Jean Marc Kwasigroch

SOuLMuSiC predicts the impact of mutations on protein solubility using a shallow neural network, outperforming existing methods on curated and external datasets.

FiTMuSiC predicts protein fitness effects using structural and coevolutionary data, achieving high accuracy and providing mechanistic insights through functional and structural scores.

pyScoMotif identifies similar 3D structural motifs across proteins, enabling tasks like catalytic site detection and drug discovery.

SWOTein predicts stability strengths and weaknesses in proteins using statistical energy functions, showing agreement with experimental data and identifying functional regions.

The paper introduces HoTMuSiC, a tool predicting the impact of point mutations on protein melting temperature, and demonstrates its use in thermal stability engineering of Rhizomucor miehei lipase.

SOLart predicts protein solubility using structure-based features, achieving high correlation with experimental values and outperforming existing predictors.

The paper analyzes biases in protein stability prediction tools and proposes a symmetry-based solution to reduce bias towards destabilizing mutations.