{
  "abstract": null,
  "abstract_shown": false,
  "affiliations": [
    "Department of Systems Biology, Columbia University Irving Medical Center, New York, NY, USA. ch3849@cumc.columbia.edu",
    "Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA",
    "Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA. ys2411@cumc.columbia.edu",
    "Department of Systems Biology, Columbia University Irving Medical Center, New York, NY, USA. ys2411@cumc.columbia.edu",
    "JP Sulzberger Columbia Genome Center, Columbia University, New York, NY, USA. ys2411@cumc.columbia.edu",
    "Program for Mathematical Genomics, Columbia University Irving Medical Center, New York, NY, USA. ys2411@cumc.columbia.edu"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Chao Hou",
      "orcid": "0000-0003-4806-7637"
    },
    {
      "affs": [
        1
      ],
      "name": "Ди Лю",
      "orcid": "0009-0004-2021-4468"
    },
    {
      "affs": [
        1
      ],
      "name": "Aziz Zafar",
      "orcid": "0000-0001-7284-3021"
    },
    {
      "affs": [
        2,
        3,
        4,
        5
      ],
      "name": "Yufeng Shen",
      "orcid": "0000-0002-1299-5979"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c5araxvxaktk7.bib",
  "cited_by": 18,
  "doi": "10.1038/s43588-026-01010-z",
  "fulltext_url": null,
  "id": "c5araxvxaktk7",
  "issns": [
    "2662-8457"
  ],
  "landing_url": "https://doi.org/10.1101/2025.04.25.650688",
  "language": "en",
  "licence": "unknown",
  "licence_label": "Licence not stated",
  "licence_source": "unknown",
  "licence_url": null,
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7168148931",
  "pdf_url": "https://www.biorxiv.org/content/biorxiv/early/2025/04/29/2025.04.25.650688.full.pdf",
  "pmcid": "PMC12330683",
  "pmid": "40777237",
  "published": "2026-07-13",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/c5araxvxaktk7.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:05Z",
      "native_id": "W7168148931",
      "source": "openalex",
      "url": "https://doi.org/10.1101/2025.04.25.650688"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Protein Structure and Dynamics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Understanding language model scaling for protein fitness prediction",
  "title_text": "Understanding language model scaling for protein fitness prediction",
  "type": "peer-reviewed",
  "updated_at": "2026-11-04T13:21:05Z",
  "url": "https://research.draconitic.com/paper/c5araxvxaktk7",
  "venue": "Nature Computational Science",
  "versions": []
}