[Eeglablist] Open online discussion: How Do Cable Theory and AMPA/GABA Balance Compare in Their Contributions to 1/f?

[Евгений Машеров]

This is wonderful.
I tried to devise an experiment that would allow me to choose between the hypotheses. Due to my laziness, I asked DeepSeek about it, but he suggested what was probably a wonderful plan, but it required methods unavailable to me (perhaps I could interest colleagues from another institute, but the chances are slim).
Here's his advice:
"Excellent question. This moves the discussion from theory to experimental testing.

The main problem is that in real EEG/LFP, all four mechanisms act simultaneously. The task is not to choose "the one true one" but to estimate the relative contribution of each in a specific context (type of activity, brain region, state, species, age).

Below is one "clean" experiment (or type of analysis) for testing the primacy of each hypothesis. The gold standard is to compare model predictions with data, manipulating only one parameter at a time.

1. Testing hypothesis 2.1 (spatial averaging / source size)
What experiment: Simultaneous scalp EEG + intracortical LFP (high-density linear array) in the same animal/human (intraoperatively).

Logic:

LFP registers local sources with a radius of ~0.5–2 mm — here, the mutual cancellation between spatially separated generators is minimal.

Scalp EEG is the result of averaging over areas of several cm².

Prediction: If spatial averaging is the main contributor to the 1/f slope:

In LFP, the spectral slope will be significantly flatter (closer to 1/f⁰…¹) compared to EEG.

The difference in slope (EEG minus LFP) will be positive and correlate with the size of the coherent region, estimated via cross-coherence on LFP.

Control: If there is no difference, then the 1/f on the scalp is mainly shaped by local membrane/synaptic mechanisms (2.2, 2.3).

2. Testing hypothesis 2.2 (cable theory / dendritic filtering)
What experiment: Patch-clamp from the soma + simultaneous activation of distal and proximal dendritic synapses (optogenetics or focal glutamate stimulation) in a single neuron in slice / in vivo.

Logic:

Stimulate proximal synapses (near the soma) — record EPSP at the soma.

Stimulate distal synapses (on the same neuron) — record EPSP at the soma.

Compare the spectra of these two response types.

Prediction: If cable filtering is significant:

EPSPs from distal inputs will have a steeper 1/f roll-off (less high-frequency power) compared to proximal ones.

The peak amplitude (20–50 Hz) will be significantly reduced.

Key experiment: Do the same in the presence of separate AMPA and GABA-A blockers to eliminate their kinetics. The remaining difference is purely passive filtering.

Quantitative check: Compare with a cable model (Rall, NEURON) — match the spectral slope at different distances.

3. Testing hypothesis 2.3 (AMPA vs GABA-A kinetics)
What experiment: Dynamic pharmacological manipulation (and optogenetics with different kinetics) at the same LFP site.

Logic:

Block GABA-A (bicuculline) — get predominance of fast AMPA-EPSPs.

Block AMPA (CNQX) — leave slow GABA-A-IPSPs.

Then restore the original balance.

Compare the 1/f slope (2–100 Hz range).

Prediction (per Gao & Donoghue 2016):

AMPA-dominant → flatter spectrum (weak 1/f dependence).

GABA-A-dominant → steeper spectrum (strong 1/f dependence).

Critical control: Simultaneously monitor spatial coherence (to rule out mechanism 2.1) and vary stimulation distance from soma (to rule out 2.2).

If effect exists — receptor kinetics make an independent contribution.
If no effect — the 1/f slope is not primarily determined by kinetics (unlikely but possible).

4. Testing hypothesis 2.4 (slow ion concentration / open-loop current)
What experiment: Long-duration (>10–20 min) recording of LFP + ion-selective microelectrodes (K⁺, Ca²⁺) in cortex without external stimulation (spontaneous activity).

Logic:

Standard microelectrodes record high-frequency LFP (0.5–200 Hz).

Ion-selective electrodes give extracellular K⁺ concentration with ~0.1–1 Hz temporal resolution.

Prediction: If slow ionic shifts affect 1/f:

The spectral slope in the 0.05–1 Hz range will correlate with K⁺ concentration.

When the "closed-loop" current is disrupted (e.g., via Na⁺-K⁺-ATPase blockade with ouabain, or during hypoxia), the 1/f slope will first change, then return with a time constant of tens of seconds to minutes.

Key test: Look at 40 Hz ASSR in two groups (red vs blue, as in your example) — if the difference in 1/f is at frequencies <<1 Hz but not at >10 Hz, that supports 2.4. If the difference is at high frequencies, that points to 2.1–2.3.

Summary: which single experiment is the most powerful for disentangling these?
There isn't one. But there is a combinatorial protocol that could yield a weighted contribution:

Step	Manipulation	Tests
1	Scalp EEG vs intracortical LFP	2.1
2	Proximal vs distal responses (optogenetics)	2.2
3	Pharmacology (CNQX + bicuculline) at same LFP site	2.3
4	Long-term recording + ion-selective electrodes + ouabain	2.4
If after step 2 (distance control) the pharmacological effect remains — 2.3 is real.
If after step 1 (accounting for source size) the 1/f almost disappears — 2.1 is the main contributor.
If slope changes appear only in the very low-frequency range (<<1 Hz) — that's 2.4.

This is a complex experiment, but it is already being partially performed in neurophysiology using optogenetics and high-density probe arrays."

In the meantime, I'll try to come up with a way to differentiate between the two using existing EEG recordings of people in different states. I'm not sure it will work, but maybe it will be informative.

Eugen Masherov



> Hello 1/f people,
> 
> Gin Estrella Cruz and I will meet online to discuss whether it is possible
> to quantitatively compare the contributions of cable theory and AMPA/GABA
> (i.e., E/I) balance to EEG's 1/f power distribution. At this point, I do
> not know whether such a comparison is feasible. Anyone is welcome to join
> if the timing works, I'd love to hear your opinions and advice. Since there
> is a 12-hour time difference between us, the meeting time is a bit awkward.
> 
> *Time*: Apr 15, 2026 08:00 AM Eastern Time (US and Canada, EDT)
> *Place*:
> https://urldefense.com/v3/__https://ucsd.zoom.us/j/3026035468?pwd=bQg61iUIe0AHfDQ5QSipOSEXi4FzCs.1&omn=97531862557__;!!Mih3wA!FZmTaWWKaDH-9ElW5sUmquTyS4E1TAy3KcNOWuur9efjaocNW7F7lNBCzhmS1d1FL9tA6L-gHGo2EbexRI-rf5m6dcE$
> *Meeting ID*: 302 603 5468
> *Password*: 1overF
> 
> To provide a bit of background, since the publication of the original FOOOF
> paper, the idea that a flatter or steeper 1/f slope in the EEG power
> spectral density reflects excitatory/inhibitory states appears to have been
> overgeneralized. However, the 1/f-like behavior of EEG is an intrinsic
> property predicted by cable theory. If there are two contributors (at
> least) to 1/f-ness, they should be compared quantitatively to determine
> which contributes more.
> 
> Makoto
> _______________________________________________
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu or visit https://sccn.ucsd.edu/mailman/listinfo/eeglablist .