Ca²⁺ enters whenever VGCCs open — which happens on every AP. Postsynaptic Ca²⁺ enters through NMDA receptors only when two conditions are simultaneously true: NT is present in the cleft (presynapse just fired) AND the membrane is depolarised (either from accumulated AMPA activation or from a backpropagating AP). This dual requirement makes Ca_post a detector of coordinated activity rather than just a measure of input rate. The loop closes through the Ca_post trace: sustained high Ca_post potentiates the synapse (LTP, more AMPA receptors), sustained low Ca_post depresses it (LTD, fewer AMPA receptors), and the changed receptor density feeds back into how strongly the next NT release activates V_post. The timescale spans milliseconds (NMDA opening) to minutes (plasticity expression).
|
||||
|
||||
---
|
||||
|
||||
**The retrograde signalling loop**
|
||||
|
||||
This loop has no presynaptic equivalent — it is unique to the postsynapse because it is the only signal that crosses back from post to pre. When Ca_post rises above the eCB threshold (sustained coincident activity), the postsynapse synthesises endocannabinoids and releases them retrogradely. eCB travels back across the cleft and suppresses presynaptic VGCC conductance, reducing Ca²⁺ influx and therefore NT release. The loop closes when reduced NT release lowers Ca_post, which eventually reduces eCB synthesis, allowing the presynaptic brake to lift. The timescale is seconds to tens of seconds — slower than the NT detection loop, faster than plasticity. This is the loop that connects the two sides of the synapse and makes the tripartite system a genuine closed system rather than two independent models running in parallel.
|
||||
|
||||
---
|
||||
|
||||
**How the three postsynaptic loops relate to the three presynaptic loops**
|
||||
|
||||
| Presynaptic | Postsynaptic | Shared variable |
|
||||
|-------------|----------------------------|----------------------|
|
||||
| NT loop | NT detection loop | NT_cleft |
|
||||
| Ca²⁺ loop | Ca²⁺ coincidence loop | — (independent Ca²⁺) |
|
||||
| ATP loop | retrograde signalling loop | eCB_level |
|
||||
|
||||
The NT loop pair is the primary communication channel — pre releases, post detects. The Ca²⁺ loops are parallel but independent — each side manages its own calcium for its own purposes. The ATP/retrograde pair is the feedback channel — post reports back to pre when activity is excessive. Together the six loops form the complete tripartite system, with the cleft and the eCB signal as the two bridges between the two neurons.
|
||||
|
||||
---
|
||||
|
||||
Yes — and in ways that are structurally similar to the presynapse but with different priorities.
|
||||
|
||||
---
|
||||
|
||||
**Where ATP is consumed in the postsynapse**
|
||||
|
||||
**Na/K-ATPase recharge** is the same dominant cost as in the presynapse. Every postsynaptic potential — every time V_post rises — ion gradients are disturbed and the Na/K-ATPase must restore them. At high firing rates this is the largest ATP drain, identical in mechanism to the presynaptic side.
|
||||
|
||||
**Ca²⁺ clearance from the spine** is the direct equivalent of PMCA and SERCA in the presynapse. After NMDA-driven Ca_post rises, the spine must pump Ca²⁺ back out. The postsynaptic spine has its own PMCA on the plasma membrane and its own SERCA loading a small ER compartment (the spine apparatus). Both are ATP-dependent. This is actually more critical in the postsynapse than the presynapse in one respect: if Ca_post clearance fails, the spine cannot distinguish a coincidence signal from background noise — the Ca²⁺ threshold logic for LTP vs LTD collapses entirely.
|
||||
|
||||
**Plasticity machinery** is an ATP cost that has no presynaptic equivalent. LTP requires physical insertion of new AMPA receptors into the membrane — a process driven by CaMKII phosphorylation, actin cytoskeleton remodelling, and vesicle trafficking, all of which consume ATP. LTD requires the reverse: receptor internalisation via endocytosis, also ATP-dependent. The plasticity loop is therefore metabolically expensive in a way that scales not with firing rate but with the rate of synaptic change.
|
||||
|
||||
**NMDA receptor maintenance** — the receptor itself requires ATP for regulatory phosphorylation that controls its sensitivity and trafficking. Under energy stress, NMDA receptors are among the first to be downregulated.
|
||||
|
||||
---
|
||||
|
||||
**How ATP failure affects the postsynapse differently from the presynapse**
|
||||
|
||||
In the presynapse, ATP failure produces a clean, protective outcome: the synapse silences itself through CDI lock-out, which prevents excitotoxic Ca²⁺ overload. The silence is the protection.
|
||||
|
||||
In the postsynapse, ATP failure is more dangerous rather than protective. The sequence is:
|
||||
|
||||
```
|
||||
ATP falls
|
||||
→ Ca2+ clearance slows (PMCA/SERCA fail)
|
||||
→ Ca_post stays elevated between coincidence events
|
||||
→ Ca_post threshold for LTP is permanently crossed
|
||||
→ runaway LTP — synapse strengthens uncontrollably
|
||||
→ NMDA receptors stay open longer (no ATP to phosphorylate/regulate them)
|
||||
→ more Ca2+ entry
|
||||
→ positive feedback loop
|
||||
→ excitotoxic Ca2+ overload in the spine
|
||||
→ spine collapse and cell death
|
||||
```
|
||||
|
||||
This is the postsynaptic excitotoxicity cascade — the mirror image of the presynaptic one but with the opposite outcome. The presynapse protects itself by going silent. The postsynapse is vulnerable precisely because it has no equivalent of CDI — there is no mechanism that uses elevated Ca_post to shut down Ca_post entry. The NMDA receptor does have a weak Ca²⁺-dependent inactivation, but it is far less effective than presynaptic CDI.
|
||||
|
||||
---
|
||||
|
||||
**Should ATP be in the postsynaptic model?**
|
||||
|
||||
At the same level of abstraction as the presynapse, yes — but the loop looks different:
|
||||
|
||||
```
|
||||
— ms (postsynapse, ATP):
|
||||
- ATP cost charged per bAP (Na/K-ATPase recharge)
|
||||
- ATP cost charged per unit Ca_post cleared (PMCA/SERCA)
|
||||
|
||||
— seconds (postsynapse, ATP):
|
||||
- pump_scale_post = Hill(ATP_level_post)
|
||||
- Ca_post clearance gated by pump_scale_post
|
||||
- if pump_scale_post low → Ca_post stays elevated → eCB threshold
|
||||
crossed even without genuine coincidence → false retrograde signal
|
||||
|
||||
— mins (postsynapse, ATP):
|
||||
- ATP_level_post set by local glucose supply (astrocyte delivers to both sides)
|
||||
- if low → plasticity machinery slows → LTP/LTD expression delayed or absent
|
||||
- if critically low → runaway Ca_post → excitotoxicity cascade
|
||||
```
|
||||
|
||||
The most important addition this enables is **shared metabolic vulnerability**: the astrocyte supplies glucose to both the presynapse and the postsynapse. Under sustained high-frequency firing, both sides are drawing from the same supply. The presynapse silences first (CDI is an efficient brake), which paradoxically protects the postsynapse — reduced NT release means less NMDA activation means less Ca_post means less postsynaptic ATP demand. The presynaptic ATP loop and the postsynaptic ATP loop are therefore coupled through the astrocyte's glucose budget, and the presynaptic silence functions as a protective brake for both sides simultaneously.
|
||||
|
||||
---
|
||||
@@ -0,0 +1,85 @@
|
||||
import os
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
def generate_architectural_graph(directory, output_file):
|
||||
# Setup node definitions and edges
|
||||
node_types = {} # entity_name -> type (container/context/task)
|
||||
edges = []
|
||||
|
||||
# Regex to extract Gen blocks
|
||||
block_re = re.compile(r"```Gen\s*(.*?)\s*```", re.DOTALL)
|
||||
|
||||
for md_file in Path(directory).rglob("*.md"):
|
||||
content = md_file.read_text()
|
||||
blocks = block_re.findall(content)
|
||||
|
||||
for block in blocks:
|
||||
lines = [l.strip() for l in block.split('\n') if l.strip()]
|
||||
props = {}
|
||||
current_entity = None
|
||||
current_type = None
|
||||
|
||||
# Parse lines for entity definition and properties
|
||||
for line in lines:
|
||||
if ':' in line:
|
||||
key, val = line.split(':', 1)
|
||||
key, val = key.strip(), val.strip()
|
||||
props[key] = val
|
||||
|
||||
if key in ['comprehension', 'modulator', 'container', 'context', 'task']:
|
||||
current_entity = val
|
||||
current_type = key
|
||||
node_types[current_entity] = current_type
|
||||
|
||||
if not current_entity: continue
|
||||
|
||||
# Morphism Logic: Contained By (Parent <- Child)
|
||||
if 'contained_by' in props:
|
||||
parent = props['contained_by']
|
||||
edges.append((parent, current_entity, "contains"))
|
||||
|
||||
# Morphism Logic: Expands (Parent -> Child)
|
||||
if 'expands' in props:
|
||||
contains_val = props['expands']
|
||||
match = re.match(r"(\d+x)?\s*(.*)", contains_val)
|
||||
label = match.group(1) if match.group(1) else "expands"
|
||||
child = match.group(2)
|
||||
edges.append((current_entity, child, label))
|
||||
|
||||
# Build Mermaid syntax
|
||||
mermaid_lines = ["graph TD"]
|
||||
|
||||
# Define Nodes with Types (Styling)
|
||||
# Containers = Rectangles [], Contexts = Hexagons {{}}, Tasks = Ovals (())
|
||||
for name, n_type in node_types.items():
|
||||
if n_type == 'comprehension':
|
||||
mermaid_lines.append(f' {name}["comprehension: {name}"]')
|
||||
elif n_type == 'modulator':
|
||||
mermaid_lines.append(f' {name}["modulator: {name}"]')
|
||||
elif n_type == 'container':
|
||||
mermaid_lines.append(f' {name}["container: {name}"]')
|
||||
elif n_type == 'context':
|
||||
mermaid_lines.append(f' {name}{{{{"context: {name}"}}}}')
|
||||
elif n_type == 'task':
|
||||
mermaid_lines.append(f' {name}(("task: {name}"))')
|
||||
|
||||
|
||||
# Add Edges
|
||||
for source, target, label in edges:
|
||||
# Determine relationship type string for the arrow
|
||||
s_type = node_types.get(source, "unknown")
|
||||
t_type = node_types.get(target, "unknown")
|
||||
# Example: container tre -- contains --> task bbgg
|
||||
mermaid_lines.append(f' {source} -- "{label}" --> {target}')
|
||||
|
||||
# Save to file
|
||||
with open(output_file, "w") as f:
|
||||
f.write("# Architectural Hierarchy Graph\n\n")
|
||||
f.write("```mermaid\n")
|
||||
f.write("\n".join(mermaid_lines))
|
||||
f.write("\n```")
|
||||
|
||||
if __name__ == "__main__":
|
||||
generate_architectural_graph("..", "architecture_graph.mmd")
|
||||
print("Success: architecture_graph.md has been generated.")
|
||||
Reference in New Issue
Block a user