Validation ofde novodesigned water-soluble and transmembrane proteins byin silicofolding and melting

Abstract

AbstractIn silicovalidation ofde novodesigned proteins with deep learning (DL)-based structure prediction algorithms has become mainstream. However, formal evidence of the relationship between a high-quality predicted model and the chance of experimental success is lacking. We used experimentally characterizedde novodesigns to show that AlphaFold2 and ESMFold excel at different tasks. ESMFold can efficiently identify designs generated based on high-quality (designable) backbones. However, only AlphaFold2 can predict which sequences have the best chance of experimentally folding among similar designs. We show that ESMFold can generate high-quality structures from just a few predicted contacts and introduce a new approach based on incremental perturbation of the prediction (“in silicomelting”), which can reveal differences in the presence of favorable contacts between designs. This study provides a new insight on DL-based structure prediction models explainability and on how they could be leveraged for the design of increasingly complex proteins; in particular membrane proteins which have historically lacked basicin silicovalidation tools.