{
  "abstract": "Many phage proteins remain functionally uncharacterized despite advances in structural-similarity-based annotation. We introduce PhageFlare, a deep learning framework for predicting phage protein functions lacking significant structural matches to annotated references. Across three structure-disjoint benchmarks, where no significant Foldseek match was detected between training and test proteins (E-value thresholds of 10-3, 10-4, and 10-2), PhageFlare achieved macro-averaged F1 scores of 0.871, 0.889, and 0.738 outperforming the strongest baseline (0.789, 0.814, and 0.732). Systematic evaluations demonstrated that protein language model selection critically influences performance, with ESM-C achieving stronger overall performance than ESM-2 and ProtBert. Embedding-guided case studies revealed local structural correspondences among proteins with limited global similarity. Applied to the efam and Metagenomic Gut Virus datasets, PhageFlare annotated 38.0% and 51.8% of proteins unresolved by Foldseek, respectively. Furthermore, PhageFlare identified lysogenic potential in 1,866 prophage-designated genomes misclassified as lytic by BACPHLIP. These results show that PhageFlare complements structural-similarity-based annotation and expands functional discovery across viral dark matter.",
  "abstract_shown": true,
  "affiliations": [
    "Hong Kong Baptist University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "C. Wang"
    },
    {
      "name": "Y. Xu"
    },
    {
      "name": "Z. Li"
    },
    {
      "affs": [
        0
      ],
      "name": "L. Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "L. Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3dsrxmhvg6rv5.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.28.762509",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762509v1.full",
  "id": "3dsrxmhvg6rv5",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762509v1",
  "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",
      "microbiology"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762509v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3dsrxmhvg6rv5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:23Z",
      "native_id": "10.64898/2026.10.28.762509",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762509v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:microbiology",
      "subfield": "microbiology"
    }
  ],
  "title": "Illuminating phage dark matter beyond the reach of structural alignments with PhageFlare",
  "title_text": "Illuminating phage dark matter beyond the reach of structural alignments with PhageFlare",
  "type": "preprint",
  "updated_at": "2026-10-31T00:20:43Z",
  "url": "https://research.draconitic.com/paper/3dsrxmhvg6rv5",
  "venue": "bioRxiv",
  "versions": []
}