{"ID":2885358,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.16587","arxiv_id":"2508.16587","title":"HemePLM-Diffuse: A Scalable Generative Framework for Protein-Ligand Dynamics in Large Biomolecular System","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.","short_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 sim...","url_abs":"https://arxiv.org/abs/2508.16587","url_pdf":"https://arxiv.org/pdf/2508.16587v1","authors":"[\"Rakesh Thakur\",\"Riya Gupta\"]","published":"2025-08-07T17:29:52Z","proceeding":"q-bio.BM","tasks":"[\"q-bio.BM\",\"cs.LG\"]","methods":"[\"Diffusion Model\",\"Transformer\",\"Generative Adversarial Network\"]","has_code":false}