RevPert: predicting candidate drivers of transcriptomic state transitions via gallery-native reverse perturbation
- 1The No. 944 Hospital of Joint Logistic Support Force of PLA
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 ranks a fixed genetic catalog for a query contrast {Delta}Y* = YB - YA by combining signed Pearson connectivity with a learned residual. Across Replogle Essential Perturb-seq (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 ranking placed pre-specified disease anchors far higher on the expected arms than ranking the same signatures by differential-expression magnitude alone (Essential residual model for HCC; a transductive GWPS residual for CML). RevPert therefore couples within-screen reverse ranking to a screen-external signed-geometry check; the latter calibrates literature anchors and is not claimed as held-out recovery.
Related
- A purinergic receptor dominance model for microglial state transitions: balancing perturbation and restraint during neuroinflammation
- Identification of CLOCK and MARK2 as Candidate Blood-Based Biomarkers in Type 2 Diabetes: An Integrated Bulk and Single-Cell Transcriptomic Study
- ISP Platform powered by Geneformer: Framework for Cross-Species, Sequential, and Multi-Gene In Silico Perturbation Screens with Application to iPS Cell State Transitions
- Spatial transcriptomic analysis identifies tnni2a.3 as a candidate associated with intermuscular bone formation in zebrafish
- MultiFlow: coupled flow matching for predicting single-cell multiomic perturbation responses in unseen cellular contexts
BibTeX
@misc{liang2026revpert,
title = {{RevPert: predicting candidate drivers of transcriptomic state transitions via gallery-native reverse perturbation}},
author = {S. Liang and C. Yang and J. Wang and y. Li},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.19.745674},
url = {https://www.biorxiv.org/content/10.64898/2026.08.19.745674v2},
note = {CC BY},
}
RIS
TY - UNPB
TI - RevPert: predicting candidate drivers of transcriptomic state transitions via gallery-native reverse perturbation
AU - S. Liang
AU - C. Yang
AU - J. Wang
AU - y. Li
PY - 2026
DA - 2026/08/19
PB - bioRxiv
DO - 10.64898/2026.08.19.745674
UR - https://www.biorxiv.org/content/10.64898/2026.08.19.745674v2
AB - 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 ranks a fixed genetic catalog for a query contrast {Delta}Y* = YB - YA by combining signed Pearson connectivity with a learned residual. Across Replogle Essential Perturb-seq (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 ranking placed pre-specified disease anchors far higher on the expected arms than ranking the same signatures by differential-expression magnitude alone (Essential residual model for HCC; a transductive GWPS residual for CML). RevPert therefore couples within-screen reverse ranking to a screen-external signed-geometry check; the latter calibrates literature anchors and is not claimed as held-out recovery.
ER -