RevPert: predicting candidate drivers of transcriptomic state transitions via gallery-native reverse perturbation
TL;DR
RevPert is a gallery-native reverse perturbation model that predicts candidate drivers from a fixed genetic catalog for a query contrast ΔY ⋆ = YB −YA by combining signed Pearson connectivity with a learned residual, and couples within-screen reverse prediction to a screen-external signed-geometry check.
Abstract
Cellular state transitions underlie adaptation, ageing and disease, yet prioritizing catalogued genetic perturbations whose expression signatures match an observed transcriptomic shift remains difficult. Most models predict phenotype from a nominated intervention, whereas genetic inverse benchmarks are largely restricted to within-screen identity recovery. Here we introduce RevPert, a gallery-native reverse perturbation model that predicts candidate drivers from a fixed genetic catalog for a query contrast ΔY ⋆ = YB −YA by combining signed Pearson connectivity with a learned residual. Across Replogle Essential Perturbseq (four lines) and LINCS-KO screens (ten lines), RevPert recovered held-out interventions at leading performance relative to matched baselines. Applied to public drug-resistance contrasts in HCC and CML, dual-arm prediction placed pre-specified disease anchors far higher on the expected arms than predicting from differential-expression magnitude alone (Essential residual model for HCC; a transductive GWPS residual for CML). RevPert therefore couples within-screen reverse prediction to a screen-external signed-geometry check; the latter calibrates literature anchors and is not claimed as held-out recovery.