Skip to yearly menu bar Skip to main content


Poster

Evolution-Inspired Loss Functions for Protein Representation Learning

Chengyue Gong · Adam Klivans · James Loy · Tianlong Chen · qiang liu · Danny Diaz

Hall C 4-9 #2901
[ ] [ Paper PDF ]
[ Poster
Tue 23 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

AI-based frameworks for protein engineering use self-supervised learning (SSL) to obtain representations for downstream mutation effect predictions. The most common training objective for these methods is wildtype accuracy: given a sequence or structure where a wildtype residue has been masked, predict the missing amino acid. Wildtype accuracy, however, does not align with the primary goal of protein engineering, which is to suggest a mutation rather than to identify what already appears in nature. Here we present Evolutionary Ranking (EvoRank), a training objective that incorporates evolutionary information derived from multiple sequence alignments (MSAs) to learn more diverse protein representations. EvoRank corresponds to ranking amino-acid likelihoods in the probability distribution induced by an MSA. This objective forces models to learn the underlying evolutionary dynamics of a protein. Across a variety of phenotypes and datasets, we demonstrate that EvoRank leads to dramatic improvements in zero-shot performance and can compete with models fine-tuned on experimental data. This is particularly important in protein engineering, where it is expensive to obtain data for fine-tuning.

Chat is not available.