Overview
Field: Machine Learning Authors: Yoshitaka Inoue, Minoh Jeong, Alfred Hero, Rui Kuang, Augustin Luna Published: 2026-08-21 arXiv: 2608.21349
Summary
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. The authors propose PerturbRx, a treatment-conditioned representation learning framework that learns intervention-induced latent transitions and uses them as patient-drug response features.
How it works
1. Train a drug- and dose-conditioned transition predictor from context-matched but cell-unpaired control and treated single-cell populations. 2. Freeze and transfer the predictor to pretreatment patient profiles — no post-treatment measurements are required. 3. Combine the predicted latent transition with patient and drug representations to predict response.
Results
On TCGA and patient-derived xenograft (PDX) benchmarks, PerturbRx achieved the strongest overall predictive performance among the evaluated methods. These results support perturbation-pretrained latent transitions as a useful representation for patient-level drug response prediction.
Original 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 r...
--- *Auto-collected on 2026-08-25*