All-Atom GPCR-Ligand Simulation via Residual Isometric Latent Flow

TL;DR

This paper introduces GPCRLMD, a deep generative model that efficiently simulates all-atom GPCR-ligand dynamics by combining a physics-informed autoencoder with a residual flow in a regularized latent space, enabling accurate and computationally feasible simulations.

Contribution

The paper presents a novel deep generative framework that significantly improves the efficiency and accuracy of all-atom GPCR-ligand simulations using a physics-informed latent space and residual flow sampling.

Findings

Achieves state-of-the-art performance in GPCR-ligand dynamics simulation.

Faithfully reproduces thermodynamic observables and ligand-receptor interactions.

Decouples static topology from dynamic fluctuations effectively.

Abstract

G-protein-coupled receptors (GPCRs), primary targets for over one-third of approved therapeutics, rely on intricate conformational transitions to transduce signals. While Molecular Dynamics (MD) is essential for elucidating this transduction process, particularly within ligand-bound complexes, conventional all-atom MD simulation is computationally prohibitive. In this paper, we introduce GPCRLMD, a deep generative framework for efficient all-atom GPCR-ligand simulation.GPCRLMD employs a Harmonic-Prior Variational Autoencoder (HP-VAE) to first map the complex into a regularized isometric latent space, preserving geometric topology via physics-informed constraints. Within this latent space, a Residual Latent Flow samples evolution trajectories, which are subsequently decoded back to atomic coordinates. By capturing temporal dynamics via relative displacements anchored to the initial structure, this residual mechanism effectively decouples static topology from dynamic fluctuations. Experimental results demonstrate that GPCRLMD achieves state-of-the-art performance in GPCR-ligand dynamics simulation, faithfully reproducing thermodynamic observables and critical ligand-receptor interactions.