scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liang, Zhaokang, Zhuang, Shuyang, Jiao, Xiaoran, Mao, Weian, Chen, Hao, Shen, Chunhua
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917010763415552
author Liang, Zhaokang
Zhuang, Shuyang
Jiao, Xiaoran
Mao, Weian
Chen, Hao
Shen, Chunhua
author_facet Liang, Zhaokang
Zhuang, Shuyang
Jiao, Xiaoran
Mao, Weian
Chen, Hao
Shen, Chunhua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11726
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction
Liang, Zhaokang
Zhuang, Shuyang
Jiao, Xiaoran
Mao, Weian
Chen, Hao
Shen, Chunhua
Quantitative Methods
Machine Learning
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.
title scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction
topic Quantitative Methods
Machine Learning
url https://arxiv.org/abs/2510.11726