Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Machine learning predicts cellular response to genetic perturbation

GEARS, a machine learning model informed by biological knowledge of gene–gene relationships, effectively predicts transcriptional responses to multi-gene perturbations. GEARS can predict the effects of perturbing previously unperturbed genes and detects non-additive interactions, such as synergy, when predicting combinatorial perturbation outcomes. Thus, GEARS expands insights gained from perturbational screens.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Prices vary by article type



Prices may be subject to local taxes which are calculated during checkout

Fig. 1: GEARS performs in silico gene perturbation.


  1. Dixit, A. et al. Perturb-Seq: dissecting molecular circuits with scalable single-cell RNA profiling of pooled genetic screens. Cell 167, 1853–1866 (2016). This paper describes the assay used to measure single-cell transcriptional responses to perturbation.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Norman, T. M. et al. Exploring genetic interaction manifolds constructed from rich single-cell phenotypes. Science 365, 786–793 (2019). These authors studied genetic interactions using a multi-gene perturbation screen.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Kamimoto, K. et al. Dissecting cell identity via network inference and in silico gene perturbation. Nature 614, 742–751 (2023). This article presents an alternative in silico gene perturbation model.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Replogle, J. M. et al. Mapping information-rich genotype-phenotype landscapes with genome-scale perturb-seq. Cell 185, 2559–2575 (2022). This article presents a genome-wide perturbation screen.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Nelson, M. R. et al. The support of human genetic evidence for approved drug indications. Nat. Genet. 47, 856–860 (2015). This article presents the importance of genetic information for drug efficacy.

    Article  CAS  PubMed  Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Roohani, Y., Huang, K. & Leskovec, J. Predicting transcriptional outcomes of novel multigene perturbations with GEARS. Nat. Biotechnol. (2023)

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Machine learning predicts cellular response to genetic perturbation. Nat Biotechnol (2023).

Download citation

  • Published:

  • DOI:


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing