EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interaction-finder: automated literature-based discovery of biological entity associations with quote-level provenance

Timothy Chapman iD, Timo Lassmann iD

Briefings in Bioinformatics · 02.11.2026 · 27 (6)

DOI: 10.1093/bib/bbag624 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 13.11.2026. Verfasst von Timothy Chapman und 1 weiteren Autor:innen. Beteiligte Einrichtung: Precision Health, The Kids Research Institute Australia, University of Western Australia, Perth Children's Hospital, 15 Hospital Avenue, Nedlands, WA…. Hauptthemen laut MEDLINE: Data Mining, Software, Computational Biology. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Government Research Training Program Scholarship.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying interactions between biological entities is a cornerstone of molecular research, but assembling such lists from the literature is slow and tedious. For many research questions, no curated database exists, leaving researchers to survey the relevant literature themselves. We present interaction-finder, a tool that automates this process: given a topic string and user-defined entity types, it discovers relevant literature through LLM-guided iterative search, extracts candidate associations from full-text articles, and produces a ranked list where every association is backed by quoted passages verified against the source text. A self-contained interactive HTML report enables rapid triage of the results. Evaluated across 60 topics in three domains (celltype–cellmarker, disease–gene, and ligand–receptor), interaction-finder recovers up to 4.3× as many known associations as the best of single-shot prompting and an off-the-shelf deep-research framework, with all extracted quotes verified against source text. To assess candidates unrecognised from the gold-standard databases, we scored each candidate using an independent LLM judge blind to the tool’s reasoning. Across the three domains, unverified candidates score similarly to gold-standard associations. We find the gold-standard associations are enriched at the top of our ranked candidates, with an overall recall@20 of 0.61. Interaction-finder is freely available at https://github.com/tecosaur/interaction_finder under an MIT licence.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Data MiningSoftwareComputational BiologyHumansLarge Language ModelsDatabases, FactualBiocuration

Stichwörter der Autor:innen

biomedical relation extractionlarge language modelsliterature mining

Autor:innen und Institutionen

  • Precision Health, The Kids Research Institute Australia, University of Western Australia, Perth Children's Hospital, 15 Hospital Avenue, Nedlands, WA 6009, Australia.

ORCID-Profile: Timothy Chapman, Timo Lassmann

Förderung

  • Australian Government Research Training Program Scholarship

Zitieren

APA

Chapman, T., & Lassmann, T. (2026). Interaction-finder: automated literature-based discovery of biological entity associations with quote-level provenance. Briefings in Bioinformatics, 27(6). https://doi.org/10.1093/bib/bbag624

Vancouver

Chapman T, Lassmann T. Interaction-finder: automated literature-based discovery of biological entity associations with quote-level provenance. Briefings in Bioinformatics. 2026;27(6). doi:10.1093/bib/bbag624

BibTeX
@article{Chapman2026,
  author = {Chapman, Timothy and Lassmann, Timo},
  title = {Interaction-finder: automated literature-based discovery of biological entity associations with quote-level provenance},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {6},
  doi = {10.1093/bib/bbag624}
}
Kostenlos starten →