Drug Response Prediction Provides a Biologically Relevant Benchmark for Perturbation Response Models

Abstract

Perturbation response models (PRMs) predict transcriptional responses to interventions such as gene knockout or drug treatments. While simple baseline models match PRMs in reconstructing post-treatment profiles, we show that drug response predictors trained on PRM-generated profiles significantly outperform those trained on baseline or pre-treatment profiles. Unlike simple baseline models, PRMs preserve variation in response-relevant genes, making them a highly valuable tool for predicting drug response.