scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction
This work addresses drug-response prediction for single-cell biology, enabling transparent what-if analyses and dose tuning to reduce experimental burden.
The paper tackled the problem of predicting single-cell drug responses from scRNA-seq data by introducing scPPDM, a diffusion-based framework that achieved state-of-the-art results, such as +36.11% and +34.21% gains in DEG logFC-Spearman and Pearson correlations on unseen drugs.
This paper introduces the Single-Cell Perturbation Prediction Diffusion Model (scPPDM), the first diffusion-based framework for single-cell drug-response prediction from scRNA-seq data. scPPDM couples two condition channels, pre-perturbation state and drug with dose, in a unified latent space via non-concatenative GD-Attn. During inference, factorized classifier-free guidance exposes two interpretable controls for state preservation and drug-response strength and maps dose to guidance magnitude for tunable intensity. Evaluated on the Tahoe-100M benchmark under two stringent regimes, unseen covariate combinations (UC) and unseen drugs (UD), scPPDM sets new state-of-the-art results across log fold-change recovery, delta correlations, explained variance, and DE-overlap. Representative gains include +36.11%/+34.21% on DEG logFC-Spearman/Pearson in UD over the second-best model. This control interface enables transparent what-if analyses and dose tuning, reducing experimental burden while preserving biological specificity.