scDEFT: A deep learning framework for drug-effect prediction and counterfactual reasoning

arXiv:2609.10831v1 Announce Type: cross Abstract: Longitudinal single cell atlases now capture matched pre treatment and post treatment states from responders and non responders, presenting an opportunity to mechanistically explain why two patients on the same drug diverge. We introduce scDEFT (single cell Drug EFfect Transducer), which treats a drug as a conditioning operator on cell representations, enabling prediction and explanation. In scDEFT, feature wise linear modulation produces drug conditioned cell latents, learned under abundant per cell supervision and then frozen. Two independent heads aggregate those latents over shared transcriptional neighborhoods to predict drug induced state change and responder status. A backward stage ranks the latent dimensions by how strongly they separate responders from non responders and maps them to genes under a cell composition control. On a harmonized inflammatory bowel disease atlas of 1.16 million cells, three cohorts and two drug classes, scDEFT predicts state change at 45% of the baseline to reproducibility ceiling headroom and stratifies responders before treatment at AUROC 0.70, where standard predictors remain at chance. These predictions and the drivers behind them support target and co target nomination, patient stratification, and counterfactual prediction of unseen drug cohort effects.

Related

• PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction
• Semi-Supervised Treatment Effect Estimation with Unlabeled Covariates for Prediction-Powered Causal Inference
• Modeling Covariate Transition for Efficient Estimation of Longitudinal Treatment Effects in Randomized Experiments
• MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis

Source: arXiv cs.LG | 2026-09-11