{
  "abstract": "Data scarcity is a major bottleneck in artificial intelligence (AI)-guided peptide engineering, where experimental training sets often contain only tens to a few hundred sequences, and it is difficult to judge in advance whether a protein language model (PLM) will effectively guide iterative discovery before committing to wet-lab work. Here we present SCARSE, a machine learning framework that couples ESM2 protein language model embeddings with Gaussian process regression. Benchmarked across 24 diverse peptide and small-protein datasets spanning substitution and indel variants, antimicrobial peptides, and hemolytic peptides, SCARSE significantly outperformed hand-engineered descriptor baselines on substitution and indel tasks in low-data regimes (20-500 training samples) and performed comparably on short non-mutant peptides. In active learning simulations it consistently prioritized high-performing candidates, discovering up to 7-fold more top-tier peptides than random sampling. Cross-validation (CV) R2 correlated strongly with final active learning performance (Pearson r = 0.80-0.84), and evaluating on as few as 50 labeled peptides reduced CV R2 variance enough for it to serve as a practical, data-efficient criterion for assessing model suitability before iterative screening. SCARSE thus provides an early diagnostic indicator for active learning success and is freely available as an open-source Python package (pip) and through an interactive Hugging Face Spaces web interface.",
  "abstract_shown": true,
  "affiliations": [
    "Division of Molecular Bioscience, Department of Life Sciences, Chalmers University of Technology"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "L. Andrekson"
    },
    {
      "name": "R. Rydbergh"
    },
    {
      "name": "R. Mercado"
    },
    {
      "affs": [
        0
      ],
      "name": "M. Wenzel"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/db8g0j054411z.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.06.25.734678",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.06.25.734678v2.full",
  "id": "db8g0j054411z",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.06.25.734678v2",
  "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",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7166846010",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.06.25.734678v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-25",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/db8g0j054411z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:12Z",
      "native_id": "10.64898/2026.06.25.734678",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.06.25.734678v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "AI-guided discovery for low-resource peptide engineering using evolutionary scale modeling",
  "title_text": "AI-guided discovery for low-resource peptide engineering using evolutionary scale modeling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:12Z",
  "url": "https://research.draconitic.com/paper/db8g0j054411z",
  "venue": "bioRxiv",
  "versions": []
}