UniPert-G2CP bridges genetic and chemical screens from molecular representation to phenotype modeling.

Abstract

Systematically simulating and predicting phenotypic effects of diverse interventions across heterogeneous cellular environments is central to the vision of artificial intelligence virtual cell (AIVC). However, disparities in perturbagen modalities, assay formats, and data production efficiency hinder unified modeling and analysis of genetic and chemical screens. This study presents UniPert-G2CP, a two-stage deep learning framework that bridges genetic and chemical screens by unifying multimodal molecular perturbagen (cause) representations and enabling genetic-to-chemical perturbation phenotype (effect) transfer learning. Validated on large-scale genetic and chemical screening datasets, UniPert-G2CP enables more efficient, accurate, robust, interpretable, and generalizable simulation of multicellular and multidomain perturbation cause-effect spaces. Further joint analysis of these spaces reveals cellular heterogeneity underlying drug responses, providing mechanistic insights into drug action and resistance. Collectively, UniPert-G2CP advances universal biological causal modeling, accelerates AIVC realization, and expands the potential of AI-powered precision medicine.