T-CTRL
Perturbation screens often rank genes by effect size, so a gene that changes many transcripts can be mistaken for one that actually controls cell state.
Core trick
Ranks Perturb-seq genes by functional direction and cross-donor repeatability after conditioning on effect magnitude, with permutation tests.
Description
Perturbation screens often rank genes by effect size, so a gene that changes many transcripts can be mistaken for one that actually controls cell state. We built T-CTRL, an auditable workflow that computes ISCI, our Immune-State Controllability Index, and asks whether functional direction and cross-donor repeatability add information after effect magnitude is already known.
In the Marson CD4+ T-cell Perturb-seq screen, the pre-specified full-sample M→M+C test improved recovery of known regulators by +0.357 AUPRC (95% CI [+0.117,+0.538]). A separate, stricter, fully refit leakage-free out-of-fold estimate was +0.215 ([+0.074,+0.560], permutation p=0.010). These are distinct measurements, and we report both.
Stress tests deliberately bound the claim. A broad external functional-regulator set fails (ΔAUPRC −0.281); the CAR-T clinical-prediction analysis is NULL; and scGPT corroboration is NOT-EVALUABLE because required inputs were unavailable. Marson CD4+ passes, Schmidt CD4+ and THP-1 are near-misses, and non-immune K562/RPE1 systems fail.
The result is therefore a tested scope map, not a universal controller score or target list. T-CTRL ships as a Python CLI, reusable DatasetSpec framework, executable notebook, interactive demo, claim ledger and provenance-bound evidence package, with 151 tests and 21/21 automated release gates.
README excerpt
# T-CTRL — Which genes actually steer T-cell state? [](https://doi.org/10.5281/zenodo.21348207) **T-CTRL** is the judge-facing experience. **ISCI (Immune-State Controllability Index)** is the open-source, auditable method behind it. Most perturbation screens reward genes that cause the biggest change. T-CTRL asks a harder question: **among perturbations with a similar effect size, which genes move a T cell toward a specific functional state and repeat that behavior across donors?** The output is not a therapeutic-target list. It is a bounded scientific verdict — **PASS, FAIL, NULL or NOT-EVALUABLE** — with the evidence and provenance needed to audit it. > **Built with Claude: Life Sciences · Researcher Track · MIT open source** > > Genome-scale Perturb-seq in primary human CD4+ T cells · CPU-local on a 24 GB Mac · no raw > clinical or large H5AD/H5MU data committed ## Start here This is a reusable public research project with a short evaluation path for the hackathon. Choose the route that matches what you want to do: | For | Time | Start here | What you will get | |---|---:|---|---| | **Hackathon judges** | **3 min** | [Watch the narrated demo](https://youtu.be/7Rz4PpmQZuI) · [Open the interactive overview](https://anetoc.github.io/ISCI-hackathon/) | The scientific question, result, failed tests, reusable workflow and next experiment | | **New readers** | **5 min** | [Read the plain-language package map]