EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering

arXiv:2603.11703 · cs.LG · Submitted 2026-03-12 · Read on arXiv

cs.LG

Submitted: 2026-03-12

Updated: 2026-11-11

Comments: Accepted at Workshop on Foundation Models for Science: Real-World Impact and Science-First Design, ICLR 2026; Published at the 21st Machine Learning in Computational Biology (MLCB 2026)

License: http://creativecommons.org/licenses/by/4.0/

The gist: Protein optimization improves an existing protein through targeted mutations, but existing protein language models are poorly suited to it…

Terminology

Abstract

Protein optimization improves an existing protein through targeted mutations, but existing protein language models are poorly suited to it: autoregressive models require full sequence generation, masked language and discrete diffusion models rely on pre-specified mutation locations, and none naturally support insertions and deletions relative to a template. We introduce EvoFlows, a variable-length sequence-to-sequence approach that learns mutational trajectories between evolutionarily related proteins via edit flows, predicting not only which mutation to perform, but also where and how many should occur. Across diverse protein families from UniRef and OAS, EvoFlows generates variants that remain consistent with natural families while exploring farther from the template than leading baselines. In vitro validation of a VHH binder and an enzyme confirms that the large majority of generated variants remain functional and stable without computational downselection.

Related papers