{
  "abstract": "Protein language models (PLMs) provide powerful representations of protein sequence, but their utility for proteome-scale binding-site retrieval remains unclear. Here, we present PocketScope, a training-free framework that represents cavity-lining residues using frozen ESM-C 600M embeddings and retrieves related binding sites through exhaustive late-interaction MaxSim, without pooling or approximate nearest-neighbor search. PocketScope identified 153,805 cavities across 37,682 proteins in the AlphaFold human proteome and recovered documented drug off-targets across a curated set of pharmacological pairs. On the ProSPECCTs benchmark, PocketScope ranks 1st of 23 methods by mean rank across the ten collections. PocketScope provides a practical framework for proteome-scale off-target prediction. PocketScope is open source and also freely available as a web server at https://www.bhargavaresearch.org/pocketscope.",
  "abstract_shown": true,
  "affiliations": [
    "Bhargava Systems Research Inc."
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "K. Mohan"
    },
    {
      "affs": [
        0
      ],
      "name": "Y. Bhargava"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/89xgx4a2da0xh.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.30.748136",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748136v1.full",
  "id": "89xgx4a2da0xh",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748136v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7204682361",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748136v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/89xgx4a2da0xh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:19Z",
      "native_id": "10.64898/2026.08.30.748136",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748136v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Retrieval of binding sites across the AlphaFold human proteome using protein language model representations",
  "title_text": "Retrieval of binding sites across the AlphaFold human proteome using protein language model representations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:19Z",
  "url": "https://research.draconitic.com/paper/89xgx4a2da0xh",
  "venue": "bioRxiv",
  "versions": []
}