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

2026-02-03

AI Summary

This work proposes GPCRLMD, a novel framework for efficiently simulating the conformational dynamics of all-atom G protein–coupled receptor (GPCR)–ligand complexes, which are typically computationally prohibitive. GPCRLMD integrates residual normalizing flows with a physically constrained isometric latent space, leveraging a harmonic prior variational autoencoder (HP-VAE) to disentangle static structural topology from dynamic fluctuations. This enables accurate and efficient modeling of temporal evolution in the latent space. The method drastically reduces computational cost while generating high-fidelity, all-atom trajectories that faithfully reproduce key intermolecular interactions and thermodynamic observables, achieving state-of-the-art performance in GPCR–ligand dynamics simulation.

Technology Category

• Machine Learning: Learning with Manifolds
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• GPCR
• ligand simulation
• molecular dynamics
• conformational transitions
• computational cost

Innovation

• GPCR
• deep generative model
• latent space
• residual flow
• all-atom simulation