PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction
2026-08-21 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created a method called PerturbRx to better predict how cancer patients will respond to treatments. Unlike previous methods, their approach learns how molecular profiles change when a drug is applied, even without direct patient data after treatment. They first train a model on single-cell data to understand drug effects and then use this to predict patient responses before treatment. Their method showed better prediction results compared to others on several cancer datasets. This suggests that modeling treatment-induced changes can improve personalized cancer therapy predictions.
cancer treatment responseperturbationsingle-cell datalatent transitiondrug dosemolecular profilepatient-derived xenograftTCGArepresentation learning
Authors
Yoshitaka Inoue, Minoh Jeong, Alfred Hero, Rui Kuang, Augustin Luna
Abstract
Scarce data and tumor heterogeneity limit patient-level cancer treatment-response prediction. Existing approaches predict response from pretreatment molecular profiles and drug representations, without explicitly modeling the molecular changes expected under treatment. We propose PerturbRx, a treatment-conditioned representation learning framework that learns intervention-induced latent transitions and uses them as patient-drug response features. PerturbRx trains a drug- and dose-conditioned transition predictor from context-matched but cell-unpaired control and treated single-cell populations, then freezes and transfers the predictor to pretreatment patient profiles without requiring post-treatment measurements. The transition is combined with patient and drug representations to predict response. Across TCGA and patient-derived xenograft benchmarks, PerturbRx achieves the strongest aggregate predictive performance among the evaluated methods. These results support perturbation-pretrained latent transitions as useful representations for patient-level drug-response prediction.