Jeremy M. G. Leung

This study compares AI tools for predicting protein structural ensembles, finding they generate diverse but distinct conformational distributions, with limited coverage of experimental structures and minimal response to known mutations.

The paper describes a method to generate equilibrium protein structure ensembles using physics-based computations to harmonize AI-generated outputs.

PRISM clusters molecular pathways using structural medoids and geometric dissimilarities, showing robust clustering across complex biomolecular transitions.

SHINE improves pathway ensemble analysis by integrating n-ary similarity, cheminformatics tools, and hierarchical clustering for MD simulations.

This paper develops a deep learning method to identify progress coordinates during weighted ensemble simulations, improving folding rate constant estimation by >3-fold in protein folding simulations.

The paper introduces LPATH, a Python tool for clustering molecular pathways using linguistics-assisted methods, demonstrating its effectiveness on alanine dipeptide conformational transitions.