PerturbGate
PerturbGate is an open-data, reproducible pipeline that turns a genome-scale primary human CD4 T-cell Perturb-seq screen into evidence-gated mechanism hypotheses — not another ranking of hits.
Core trick
Scores each knockdown by whether it reverses a donor-paired disease expression direction, then gates hits on technical validity and external cohort replication.
Description
PerturbGate is an open-data, reproducible pipeline that turns a genome-scale primary human CD4 T-cell Perturb-seq screen into evidence-gated mechanism hypotheses — not another ranking of hits. Each of 924 knockdowns is scored not by "does the cell change?" but by "does it reverse a donor-paired juvenile-arthritis disease direction?", then put through gates for technical validity, disease direction, an external patient cohort, and translatability. The result is an honest triad: PAK2, a strong reproducible cellular hit, was rejected as non-directional; RIPK1 is an unsupported comparator; RICTOR reverses the inflamed T-cell programme (+0.161 internal, +0.165 in an independent JIA cohort, 6/6 leave-one-donor-out) but is retained only as a mechanism hypothesis with an explicit modality gap - never a validated target. Every number resolves to a committed frozen table; negatives and corrected results are first-class outputs. It recomputes on a laptop in minutes.
MargoSolo/perturbgate-perturbseq★ 90 forksHTMLNOASSERTIONCreated Jul 12, 2026 · last push Jul 22, 2026
README excerpt
# PerturbGate **Evidence-Gated Pipeline for T-cell Perturb-seq Mechanism Hypotheses** A reproducible analysis of a genome-scale primary human CD4 T-cell Perturb-seq screen, designed to distinguish real perturbation effects from defensible mechanism hypotheses. **RICTOR is our lead candidate drug target.** It was nominated *de novo* by our disease-rescue analysis of the screen, survived the internal evidence gates, and reproduced the same directional reversal in an **external JIA patient cohort**. It is a promising, evidence-backed target **hypothesis** — the step from here to an advanceable drug is a RICTOR-selective molecule plus experimental validation. Our first lead, **PAK2**, was technically reproducible but **failed the disease-direction test** and was rejected. ## TL;DR - **What we built** — an open, reproducible pipeline that turns a genome-scale human CD4 T-cell Perturb-seq screen into **auditable drug-target hypotheses**, not just a ranked hit list. Every number resolves to a committed artifact. - **What we found** — **RICTOR**: knocking it down moves inflamed-joint (JIA) CD4 T cells *against* the disease programme (internal reversal **+0.161**), and this **reproduces in an external patient cohort** (**+0.165**, GSE160097; 6/6 paired leave-one-donor-out). PAK2 looked good technically but was **rejected** on the disease-direction test. - **Why it matters** — most Perturb-seq studies stop at *"which knockdown changes the cell most."* We show *which