Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks

TL;DR

This paper introduces a novel AI-based method that encodes protein conformations into a simplified textual form, enabling the generation of extensive, molecule-free protein dynamics trajectories that explore conformational space more efficiently than traditional methods.

Contribution

The authors develop a new approach using generative neural networks on a simplified protein trajectory representation, allowing indefinite extension and sampling of protein conformations without physical molecules.

Findings

Encoded trajectories retain key structural information.

Generative models can produce realistic, extended protein dynamics.

Method accesses conformational states difficult for traditional simulations.

Abstract

All-atom and coarse-grained molecular dynamics are two widely used computational tools to study the conformational states of proteins. Yet, these two simulation methods suffer from the fact that without access to supercomputing resources, the time and length scales at which these states become detectable are difficult to achieve. One alternative to such methods is based on encoding the atomistic trajectory of molecular dynamics as a shorthand version devoid of physical particles, and then learning to propagate the encoded trajectory through the use of artificial intelligence. Here we show that a simple textual representation of the frames of molecular dynamics trajectories as vectors of Ramachandran basin classes retains most of the structural information of the full atomistic representation of a protein in each frame, and can be used to generate equivalent atom-less trajectories suitable to train different types of generative neural networks. In turn, the trained generative models can be used to extend indefinitely the atom-less dynamics or to sample the conformational space of proteins from their representation in the models latent space. We define intuitively this methodology as molecular dynamics without molecules, and show that it enables to cover physically relevant states of proteins that are difficult to access with traditional molecular dynamics.