{
  "abstract": "Protein language models (PLMs) are trained primarily on individual protein sequences, yet many peptide-discovery problems require inference from only a small number of labeled examples. Here, we show that single-sequence PLMs can perform in-context peptide learning without gradient updates, task-specific retraining, or architectural modification. We introduce multi-peptide example prompts (MPEPs), in which demonstration peptides are concatenated with glycine spacers and used as context for scoring query peptides by their prompted probability. We evaluate this approach across a synthetic pattern-completion task, secondary-structure classification, and MHC-II binder prediction using both encoder-only ESM-2 models and decoder-only ProGen2 models. Across tasks, performance improves with the number of peptide examples and with model scale, indicating that PLMs can extract shared sequence-level properties from prompted examples. We further introduce a difference score that contrasts positive-example and negative-example MPEPs, reducing compositional biases in raw PLM probabilities and substantially improving classification. On MHC-II binder prediction, MPEP-based classification with larger ESM-2 models matches or exceeds low-data classifiers trained on frozen ESM-2 embeddings, while requiring no training. These results reveal an unexpected in-context inference capability in single-sequence PLMs and establish MPEP conditioning as a lightweight strategy for low-data peptide classification.",
  "abstract_shown": true,
  "affiliations": [
    "Cornell University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "J. Almonte"
    },
    {
      "name": "M. T. Vu"
    },
    {
      "name": "A. Ahn"
    },
    {
      "affs": [
        0
      ],
      "name": "E. H. Thiede"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/atvebw7n3tkf1.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.26.747074",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.08.26.747074v2.full",
  "id": "atvebw7n3tkf1",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.08.26.747074v2",
  "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",
      "biochemistry"
    ],
    [
      "openalex",
      "1312|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7204480085",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.08.26.747074v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/atvebw7n3tkf1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:31Z",
      "native_id": "10.64898/2026.08.26.747074",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.08.26.747074v2"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Machine Learning in Bioinformatics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Multi-Peptide Prompting Enables In-Context Learning in Protein Language",
  "title_text": "Multi-Peptide Prompting Enables In-Context Learning in Protein Language",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:31Z",
  "url": "https://research.draconitic.com/paper/atvebw7n3tkf1",
  "venue": "bioRxiv",
  "versions": []
}