{
  "abstract": "Motivation: Accurate peptide-MHC class II (pMHC-II) binding prediction is complicated by MHC polymorphism and context-dependent peptide recognition. Protein representations are usually evaluated in different pipelines, obscuring their contribution to predictive performance. Results: We present PREpiBind, a joint-attention framework comparing ten protein representations under a fixed architecture and identical data splits across qualitative binding, mass spectrometry, and thresholded IC50 datasets. PLMs generally achieved the strongest pooled performance; ESM3 Large reached a ROC-AUC of 0.927 +/- 0.002 on the qualitative dataset. PREpiBind PLM variants exceeded evaluated reference methods on qualitative and mass-spectrometry benchmarks, whereas NetMHCIIpan-4.3 was higher on thresholded IC50 using its binding-affinity head. PLM advantages narrowed in allele-wise and held-out MHC-molecule evaluations, and H2-out rankings depended on aggregation, indicating scenario-dependent representation performance. Availability and implementation: Source code and the training and evaluation datasets are available at https://github.com/daylight-00/PREpiBind and archived at https://doi.org/10.5281/zenodo.22934281; trained model checkpoints are available at https://huggingface.co/daylight-00/prepibind. Implemented in Python and released under the MIT License. Contact: nicole23@snu.ac.kr Supplementary information: Supplementary data are available online.",
  "abstract_shown": true,
  "affiliations": [
    "Seoul National University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "D. H. Jang"
    },
    {
      "name": "D. Kim"
    },
    {
      "name": "B. Park"
    },
    {
      "name": "U. Hwang"
    },
    {
      "name": "Y. Choi"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dm7b0tjqj7d92.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.15.751749",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751749v1.full",
  "id": "dm7b0tjqj7d92",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751749v1",
  "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|vaccines and immunoinformatics approaches"
    ]
  ],
  "openalex": "W7213976595",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751749v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dm7b0tjqj7d92.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:37Z",
      "native_id": "10.64898/2026.09.15.751749",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751749v3"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "PREpiBind: Protein Representation-integrated Epitope--MHC Class II Binding Prediction",
  "title_text": "PREpiBind: Protein Representation-integrated Epitope--MHC Class II Binding Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:16Z",
  "url": "https://research.draconitic.com/paper/dm7b0tjqj7d92",
  "venue": "bioRxiv",
  "versions": []
}