scTREAT: Latent Diffusion for Single-Cell Drug-Response Prediction

Generating drug-induced transcriptional responses requires a model to account for cellular background together with molecular identity and dose. We present Single-Cell Transcriptomic Response Estimation After Treatment (scTREAT), a latent diffusion model with separate state and drug guidance. A shared expression space connects the baseline and response, while Guided Decomposable Attention (GD-Attn) injects a baseline representation and a dose-conditioned molecular embedding. Independent channel dropout exposes four conditioning states during training; inference combines three conditional predictions with separately specified state and drug coefficients, and dose modulates drug-guidance strength. On condition-level pseudobulk profiles derived from the Tahoe-100M single-cell atlas, scTREAT achieves the best value on 10 of 12 metrics for unseen cell line–drug combinations (UC) and 11 of 12 for unseen drugs (UD). Ablations examine condition injection, molecular representation, and guidance design. These findings support a conditional response generator with an explicit inference interface, motivating its study as a downstream response-modeling component for biomolecular design.