EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

scDRP: disentangled representation learning for predicting single-cell responses to perturbations and estimating individual treatment effects

Jianle Sun iD, Petar Stojanov, Kun Zhang

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag482 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Jianle Sun und 2 weiteren Autor:innen. Beteiligte Einrichtung: Carnegie Mellon University, Pittsburgh 15213, PA, United States. Hauptthemen laut MEDLINE: Single-Cell Analysis, Leukemia, Myelogenous, Chronic, BCR-ABL Positive. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MBZUAI-WIS Joint Program, National Institutes of Health (NIH), NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dissecting cell-state-specific changes in gene regulation induced by perturbations is crucial for understanding biological mechanisms. However, single-cell sequencing provides only unmatched snapshots of cells under different conditions. This destructive measurement process hinders the estimation of individualized treatment effects (ITEs), which are essential for pinpointing these heterogeneous mechanistic responses. We develop scDRP, a generative framework that leverages disentangled representation learning with asymptotic correctness guarantees to separate perturbation-induced and perturbation-invariant latent variables via a sparsity regularized $\beta $-variational autoencoder. Assuming quantile-preserving effects of perturbations conditional on confounders, scDRP performs conditional optimal transport in the disentangled latent space to infer counterfactual states and estimate ITEs. Applied to simulated and real single-cell perturbation data, scDRP accurately estimates treatment effects and individual counterfactual responses, with subsequent biclustering analysis further elucidating cell-type-specific functional gene module dynamics. Specifically, it captures distinct cellular patterns under rhinovirus and cigarette-smoke extract exposures, reveals heterogeneous responses to interferon stimulation across diverse immune cell types, and identifies distinct functional module activation in chronic myeloid leukemia cells following CRISPR activation targeting different genes. scDRP also generalizes to unseen perturbation doses and combinations. Our framework provides a principled computational approach to extracting heterogeneous causal relationships from single-cell perturbation data, enabling a deeper understanding of cellular and molecular mechanisms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisLeukemia, Myelogenous, Chronic, BCR-ABL PositiveHumansRepresentation Machine LearningSingle-Cell Gene Expression AnalysisAutoencoderTreatment Effect Heterogeneity

Stichwörter der Autor:innen

disentangled representationfunctional gene moduleheterogeneous cellular responseindividual treatment effectoptimal transportsingle-cell perturbation

Autor:innen und Institutionen

  • Carnegie Mellon University, Pittsburgh 15213, PA, United States.
  • Broad institute of MIT and Harvard, Cambridge 02142, MA, United States.
  • Mohamed bin Zayed University of Artificial Intelligence, Masdar City Abu Dhabi, United Arab Emirates.

ORCID-Profile: Jianle Sun

Förderung

  • MBZUAI-WIS Joint Program
  • National Institutes of Health (NIH)
  • NHLBI NIH HHS
  • Quris AI
  • Florin Court Capital
  • Al Deira Causal Education project
  • AI Institute for Societal Decision Making (AI-SDM)
  • NSF

Zitieren

APA

Sun, J., Stojanov, P., & Zhang, K. (2026). scDRP: disentangled representation learning for predicting single-cell responses to perturbations and estimating individual treatment effects. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag482

Vancouver

Sun J, Stojanov P, Zhang K. scDRP: disentangled representation learning for predicting single-cell responses to perturbations and estimating individual treatment effects. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag482

BibTeX
@article{Sun2026,
  author = {Sun, Jianle and Stojanov, Petar and Zhang, Kun},
  title = {scDRP: disentangled representation learning for predicting single-cell responses to perturbations and estimating individual treatment effects},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag482}
}
Kostenlos starten →