{
  "abstract": "Protein sequence databases are growing far faster than experimentally curated annotations, limiting functional interpretation of newly identified proteins and coding variants. We developed PALM, a protein annotation language model that jointly predicts domain and functional-site occurrence, while preserving overlapping and nested annotations through a soft-target objective. PALM integrates ESM2 with low-rank adaptation (LoRA), learned layer aggregation, and a bidirectional long short-term memory (BiLSTM) encoder. PALM was trained on ~15 million InterPro-annotated UniRef50 sequences spanning 17,951 domain and 1,383 site classes. Across 2.3 million held-out proteins, PALM achieved domain- and site-occurrence F1 scores of 0.941 and 0.877, respectively, and retained substantial performance in proteins with <20% sequence identity to the training and validation data. PALM also substantially outperformed ESM3 annotation baseline. Without training on variant-pathogenicity labels, PALM embedding disruption distinguished 151,823 ClinVar missense variants more accurately than ESM2 embedding disruption (AUROC 0.835 versus 0.710), and combining PALM embedding disruption with the ESM2 likelihood-ratio signal reached an AUROC of 0.877. The same combined zero-shot score outperformed AlphaMissense on a benchmark dataset on 128,161 missense variants, that were derived from literature but not present in ClinVar database. At the protein level, PALM embeddings showed stronger CATH-Gene3D superfamily organization than frozen ESM2 and ESM3 embeddings, and improved prediction of experimental activation and repression effects when combined with ESM2. In a downstream case study, we demonstrated the ability to use PALM-derived embedding as proxy of deep mutational scanning (DMS), showcasing the broad application of PALM. Together, PALM converts curated residue-level knowledge into transferable and mechanistically interpretable representations that connect protein sequence, function, and variant consequence.",
  "abstract_shown": true,
  "affiliations": [
    "Children's Hospital of Philadelphia"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "P. Wang"
    },
    {
      "name": "M. U. Ahsan"
    },
    {
      "name": "T. Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "K. Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/57mxcdkk0r7pf.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.03.764008",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764008v1.full",
  "id": "57mxcdkk0r7pf",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764008v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764008v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/57mxcdkk0r7pf.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T00:22:14Z",
      "native_id": "10.64898/2026.11.03.764008",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764008v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "A protein language model for domain, functional site, and variant effect prediction",
  "title_text": "A protein language model for domain, functional site, and variant effect prediction",
  "type": "preprint",
  "updated_at": "2026-11-07T00:20:59Z",
  "url": "https://research.draconitic.com/paper/57mxcdkk0r7pf",
  "venue": "bioRxiv",
  "versions": []
}