{
  "abstract": "Protein language models (PLMs) trained on evolutionary sequences learn representations that encode protein structure, enabling direct structure prediction without multiple-sequence alignments (MSAs). Here we present the Atlas model family, an open and trainable system spanning protein language modeling, monomer folding, and protein-complex prediction. AtlasLM-3B is a 3B-scale language model trained with masked language modeling on approximately 1.56 billion sequences, including metagenomic data, and outperforms the similarly sized ESM2-3B in unsupervised contact prediction. Building on these representations, AtlasFold predicts all-atom protein structures and achieves state-of-the-art accuracy among PLM-based folding models. Fine-tuning AtlasFold for protein-complex prediction produces AtlasFold-Multimer (AtlasFold-M), whose antibody-antigen prediction performance is comparable to that of AlphaFold3 and ESMFold2. This protein-specific folding architecture enables fast, memory-efficient inference with AtlasFold and AtlasFold-M. By releasing the training code and data, stage checkpoints, and model weights under the MIT License, we provide a foundation for advancing PLM-based protein structure prediction.",
  "abstract_shown": true,
  "affiliations": [
    "Korea Advanced Institute of Science and Technology (KAIST)"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "S. Seo"
    },
    {
      "name": "H. Kim"
    },
    {
      "name": "S. Moon"
    },
    {
      "name": "W. Y. Kim"
    },
    {
      "name": "Team KAIST"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8thjrvqmse04e.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.04.749352",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749352v1.full",
  "id": "8thjrvqmse04e",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749352v1",
  "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|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7211936314",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749352v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8thjrvqmse04e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:03Z",
      "native_id": "10.64898/2026.09.04.749352",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749352v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "AtlasFold: Protein structure prediction with metagenomic-scale language models",
  "title_text": "AtlasFold: Protein structure prediction with metagenomic-scale language models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:07Z",
  "url": "https://research.draconitic.com/paper/8thjrvqmse04e",
  "venue": "bioRxiv",
  "versions": []
}