Machine learning methods to decipher the evolutionary dynamics of microbial pathogens.

Authors

Manolo F Perez, Anna Zhukova, Renny Doig, Olivier Gascuel, Caroline Colijn

Published in

Trends in microbiology. Nov 12, 2026. Epub Nov 12, 2026.

Abstract

We are currently witnessing an unprecedented rise in the amount of diverse data on pathogens and epidemics. These data include genomic sequences with metadata such as geographic locations, risk groups, and sampling information. Machine learning (ML) has been applied to overcome the scalability bottlenecks inherent in these heterogeneous and high-dimensional datasets. This review highlights how ML tools are achieving concrete successes in predicting pathogen adaptation and drug resistance, performing source and host prediction, identifying high-risk lineages, and estimating phylodynamic and epidemiological parameters. We also show how ML is transitioning molecular epidemiology from a retrospective monitoring field to a proactive and predictive framework for major global microbial threats. Finally, we discuss the limitations of these approaches with respect to interpretability, uncertainty estimation, data volume requirements, and model misspecification.

PMID:
43020769
Bibliographic data and abstract were imported from PubMed on 13 Nov 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.