EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

An advanced LLM-powered article extraction pipeline delivers a database of buffers for protein studies and protein expression conditions

Zhuojian Chen iD, Eng Aloysius, J Sivaraman iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag570 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Zhuojian Chen und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biological Sciences, National University of Singapore, 14 Science Drive 4, Singapore 117543, Singapore. Hauptthemen laut MEDLINE: Databases, Protein, Data Mining, Proteins, Computational Biology. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Ministry of Education, Singapore, NUS Inter Fund, National University of Singapore.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Databases, ProteinData MiningProteinsComputational BiologyLarge Language ModelsBiocurationSoftware

Stichwörter der Autor:innen

LLMbuffersdatabaseliterature miningproteinsstrategies

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Biological Sciences, National University of Singapore, 14 Science Drive 4, Singapore 117543, Singapore.

ORCID-Profile: Zhuojian Chen, J Sivaraman

Förderung

  • Ministry of Education, Singapore
  • NUS Inter Fund
  • National University of Singapore

Zitieren

APA

Chen, Z., Aloysius, E., & Sivaraman, J. (2026). An advanced LLM-powered article extraction pipeline delivers a database of buffers for protein studies and protein expression conditions. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag570

Vancouver

Chen Z, Aloysius E, Sivaraman J. An advanced LLM-powered article extraction pipeline delivers a database of buffers for protein studies and protein expression conditions. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag570

BibTeX
@article{Chen2026,
  author = {Chen, Zhuojian and Aloysius, Eng and Sivaraman, J},
  title = {An advanced LLM-powered article extraction pipeline delivers a database of buffers for protein studies and protein expression conditions},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag570}
}
Kostenlos starten →