{
  "abstract": "Phytoplankton drive ~46% of global primary production, yet whether their protein repertoires encode ocean conditions - and whether reference databases capture the environmentally responsive fraction - is unknown. We used a protein language model to classify 447.7 million proteins from 2,357 samples and analyzed domain profiles for 231.7 million algal proteins across 2,044 samples. Under spatial block cross-validation, environment predicted individual domain abundances at R2 up to 0.59, while domain profiles predicted sea surface temperature at R2 = 0.38. The strongest coupling lay beyond annotated sequence space: 33,950 families clustered from 201 million Pfam-dark proteins coupled to environment 2.29-fold more strongly than Pfam domains. Cross-taxonomic selection, protein language modeling, and AlphaFold 3 predictions of 138 well-folded, InterPro-unannotated representatives support the Pfam-dark proteome as a biologically structured evolutionary compartment. Thus, the proteins most tightly coupled to ocean state are those least represented in reference databases.",
  "abstract_shown": true,
  "affiliations": [
    "Division of Science, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "D. R. Nelson"
    },
    {
      "name": "M. Plouviez"
    },
    {
      "name": "S. Daakour"
    },
    {
      "name": "A. Jaiswal"
    },
    {
      "name": "W. Fu"
    },
    {
      "name": "S. A. Amin"
    },
    {
      "affs": [
        0
      ],
      "name": "K. Salehi-Ashtiani"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/02vasdpft7p3r.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.23.753693",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753693v1.full",
  "id": "02vasdpft7p3r",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753693v1",
  "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",
      "1312|Genomics and Phylogenetic Studies"
    ]
  ],
  "openalex": "W7214769779",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753693v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/02vasdpft7p3r.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:02Z",
      "native_id": "10.64898/2026.09.23.753693",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753693v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Coupling of oceanographic state to the dark proteome: a foundation for genome-informed marine productivity modeling",
  "title_text": "Coupling of oceanographic state to the dark proteome: a foundation for genome-informed marine productivity modeling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:02Z",
  "url": "https://research.draconitic.com/paper/02vasdpft7p3r",
  "venue": "bioRxiv",
  "versions": []
}