Deep learning of protein energy landscape and conformational dynamics from experimental structures in PDB

Abstract

Protein structure prediction has reached revolutionary levels of accuracy on single structures, implying biophysical energy function can be learned from known protein structures. However apart from single static structure, conformational distributions and dynamics often control protein biological functions. In this work, we tested a hypothesis that protein energy landscape and conformational dynamics can be learned from experimental structures in PDB and coevolution data. Towards this goal, we develop DeepConformer, a diffusion generative model for sampling protein conformation distributions from a given amino acid sequence. Despite the lack of molecular dynamics (MD) simulation data in training process, DeepConformer captured conformational flexibility and dynamics (RMSF and covariance matrix correlation) similar to MD simulation and reproduced experimentally observed conformational variations. Our study demonstrated that DeepConformer learned energy landscape can be used to efficiently explore protein conformational distribution and dynamics.