How deep can we decipher protein evolution with deep learning models.

Fu, Xiaozhi · Patterns (N Y) · 2024

basic_science · Level V

Where this comes from

Abstract

Evolutionary-based machine learning models have emerged as a fascinating approach to mapping the landscape for protein evolution. Lian et al. demonstrated that evolution-based deep generative models, specifically variational autoencoders, can organize SH3 homologs in a hierarchical latent space, effectively distinguishing the specific Sho1<sup>SH3</sup> domains.