StrucNS reveals interaction-weighted network topology as the driving predictor of absolute stability of natural and de novo proteins.
StrucNS is a mathematical framework that identifies principles governing protein fitness by employing network science to learn physicochemical relationships between residues and their stability contributions directly from the protein fold, and performs comparably to supervised UniRep in predicting absolute stability of...
Archita Mullick, Prodromos Daoutidis, B. Hackel
· Bioinformatics · 0 citations