Learning Geometrically Disentangled Representations of Protein Folding Simulations

TL;DR

This paper introduces ProGAE, a geometric autoencoder that learns disentangled representations of protein structures from molecular simulations, enabling accurate, interpretable, and transferable generation of protein conformations.

Contribution

The work presents a novel geometric autoencoder framework that separates intrinsic and extrinsic protein geometries, improving interpretability and transferability in protein structure modeling.

Findings

ProGAE accurately reconstructs protein conformations at near-experimental resolution.

The model efficiently generates diverse structural variations of proteins.

ProGAE's transferability reduces retraining needs across different protein states.

Abstract

Massive molecular simulations of drug-target proteins have been used as a tool to understand disease mechanism and develop therapeutics. This work focuses on learning a generative neural network on a structural ensemble of a drug-target protein, e.g. SARS-CoV-2 Spike protein, obtained from computationally expensive molecular simulations. Model tasks involve characterizing the distinct structural fluctuations of the protein bound to various drug molecules, as well as efficient generation of protein conformations that can serve as an complement of a molecular simulation engine. Specifically, we present a geometric autoencoder framework to learn separate latent space encodings of the intrinsic and extrinsic geometries of the protein structure. For this purpose, the proposed Protein Geometric AutoEncoder (ProGAE) model is trained on the protein contact map and the orientation of the backbone bonds of the protein. Using ProGAE latent embeddings, we reconstruct and generate the conformational ensemble of a protein at or near the experimental resolution, while gaining better interpretability and controllability in term of protein structure generation from the learned latent space. Additionally, ProGAE models are transferable to a different state of the same protein or to a new protein of different size, where only the dense layer decoding from the latent representation needs to be retrained. Results show that our geometric learning-based method enjoys both accuracy and efficiency for generating complex structural variations, charting the path toward scalable and improved approaches for analyzing and enhancing high-cost simulations of drug-target proteins.