Generating Multi-state Conformations of P-type ATPases with a Diffusion Model

Abstract

AbstractUnderstanding and predicting the diverse conformational states of membrane proteins is essential for elucidating their biological functions. Despite advancements in computational methods, accurately capturing these complex structural changes remains a significant challenge. In this study, we introduce a method for predicting diverse functional states of membrane protein conformations using a diffusion model. Our approach integrates forward and backward diffusion processes, incorporating state classifiers and additional conditioners to control the generation gradient of conformational states. We specifically target the P-type ATPases, a key membrane transporter, for which we curated and expanded a structural dataset. By employing a graph neural network with a custom membrane constraint, our model generates precise structures for P-type ATPases across different functional states. This approach represents a significant step forward in computational structural biology and holds great potential for studying the dynamics of other membrane proteins.