HemePLM-Diffuse: A Scalable Generative Framework for Protein-Ligand Dynamics in Large Biomolecular System

TL;DR

HemePLM-Diffuse is a scalable transformer-based generative model that accurately simulates protein-ligand dynamics, inpaints missing ligand fragments, and handles large biomolecular systems with over 10,000 atoms.

Contribution

It introduces a novel SE(3)-Invariant tokenization and time-aware diffusion approach for large-scale protein-ligand trajectory generation.

Findings

Outperforms existing models like TorchMD-Net, MDGEN, and Uni-Mol in accuracy.

Successfully simulates systems with more than 10,000 atoms.

Demonstrates effective inpainting of missing ligand fragments.

Abstract

Comprehending the long-timescale dynamics of protein-ligand complexes is very important for drug discovery and structural biology, but it continues to be computationally challenging for large biomolecular systems. We introduce HemePLM-Diffuse, an innovative generative transformer model that is designed for accurate simulation of protein-ligand trajectories, inpaints the missing ligand fragments, and sample transition paths in systems with more than 10,000 atoms. HemePLM-Diffuse has features of SE(3)-Invariant tokenization approach for proteins and ligands, that utilizes time-aware cross-attentional diffusion to effectively capture atomic motion. We also demonstrate its capabilities using the 3CQV HEME system, showing enhanced accuracy and scalability compared to leading models such as TorchMD-Net, MDGEN, and Uni-Mol.