{
  "abstract": "Ionization states are crucial to protein function, yet predicting their equilibrium constants remains challenging. Here we present KaML-ESMs, sequence-based neural networks built on the ESM protein language models and trained on the GAINES-augmented PKAD-3r dataset. KaML-ESM2/ESMC outperform alternative approaches across four benchmarks, achieving root-mean-square errors of about 0.5 units for Asp/Glu/His/Cys/Tyr/Lys residues in native proteins. Performance degrades on 89 buried engineered mutations lacking evolutionary support, revealing a limitation that supervised training may help overcome. These results suggest that protein sequence, through its evolutionary context, encodes not only structure and function but also, indirectly, electrostatic characteristics. Applying KaML-ESM2 to the entire human proteome, we show that predicted p K a values can identify functional sites and infer catalytic mechanisms. We offer KaML, a sequence-based p K a prediction platform supporting biological exploration, protein engineering, and biomolecular simulation. With further development, GAINES could provide a general framework for addressing data scarcity in machine learning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "Mingzhe Shen",
      "orcid": "0000-0001-7461-3764"
    },
    {
      "name": "Guy W. Dayhoff II",
      "orcid": "0000-0003-4271-7125"
    },
    {
      "name": "Daniel Kortzak"
    },
    {
      "name": "Jana Shen",
      "orcid": "0000-0002-3234-0769"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/67g7cbcw819wd.bib",
  "cited_by": 0,
  "doi": "10.1038/s41467-026-78406-y",
  "fulltext_url": null,
  "id": "67g7cbcw819wd",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://www.nature.com/articles/s41467-026-78406-y",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7223460039",
  "pdf_url": "https://www.nature.com/articles/s41467-026-78406-y_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/67g7cbcw819wd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:39Z",
      "native_id": "10.1038/s41467-026-78406-y",
      "source": "crossref",
      "url": "https://www.nature.com/articles/s41467-026-78406-y"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Machine Learning in Bioinformatics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Predicting protein electrostatics with protein language models",
  "title_text": "Predicting protein electrostatics with protein language models",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:39Z",
  "url": "https://research.draconitic.com/paper/67g7cbcw819wd",
  "venue": "Nature Communications",
  "versions": []
}