{
  "abstract": "Background: Protein-protein interactions govern essential cellular processes, making the identification of interface residues critical for protein engineering and molecular design. Although complex deep learning algorithms like AlphaFold3 generate full atom resolution assemblies, they are not optimized for residue-level interface identification. Existing methods face inherent limitations: sequence-based models lack explicit 3D context, while structure-based approaches can overlook evolutionary signals. Results: By combining evolutionary context with 3D geometry, the multimodal protein language model ESM3 offers the ideal foundation for residue-level interface classification. This results in the ESM3-PPISites model, which outperforms existing state-of-the-art methods across diverse training and benchmark sets. Generalization is assessed through stringent sequence- and structure-based redundancy filtering to ensure evaluation on previously unseen proteins. Notably, finetuning the open-weight ESM3 architecture meaningfully narrows the performance gap with its proprietary full-scale counterpart. Furthermore, integrating predicted interaction sites as spatial restraints into HADDOCK significantly improves the recovery of near-native binding poses while reducing computational search time by an order of magnitude compared with blind docking. Conclusions: ESM3-PPISites enables accurate interfaces identification without relying on complex structural inputs at inference time, establishing a reliable and computationally efficient strategy for mapping protein-protein interaction sites.",
  "abstract_shown": true,
  "affiliations": [
    "AREA Science Park"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "Y. Gardinazzi"
    },
    {
      "name": "E. N. Villegas Garcia"
    },
    {
      "name": "S. Senci"
    },
    {
      "name": "D. Di Vora"
    },
    {
      "name": "A. Feltrin"
    },
    {
      "affs": [
        0
      ],
      "name": "F. Cuturello"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/awd47yc63kwrq.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.05.29.728739",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.05.29.728739v3.full",
  "id": "awd47yc63kwrq",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.05.29.728739v3",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7163204050",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.05.29.728739v3.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/awd47yc63kwrq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:51Z",
      "native_id": "10.64898/2026.05.29.728739",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.05.29.728739v3"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Learning Protein-Protein Interaction Interfaces from Multimodal Representations",
  "title_text": "Learning Protein-Protein Interaction Interfaces from Multimodal Representations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:51Z",
  "url": "https://research.draconitic.com/paper/awd47yc63kwrq",
  "venue": "bioRxiv",
  "versions": []
}