Tristan Bitard‐Feildel

This study uses a deep learning framework to generate and explore new protein sequences with functional properties by navigating amino acid sequence space.

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.

The paper introduces HCAtk and pyHCA, tools for hydrophobic cluster analysis of protein sequences, improving domain detection in unannotated proteomes.