{
  "abstract": "Optimizing protein expression and buffer conditions is a major challenge in life-science research and biotechnology. We present an LLM-powered extraction pipeline that systematically converts unstructured scientific literature into a structured, queryable database. Leveraging advanced optical character recognition, custom reranker models, and large language models, our system achieves ~97% extraction accuracy. By processing 100 353 structural biology publications associated with the RCSB Protein Data Bank, we constructed a database containing 947 153 distinct buffer entries and 73 210 expression protocols for 35 690 unique proteins, establishing the largest resource of its kind. The ProBufEx (https://www.probufex.org/) web platform enables rapid exploration of optimal conditions by protein properties or functions. Case studies reveal distinct patterns in chemical usage on proteins with different post-translational modifications, and function-dependent expression strategies for proteins with different enzymatic activities. This resource transforms vast structural biology literature into actionable knowledge, accelerating evidence-based protocol design, reducing trial-and-error, and streamlining experiments in protein science.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Biological Sciences, National University of Singapore, 14 Science Drive 4, Singapore 117543, Singapore."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Zhuojian Chen",
      "orcid": "0009-0007-9772-0010"
    },
    {
      "affs": [
        0
      ],
      "name": "Eng Aloysius"
    },
    {
      "affs": [
        0
      ],
      "name": "J Sivaraman",
      "orcid": "0000-0001-9781-5326"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2dchzy8pvsk3n.bib",
  "cited_by": 0,
  "doi": "10.1093/bib/bbag570",
  "fulltext_url": "https://europepmc.org/articles/PMC13685770",
  "id": "2dchzy8pvsk3n",
  "issns": [
    "1467-5463",
    "1477-4054"
  ],
  "landing_url": "https://europepmc.org/article/MED/42905769",
  "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": [
    [
      "openalex",
      "1312|Biomedical Text Mining and Ontologies"
    ]
  ],
  "openalex": "W7223159358",
  "pdf_url": "https://europepmc.org/articles/PMC13685770?pdf=render",
  "pmcid": "PMC13685770",
  "pmid": "42905769",
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2dchzy8pvsk3n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:57Z",
      "native_id": "MED:42905769",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42905769"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Biomedical Text Mining and Ontologies",
      "subfield": "molecular-biology"
    }
  ],
  "title": "An advanced LLM-powered article extraction pipeline delivers a database of buffers for protein studies and protein expression conditions.",
  "title_text": "An advanced LLM-powered article extraction pipeline delivers a database of buffers for protein studies and protein expression conditions.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:57Z",
  "url": "https://research.draconitic.com/paper/2dchzy8pvsk3n",
  "venue": "Briefings in bioinformatics",
  "versions": []
}