Knock down a gene, or block a current. Watch the heartbeat change.

A cross-scale causal model of a human iPSC-cardiomyocyte. Knock down a gene with CRISPRi, or switch to drug-block mode and apply a percent block to an ion current. Either way the action potential recomputes in mV and ms on Kernik-Clancy 2019, published and validated. Each channel case moves the action potential in the literature direction.

CRISPRi knockdown
baseline perturbed other knockdown levels
upstroke (zoom)
The first ~10 ms of the beat, foot-aligned, at 0.1 ms resolution. The faint line is the baseline upstroke; the bright line is the current level. A slower upstroke (lower dV/dt max) is a shallower rising edge. This is a single iPSC-cardiomyocyte upstroke. It is not tissue conduction or an ECG.
APD90 = action-potential duration to 90% repolarization. Cells beat spontaneously; no external pacing. Dashed lines mark peak, the 90%-repolarization level, and the maximum diastolic potential (MDP).
closed-loop discovery

A mechanistic prior finds every active perturbation in far fewer experiments than random, because the model scores the next experiment. A DEG-count proxy does worse than random. This is expected: the loudest perturbations are ion channels, network leaves that move no other gene, so a DEG-count proxy ranks them last. Fewer experiments is better.

Ground truth here is the model's own forward simulation, so this shows the acquisition approach is internally consistent, not real-world predictive skill. That is a wet-lab question.
inverse read · trace in, causes out

The ranker scores every conductance-change hypothesis on its grid from five biomarkers: APD90, APD50, MDP, dV/dt max and beat rate. The fit score is a normalized RMSE over the five biomarkers, so lower is closer. The case below is a two-current effect: hERG and Cav1.2 block together. The single-current read fails here; the pair read recovers both.

verapamil-like case · target biomarkers
The ranker never sees the truth; it sees only this five-number summary of the trace from the forward simulation of g_Kr 0.7 with g_CaL 0.5.
rankhypothesisfit score
biomarker noise 0%
0%3%5%10%
30of 30 seeded trials whose top pair is only hERG + Cav1.2, at 0% noise
Validation run on the pair grid: 21/30 at 3% noise, 24/30 at 5%, 17/30 at 10%. The slider re-ranks the same precomputed pair grid with seeded Gaussian noise, so the count is reproducible at each step.
limits of the inverse read

These targets come from the model's own forward simulation. This page shows internal consistency. It is not evidence of skill on real wet-lab traces.

Three-current mechanisms are not identifiable from these five biomarkers. On the chlorpromazine-like case the pair grid returns true and wrong pairs at near-equal score.

Small-magnitude causes are noise-fragile. An IKs gain shifts APD90 by 9 ms; at 5% noise the top single hypothesis is right one third of the time. Large-magnitude causes, like this one, survive 5% noise about 80% of the time. Small ones do not. Five biomarkers cannot separate six single currents; stronger single-current causes separate cleanly.

scope and limits

What it is: the cross-scale causal architecture running on a published, validated electrophysiology model (Kernik-Clancy 2019, via Myokit/CVODE). Its baseline reproduces the published biomarkers within ~1% (APD90 413.4 vs 414 ms), and each channel knockdown moves the action potential in the literature direction. A gene knockdown flows through a gene-regulatory network to ion-channel conductances to the action potential, in real units.

What it is not: the calibrated model. The gene-regulatory network here is a hand-seeded placeholder, and the gene-to-conductance step is an uncalibrated first-order map, not a per-gene fit. The functional layer matches the literature; the cross-scale composition is shown here and testable against the program's CRISPRi data. The calibrated network and per-gene gains come from that data.

On drug-block mode: it scales one channel's conductance and shows how the single-cell action potential reshapes, the way an IKr or ICaL blocker would in this model. It is not a cardiotoxicity prediction, nor a clinical ECG or QRS reading. This is a single iPSC-cardiomyocyte action potential, not tissue or a body-surface signal. It shows direction and rough magnitude of the AP change from a current block in a validated model.

Get a free first read View pricing
get in touch
[email protected]