{
  "abstract": "Peptide-protein affinity models are often evaluated with a single data split, obscuring whether they interpolate among measurements for observed targets or generalize across peptide or target shifts. We integrated three sources of quantitative peptide-protein binding data to obtain 11,349 deduplicated pairs and benchmarked ten peptide representations, ESM-2 protein embeddings, and six regressors under peptide-similarity, within-target, and leave-target-out partitions. Across 60 matched representation-regressor configurations, mean test Spearman correlations were 0.462, 0.669, and 0.530, respectively. The top configuration shifted from ECFP-16 count fingerprints with random forest in the first two settings to HELM-BERT with Extra Trees when exact target sequences were excluded. Representation-rank correlations ranged from -0.042 to 0.624 across partitions, whereas regressor-rank correlations ranged from 0.771 to 0.943. Learning curves showed that representation differences were largest with limited supervision and narrowed as training data increased. PeptideCLM-2 adaptation and simple element-wise interaction features provided no consistent gain over a frozen encoder and direct concatenation under the tested protocols. These conclusions are specific to a dataset that pools transformed Kd, Ki, and IC50 measurements and to target exclusion at the exact-sequence level. Peptide-protein affinity benchmarks should therefore align data partitions with the intended use and jointly assess the effects of data scale, molecular representation, and downstream learner.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.30175",
  "author_total": 3,
  "authors": [
    {
      "name": "Jiaxin Tian"
    },
    {
      "name": "Darren An"
    },
    {
      "name": "Jun Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6cnmkwdv76nzg.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.30175",
  "fulltext_url": null,
  "id": "6cnmkwdv76nzg",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.30175",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7204918559",
  "pdf_url": "https://arxiv.org/pdf/2608.30175",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-31",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6cnmkwdv76nzg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:49Z",
      "native_id": "2608.30175",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.30175"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts",
  "title_text": "Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:49Z",
  "url": "https://research.draconitic.com/paper/6cnmkwdv76nzg",
  "venue": "arXiv",
  "versions": []
}