Resolving Protein Conformational Changes through Machine Learning Based Enhanced Sampling

The functionalities of proteins rely on protein conformational changes during many processes. Identification of the protein conformations and capturing transitions among different conformations are important but extremely challenging in both experiments and simulations. In this work, we develop a machine learning based approach to rapidly identify a reaction coordinate that accelerates the exploration of protein conformational changes in molecular simulations. Our method has foundations in local optimization, strives to predict reaction pathways before reactions completely occur, and speeds up sampling in molecular simulations. We implement our approach to study the conformational changes of human NTHL1 during the DNA repair process. Our results identified three distinct conformations: open (stable), closed (unstable), and bundle (stable). The existence of the bundle conformation can rationalize the recent experimental observations. Comparison with an NTHL1 mutant demonstrates that a closely packed cluster of positively charged residues in the linker could be a factor to search for in the genes encoding when screening for genetic abnormalities. Results will lead to better modulation of the DNA repair pathway to protect against carcinogenesis.