{
  "abstract": "Despite continuing hype about the role of AI in drug discovery, no \"AI-discovered drugs\" have so far received regulatory approval. Here we assess one of the latest AI-based tools in this domain. Boltz-2, a recently developed biomolecular foundation model, aims to bridge the gap between AI efficiency and physics-based precision through a joint \"cofolding\" approach. In this study, we provide an extensive evaluation of Boltz-2 using two large-scale data sets: 16780 compounds for 3CLPro and 21702 compounds for TNKS2. We compare Boltz-2 predicted structures with traditional docking and binding affinities with binding free energies derived from the physics-based ESMACS protocol. Structural analysis reveals significant global RMSD variations, indicating that Boltz-2 predicts multiple protein conformations and ligand binding positions rather than a single converged pose. Energetic evaluations exhibit only weak to moderate correlations across the global data sets. Furthermore, a focused analysis of the top 100 compounds yields no significant correlation between the Boltz-2 predictions and the binding free energies from fine-grained ESMACS, alongside frequently observed saturation-state errors in Boltz-2 predicted ligand structures. Our results show that Boltz-2 lacks the energetic resolution required for lead identification. These findings highlight the necessity of employing physics-based methods for the reliability and refinement of AI-derived models.",
  "abstract_shown": true,
  "affiliations": [
    "University College London , , , ,"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Shunzhou Wan",
      "orcid": "0000-0001-7192-1999"
    },
    {
      "affs": [
        0
      ],
      "name": "Xibei Zhang",
      "orcid": "0009-0008-4806-9775"
    },
    {
      "affs": [
        0
      ],
      "name": "Xue Xiao",
      "orcid": "0000-0002-1193-463X"
    },
    {
      "affs": [
        0
      ],
      "name": "Peter V. Coveney",
      "orcid": "0000-0002-8787-7256"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2rxgjj6q3518p.bib",
  "cited_by": 20,
  "doi": "10.1021/acs.jctc.6c01334",
  "fulltext_url": null,
  "id": "2rxgjj6q3518p",
  "issns": [
    "1549-9618",
    "1549-9626"
  ],
  "landing_url": "https://doi.org/10.1021/acs.jctc.6c01334",
  "language": "en",
  "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",
      "3002|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7172444685",
  "pdf_url": "https://pubs.acs.org/jctcce/article-pdf/22/15/7811/66332197/acs.jctc.6c01334.pdf",
  "pmcid": "PMC13472093",
  "pmid": "42579383",
  "published": "2026-07-29",
  "publisher": "American Chemical Society",
  "ris": "https://research.draconitic.com/paper/2rxgjj6q3518p.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:00Z",
      "native_id": "W7172444685",
      "source": "openalex",
      "url": "https://doi.org/10.1021/acs.jctc.6c01334"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:3002|Computational Drug Discovery Methods",
      "subfield": "medicinal"
    }
  ],
  "title": "Reliability of AI Methods in Drug Discovery: Evaluation of Boltz-2 for Structure and Binding Affinity Prediction",
  "title_text": "Reliability of AI Methods in Drug Discovery: Evaluation of Boltz-2 for Structure and Binding Affinity Prediction",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:17Z",
  "url": "https://research.draconitic.com/paper/2rxgjj6q3518p",
  "venue": "Journal of Chemical Theory and Computation",
  "versions": []
}