RevPert: predicting candidate drivers of transcriptomic state transitions via gallery-native reverse perturbation
Year: 2026
Type: preprint
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 Δ Y ⋆ = Y B −Y A 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.
Authors: Shiyang Liang, Cheng Yang, Jingjie Wang, Yunqi Li
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Award: G5990477661
OpenAlex ID: W7204126544