EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GOFlowLLM—curating miRNA literature with large language models and flowcharts

Andrew Green iD, Nancy Ontiveros-Palacios, Isaac Jandalala, Simona Panni, Valerie Wood iD, Giulia Antonazzo, Helen Attrill iD, Alex Bateman iD, Blake Sweeney iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btaf683 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Andrew Green und 8 weiteren Autor:innen. Beteiligte Einrichtung: European Bioinformatics Institute, Cambridge, CB10 1SD, United Kingdom. Hauptthemen laut MEDLINE: MicroRNAs, Software, Data Curation, Computational Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: United Kingdom Research and Innovation (UKRI) Biotechnology and Biological Sciences Research Council, European Union's Horizon 2020 Marie Skłodowska-Curie Actions, Wellcome Trust.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation The exponential growth of non-coding RNA research—with over 230 000 papers published since 2000—has created an urgent knowledge management crisis in molecular biology. Despite their crucial regulatory roles, microRNAs (miRNAs) face a significant curation bottleneck, with only 1400 articles manually curated to the Gene Ontology (GO) knowledgebase over a decade. This highlights the critical need for automated systems that can accelerate biocuration while maintaining high-quality standards. Results We present GOFlowLLM, an automated curation pipeline powered by reasoning-enabled Large Language Models (LLMs) that follows established GO curation flowcharts to extract and structure miRNA-mediated gene silencing data at scale. When evaluated on existing curation, GOFlowLLM selects the correct GO term in 90% of cases, with curators agreeing with 95% of the system’s reasoning steps and 90% of the evidence selected. Applied to 6996 previously uncurated articles using the Qwen QwQ-32B model, our system identified 2538 new candidate GO annotations on 1785 articles in just 58 hours—potentially doubling the available miRNA GO curation. Manual review shows curators agreed with the selected term in 87% of cases, the model’s reasoning in 92% of cases, and the extracted evidence in 93%. The integration of reasoning traces provides transparent justification for annotations that can be reviewed by human curators, addressing a key challenge in adopting AI for scientific curation. Availability and implementation GOFlowLLM is implemented as an automated pipeline that follows expert-designed reasoning frameworks to maintain curation quality. The system is available on GitHub: https://github.com/RNAcentral/GO_Flow_LLM.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MicroRNAsSoftwareData CurationComputational BiologyGene OntologyHumansMolecular Sequence AnnotationLarge Language Models

Substanzen

MicroRNAs

Autor:innen und Institutionen

  • European Bioinformatics Institute, Cambridge, CB10 1SD, United Kingdom.
  • Biology, Ecology and Earth Science, University of Calabria, Rende, 87036, Italy.
  • Department of Biochemistry, University of Cambridge, Cambridge, CB2 1GA, United Kingdom.
  • Department of Physiology, Development and Neuroscience, University of Cambridge, Cambridge, CB2 3DY, United Kingdom.

ORCID-Profile: Andrew Green, Valerie Wood, Helen Attrill, Alex Bateman, Blake Sweeney

Förderung

  • United Kingdom Research and Innovation (UKRI) Biotechnology and Biological Sciences Research Council
  • European Union's Horizon 2020 Marie Skłodowska-Curie Actions
  • Wellcome Trust
  • Medical Research Council
  • European Molecular Biology Laboratory
  • European Union’s Horizon 2020 Marie Skłodowska-Curie Actions
  • United Kingdom Medical Research Council

Zitieren

APA

Green, A., Ontiveros-Palacios, N., Jandalala, I., Panni, S., Wood, V., Antonazzo, G., Attrill, H., Bateman, A., & Sweeney, B. (2026). GOFlowLLM—curating miRNA literature with large language models and flowcharts. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf683

Vancouver

Green A, Ontiveros-Palacios N, Jandalala I, Panni S, Wood V, Antonazzo G, et al. GOFlowLLM—curating miRNA literature with large language models and flowcharts. Bioinformatics. 2026. doi:10.1093/bioinformatics/btaf683

BibTeX
@article{Green2026,
  author = {Green, Andrew and Ontiveros-Palacios, Nancy and Jandalala, Isaac and Panni, Simona and Wood, Valerie and Antonazzo, Giulia and Attrill, Helen and Bateman, Alex and Sweeney, Blake},
  title = {GOFlowLLM—curating miRNA literature with large language models and flowcharts},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btaf683}
}
Kostenlos starten →