EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning genetic perturbation effects with variational causal inference

Emily Liu, Jiaqi Zhang iD, Caroline Uhler iD

PLOS Computational Biology · 2026

DOI: 10.1371/journal.pcbi.1013194 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Emily Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, United States of America. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCCIH NIH HHS, Broad Institute, Apple.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advances in sequencing technologies have enhanced the understanding of gene regulation in cells. In particular, Perturb-seq has enabled high-resolution profiling of the transcriptomic response to genetic perturbations at the single-cell level. This understanding has implications in functional genomics and potentially for identifying therapeutic targets. Various computational models have been developed to predict perturbational effects. While deep learning models excel at interpolating observed perturbational data, they tend to overfit in the lack of enough data and may not generalize well to unseen perturbations. In contrast, mechanistic models, such as linear causal models based on gene regulatory networks, hold greater potential for extrapolation, as they encapsulate regulatory information that can predict responses to unseen perturbations. However, their application has been limited to small studies due to overly simplistic assumptions, making them less effective in handling noisy, large-scale single-cell data. We propose a hybrid approach that combines a mechanistic causal model with variational deep learning, termed Single Cell Causal Variational Autoencoder (SCCVAE). The mechanistic model employs a learned regulatory network to represent perturbational changes as shift interventions that propagate through the learned network. SCCVAE integrates this mechanistic causal model into a variational autoencoder, generating rich, comprehensive transcriptomic responses. Our results indicate that SCCVAE exhibits superior performance over current state-of-the-art baselines for extrapolating to predict unseen perturbational responses. Additionally, for the observed perturbations, the latent space learned by SCCVAE allows for the identification of functional perturbation modules and simulation of single-gene knockdown experiments of varying penetrance, presenting a robust tool for interpreting and interpolating perturbational responses at the single-cell level.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGene Regulatory NetworksComputational BiologyAutoencoderHumansSingle-Cell AnalysisModels, GeneticGene Expression ProfilingSingle-Cell Gene Expression AnalysisAnimalsTranscriptomeComputer Simulation

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, United States of America.
  • Eric and Wendy Schmidt Center, Broad Institute, Cambridge, Massachusetts, United States of America.
  • Laboratory for Information and Decision Systems, MIT, Cambridge, Massachusetts, United States of America.

ORCID-Profile: Jiaqi Zhang, Caroline Uhler

Förderung

  • NCCIH NIH HHS
  • Broad Institute
  • Apple
  • National Center for Complementary and Integrative Health
  • Office of Naval Research
  • U.S. Department of Energy
  • Simons Foundation

Zitieren

APA

Liu, E., Zhang, J., & Uhler, C. (2026). Learning genetic perturbation effects with variational causal inference. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013194

Vancouver

Liu E, Zhang J, Uhler C. Learning genetic perturbation effects with variational causal inference. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1013194

BibTeX
@article{Liu2026,
  author = {Liu, Emily and Zhang, Jiaqi and Uhler, Caroline},
  title = {Learning genetic perturbation effects with variational causal inference},
  journal = {PLOS Computational Biology},
  year = {2026},
  doi = {10.1371/journal.pcbi.1013194}
}
Kostenlos starten →