{
  "abstract": "Liquid-liquid phase separation (LLPS) of intrinsically disordered proteins drives the formation of biomolecular condensates, yet the sequence-level grammar that promotes condensation remains difficult to specify from first principles. Existing protein language models are typically trained on large, folded-protein-rich sequence corpora and may not optimally capture the compositional biases of LLPS-prone disordered proteins. Here, we show that a compact generative language model, with an architecture and size (∼17 M parameters) selected via systematic hyperparameter optimization and cross-validation, trained from scratch on a small set of phase-separating protein sequences, can learn sequence features associated with condensate formation. The model generates thousands of sequences that reproduce length-dependent trends in disorder, charge decoration, hydropathy patterning, and sequence entropy, with training and generative behavior stable across independent seeds. Homology analysis indicates that generated sequences are not full-length copies of known proteins, but instead combine short segments matching natural proteins with a novel, model-generated sequence. Descriptor-based screening of short generated sequences yielded a pool of disordered candidates, from which five synthetically feasible peptides were selected for experimental testing. Four of them show condensate-like signatures under near-physiological conditions, including droplet-like assemblies and increased turbidity. Coarse-grained phase-coexistence simulations of a subset of generated sequences with longer lengths show a broad range of phase-separation tendencies, with 12 of 89 sequences comparable to the strongly phase-separating hnRNPA1 low-complexity domain. These results suggest that compact, task-specific generative models can learn information-rich sequence grammars from small curated datasets and propose experimentally testable condensate-forming peptides.",
  "abstract_shown": true,
  "affiliations": [
    "Tata Institute of Fundamental Research Hyderabad Telangana India wabdul@tifrh.res.in jmondal@tifrh.res.in.",
    "Department of Biomedical Engineering, McKelvey School of Engineering, Washington University in St. Louis Missouri 63130 USA srudra22@wustl.edu.",
    "Department of Chemistry, Washington University in St. Louis Missouri 63130 USA."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Abdul Wasim",
      "orcid": "0000-0002-2592-4862"
    },
    {
      "affs": [
        1
      ],
      "name": "Ushasi Pramanik"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Anirban Das"
    },
    {
      "affs": [
        0
      ],
      "name": "Pikaso Latua"
    },
    {
      "affs": [
        1
      ],
      "name": "Jai S Rudra",
      "orcid": "0000-0002-7837-4980"
    },
    {
      "affs": [
        0
      ],
      "name": "Jagannath Mondal",
      "orcid": "0000-0003-1090-5199"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7a8v1p50ajf7h.bib",
  "cited_by": 0,
  "doi": "10.1039/d6sc03816f",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13726131/?tool=EBI",
  "id": "7a8v1p50ajf7h",
  "issns": [
    "2041-6520",
    "2041-6539"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13726131",
  "language": "eng",
  "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": [
    [
      "heading",
      "Chemistry"
    ],
    [
      "openalex",
      "1312|RNA Research and Splicing"
    ]
  ],
  "openalex": "W7223657656",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13726131/pdf/?tool=EBI",
  "pmcid": "PMC13726131",
  "pmid": "42974382",
  "published": "2026-10-26",
  "publisher": "Royal Society of Chemistry",
  "ris": "https://research.draconitic.com/paper/7a8v1p50ajf7h.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T15:20:51Z",
      "native_id": "PMC:PMC13726131",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13726131"
    },
    {
      "first_seen": "2026-11-04T15:20:48Z",
      "native_id": "MED:42974382",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42974382"
    },
    {
      "first_seen": "2026-11-05T12:22:32Z",
      "native_id": "PMC13726131",
      "source": "pmc",
      "url": "https://doi.org/10.1039/d6sc03816f"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|RNA Research and Splicing",
      "subfield": "molecular-biology"
    }
  ],
  "title": "A compact generative language model learns the compositional grammar of phase-separating proteins",
  "title_text": "A compact generative language model learns the compositional grammar of phase-separating proteins",
  "type": "peer-reviewed",
  "updated_at": "2026-11-06T12:22:09Z",
  "url": "https://research.draconitic.com/paper/7a8v1p50ajf7h",
  "venue": "Chemical science",
  "versions": []
}