EvoMax Evolves Compact Genome Editor to 97% Efficiency Using Sparse Data

bravo_abad · x · 2026-08-27

Addressing the data scarcity problem in protein engineering, Shijie Wan et al. introduce EvoMax, a model-guided strategy designed for the sparse-data regime. They used it to engineer compact eukaryotic genome editors achieving 97% endogenous editing efficiency.

EvoMax combines three complementary signals: a Gaussian Process Regression (GPR) learning directly from measured mutational fitness; ESM-2 contributing evolutionary information; and ESM-IF adding structure-conditioned inverse-folding info. The relative contributions shift across optimization rounds, allowing the search to move from local exploitation to broader exploration. The initial GPR uses only 209 experimentally measured single-site mutations.

Original post →

More from Research

Research channel →