Jiangyan Feng

ESMDynamic predicts protein dynamic contact maps from sequences, outperforming existing methods with less computation and enabling large-scale analysis of conformational variability.

This paper introduces a coarse-grained simulation method to predict the viscosity of antibody solutions and their response to excipients.

The paper uses molecular dynamics simulations to show how minor sequence changes in NarU enable symport instead of antiport compared to NarK.

solPredict predicts antibody solubility from sequence using transfer learning, achieving high correlation with experimental data.

FingerprintContacts predicts alternative protein conformations from residue-residue contacts by leveraging conformation-specific contact patterns in ligand-binding proteins.