{
  "abstract": "pH plays a key role in many biological processes. When the solution pH equals the isoelectric point (pI) of a protein, the protein carries zero net charge, which minimizes its solubility and thus promotes aggregation. Here we present ESMpI, a sequence-based protein pI predictor that combines optimized pKa values of seven ionizable residue types and two terminals with embeddings from a pre-trained protein language model. Benchmarked against experimental protein pI values, ESMpI outperforms other state-of-the-art methods, including structure-based approaches that derive the pI of a protein from residue-specific pKa calculations. Finally, ESMpI requires only sequence information, making it well suited for high-throughput proteomescale analyses and protein engineering.",
  "abstract_shown": true,
  "affiliations": [
    "College of Computer Engineering",
    "Jimei University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Fangfang Luo"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Xiangxiang Lu"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Zhitao Cai"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Hongyu Lin"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Yandong Huang",
      "orcid": "0000-0003-4025-6767"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/49bras89esjxn.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009857/v1",
  "fulltext_url": null,
  "id": "49bras89esjxn",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009857/v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7220459789",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009857/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-05",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/49bras89esjxn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15009857",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009857/v1"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Machine Learning in Bioinformatics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Protein Language Model-Boosted Prediction of Isoelectric Point",
  "title_text": "Protein Language Model-Boosted Prediction of Isoelectric Point",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/49bras89esjxn",
  "venue": "ChemRxiv",
  "versions": []
}