{
  "abstract": "Protein language models (PLMs) are increasingly used to represent adaptive immune receptors, yet their advantage over classical sequence comparison remains unclear. We benchmarked general and receptor-specific PLMs against classical sequence-comparison methods for antigen-specific nearest-neighbor retrieval across four B- and T-cell receptor databases. Using CDR3 sequences alone, classical methods consistently outperformed general PLMs: BLOSUM62 and Levenshtein exceeded ESM2 variants by 7-12 percentage points in retrieval accuracy. Among receptor-specific models, only SCEPTR and, on one database, TCR2vec matched these baselines, although both additionally encoded V-gene information. AntiBERTa2 and IgBert did not close the performance gap. Using full variable-domain sequences, alignment and PLM performance converged. Germline-reversion, region-masking, and V-gene control analyses indicated that this convergence largely reflected conserved germline-derived context, particularly V-gene identity, with limited evidence for improved extraction of antigen-specific information from the CDRs. Germline dependence also extended to SCEPTR and TCR2vec. Heavily mutated HIV-1 antibodies provided a setting-specific exception to this pattern. Random train-test splits yielded retrieval accuracy 15-28 percentage points higher than clone-aware splits, consistent with optimistic performance estimates due to clonal leakage. These findings emphasize the need for strong sequence-comparison baselines and explicit germline controls when evaluating immune-receptor representations and support clone-aware splitting as a minimum benchmark standard.",
  "abstract_shown": true,
  "affiliations": [
    "Laboratory of Genome Informatics, Research Institute for Microbial Diseases, The University of Osaka, 3-1 Yamadaoka, Suita 565-0871, Japan.",
    "MyImmune Corporation, 251 Little Falls Drive, Wilmington, DE 19808, United States."
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Suyue Wang"
    },
    {
      "affs": [
        1
      ],
      "name": "Ayan Sengupta"
    },
    {
      "affs": [
        0
      ],
      "name": "Songling Li"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Daron M Standley",
      "orcid": "0000-0003-4078-0817"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/an9ajjjtswpkh.bib",
  "cited_by": 0,
  "doi": "10.1093/bib/bbag614",
  "fulltext_url": "https://europepmc.org/articles/PMC13744283",
  "id": "an9ajjjtswpkh",
  "issns": [
    "1467-5463",
    "1477-4054"
  ],
  "landing_url": "https://europepmc.org/article/MED/42998279",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|vaccines and immunoinformatics approaches"
    ]
  ],
  "openalex": "W7170765142",
  "pdf_url": "https://europepmc.org/articles/PMC13744283?pdf=render",
  "pmcid": "PMC13744283",
  "pmid": "42998279",
  "published": "2026-11-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/an9ajjjtswpkh.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T15:20:34Z",
      "native_id": "MED:42998279",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42998279"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|vaccines and immunoinformatics approaches",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Germline dependence in protein language model retrieval of adaptive immune receptors.",
  "title_text": "Germline dependence in protein language model retrieval of adaptive immune receptors.",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T15:20:34Z",
  "url": "https://research.draconitic.com/paper/an9ajjjtswpkh",
  "venue": "Briefings in bioinformatics",
  "versions": []
}