Health AI Central
Share:
Peer-Reviewed Publication
J Chem Inf Model2026July 13, 2026Journal Article

Protein Language Model-Based Fitness Estimates Facilitate Resistance Mutation Identification.

Dominik Schwarz1, Sven H Giese1, Akansha Gupta2, Paulina J Dziubańska-Kusibab3, Santiago D Villalba1, Andrew Cherniack2, Xiaoping Yang2, David Root2, Gizem Karsli-Uzunbas2, Heidi Greulich2, Franziska Siegel3, Atanas Kamburov4, Ekaterina Nevedomskaya5, Clara Christ6, Matteo Aldeghi7, Jérémie Mortier6
1Bayer AG, Machine Learning Research, Research & Development, Pharmaceuticals, 13353 Berlin, Germany.
2Broad Institute of MIT and Harvard, Cambridge, Massachusetts 02142, United States.
3Bayer AG, Research & Early Development Oncology, Research & Development, Pharmaceuticals, 13353 Berlin, Germany.
4Owkin France, Research and Technology, 75009 Paris, France.
5Bayer AG, Computational Biology, Research & Development, Pharmaceuticals, 13353 Berlin, Germany.
6Bayer AG, Structural Biology & Computational Design, Research & Development, Pharmaceuticals, 13353 Berlin, Germany.
7Bayer Research and Innovation Center, Machine Learning Research, Cambridge, Massachusetts 02142, United States.
PubMed DOI

Abstract

Drug resistance is a major challenge in cancer therapy. Cancer cells with pre-existing or acquired mutations that confer resistance to a given drug treatment outgrow the susceptible cell population and cause cancer recurrence after an initial successful treatment response. Knowledge about resistance mutations before they occur in the clinic could prevent unnecessary patient treatment with ineffect…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.