Exploring the conformational ensembles of protein-protein complex with transformer-based generative model

Abstract

Protein-protein interactions are the basis of many protein functions, and understanding the contact and conformational changes of protein-protein interactions is crucial for linking protein structure to biological function. Although difficult to detect experimentally, molecular dynamics (MD) simulations are widely used to study the conformational space and dynamics of protein-protein complexes, but there are significant limitations in sampling efficiency and computational costs. In this study, a generative neural network was trained on protein-protein complex conformations obtained from molecular simulations to directly generate novel conformations with physical realism. We demonstrated the use of a deep learning model based on the transformer architecture to explore the conformational space of protein-protein complexes through MD simulations. The results showed that the learned latent space can be used to generate unsampled conformations of protein-protein complexes for obtaining new conformations complementing pre-existing ones, which can be used as an exploratory tool for the analysis and enhancement of molecular simulations of protein-protein complexes.

Application of Transformers in Cheminformatics

“…Moreover, transformer-based models are particularly suitable for simulations since they can effectively capture multiscale interactions between drugs and protein sequences amd handle multimodal data. For example, Wang et al 161 formulated molecular dynamics simulations as a generative problem with the goal of discovering novel conformation. A transformer encoder-decoder network is trained to predict propagating frames of protein complexes with data obtained from MD simulations.…”