{
  "abstract": "Accurately identifying the optimal protein–ligand binding pose is crucial for reliable binding affinity prediction, as molecular dynamics–based approaches are highly sensitive to the initial structure. However, there is currently no efficient way to predict such poses. Indeed, we assess the capabilities of three proposed AI-based software solutions (AlphaFold3, Boltz and RoseTTAFold All-Atom) and demonstrate their substantial shortcomings in this context. Here, we present a combined physics-and machine-learning-based method that predicts optimal protein-ligand poses in their relaxed states, enabling rapid and cost-effective downstream estimation of binding affinities. We apply our approach to two targets, tankyrase 2 (TNKS2) and the 3C-like protease (3CLPro), using datasets of 10,000 molecules for each system. Evaluation on an external validation set of approximately 3,000 molecules demonstrates the method’s ability to generalize to previously unseen datasets, aligning with the practical needs of high-throughput drug discovery pipelines that iteratively evaluate new molecules. Our method substantially reduces the need for costly calculations by efficiently filtering out poses unlikely to yield favorable binding affinities upon relaxation.",
  "abstract_shown": true,
  "affiliations": [
    "Wadhwani School of Data Science and Artificial Intelligence",
    "Indian Institute of Technology Madras",
    "Department of Chemistry",
    "University College London",
    "Frederick National Laboratory for Cancer Research",
    "University of Delaware"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 11,
  "authors": [
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Agastya P Bhati"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Jinyu Dong"
    },
    {
      "affs": [
        4
      ],
      "name": "Sean Black"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Shunzhou Wan",
      "orcid": "0000-0001-7192-1999"
    },
    {
      "affs": [
        5
      ],
      "name": "Vineeth Gutta"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Xibei Zhang"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Mateusz Bieniek"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Darren V. S. Green"
    },
    {
      "affs": [
        5
      ],
      "name": "Sunita Chandrasekaran"
    },
    {
      "affs": [
        4
      ],
      "name": "Eric Stahlberg"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Peter V. Coveney"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/btb5e37mev389.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009330/v1",
  "fulltext_url": null,
  "id": "btb5e37mev389",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009330/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7214074633",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009330/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/btb5e37mev389.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:21Z",
      "native_id": "10.26434/chemrxiv.15009330",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009330/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Integrative Physics and Machine Learning-Based Optimal Binding Pose Generator for Protein-Ligand Complexes",
  "title_text": "Integrative Physics and Machine Learning-Based Optimal Binding Pose Generator for Protein-Ligand Complexes",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:21Z",
  "url": "https://research.draconitic.com/paper/btb5e37mev389",
  "venue": "ChemRxiv",
  "versions": []
}