Machine learning for perturbational single-cell omics

Yuge Ji, Mohammad Lotfollahi, F. Alexander Wolf, Fabian J. Theis

Research output: Contribution to journalReview articlepeer-review

44 Scopus citations

Abstract

Cell biology is fundamentally limited in its ability to collect complete data on cellular phenotypes and the wide range of responses to perturbation. Areas such as computer vision and speech recognition have addressed this problem of characterizing unseen or unlabeled conditions with the combined advances of big data, deep learning, and computing resources in the past 5 years. Similarly, recent advances in machine learning approaches enabled by single-cell data start to address prediction tasks in perturbation response modeling. We first define objectives in learning perturbation response in single-cell omics; survey existing approaches, resources, and datasets (https://github.com/theislab/sc-pert); and discuss how a perturbation atlas can enable deep learning models to construct an informative perturbation latent space. We then examine future avenues toward more powerful and explainable modeling using deep neural networks, which enable the integration of disparate information sources and an understanding of heterogeneous, complex, and unseen systems.

Original languageEnglish
Pages (from-to)522-537
Number of pages16
JournalCell Systems
Volume12
Issue number6
DOIs
StatePublished - 16 Jun 2021

Keywords

  • cell state
  • deep learning
  • drug
  • heterogeneous systems
  • machine learning
  • perturbation
  • single-cell

Fingerprint

Dive into the research topics of 'Machine learning for perturbational single-cell omics'. Together they form a unique fingerprint.

Cite this