Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Microbial named entity recognition and normalisation for AI-assisted literature review and meta-analysis.

Dhylan Patel1,2, Antoine D Lain1, Avish Vijayaraghavan1,3

  • 1Section of Bioinformatics, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London, London W12 0NN, United Kingdom.

Bioinformatics (Oxford, England)
|June 21, 2026
PubMed
Summary

Related Concept Videos

Automated Microbial Diagnostics01:24

Automated Microbial Diagnostics

Automated diagnostic analyzers have transformed clinical microbiology by providing rapid and reliable methods for pathogen identification and antibiotic susceptibility testing. Among these systems, the Vitek 2 is widely used because it automates the traditionally labor-intensive processes of microbial identification (ID) and antibiotic susceptibility testing (AST), delivering standardized and timely results that are essential for effective patient care.Microbial Identification with ID CardsThe...
MALDI-TOF Mass Spectrometry01:19

MALDI-TOF Mass Spectrometry

Mass spectrometry is a powerful characterization technique that can identify and separate a wide variety of compounds ranging from chemical to biological entities, based on their mass-to-charge ratio (m/z). The instruments that allow this detection, known as mass spectrometers, have three components: an ion source, a mass analyzer, and a detector. These spectrometers differ based on the nature of their ion source and analyzers.Matrix-assisted laser desorption ionization (MALDI) is a commonly...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Toward Efficient and Generalizable Text Dataset Distillation via a Dual-Agent Large Language Model Framework.

International journal of neural systems·2026
Same author

A micropeptide encoded by the lncRNA USP30-AS1 promotes tumor growth by attenuating cGAS-STING-type I IFN signaling in macrophages.

Nature cancer·2026
Same author

Albumin-Bound Paclitaxel (SYHX2011) in Patients with Advanced Breast Cancer: A Multicenter, Randomized, Double-Blind, Phase III Study.

Cancer communications (London, England)·2026
Same author

Effects of N-carbamylglutamate on down yield and quality and thyroid transcriptome in breeding Huoyan geese.

Poultry science·2026
Same author

Haemoperfusion Combined With Xuebijing Injection Improves Inflammatory Status And Prognosis In Patients With End-Stage Renal Disease.

Journal of visualized experiments : JoVE·2026
Same author

Is there a bidirectional relationship between the number of unhealthy lifestyle factors and depressive symptoms in adolescents? Evidence from a longitudinal study.

BMC medicine·2026

We developed deep learning models trained on a novel microbiome-specific text corpus for accurate named-entity recognition (NER) and entity linking (EL). These models significantly outperform existing methods, enabling efficient meta-analysis of microbiome literature.

Area of Science:

  • Microbiome research
  • Bioinformatics
  • Computational biology

Background:

  • Manual curation of biomedical literature is time-consuming and prone to errors.
  • General large language models lack the domain-specific expertise for accurate biomedical text analysis.
  • There is a need for automated methods to efficiently process and analyze the growing body of microbiome literature.

Purpose of the Study:

  • To create the first microbiome-specific text corpus.
  • To train deep learning algorithms for named-entity recognition (NER) and entity linking (EL) within microbiome literature.
  • To demonstrate the utility of these models for meta-analyzing microbiome research.

Main Methods:

  • Development of a specialized text corpus for the microbiome domain.

Related Experiment Videos

  • Training deep learning models, including a fine-tuned BioBERT model, for NER and EL tasks.
  • Evaluation of model performance against a gold-standard test set and a rule- and dictionary-based pipeline.

    • Main Results:

    • The fine-tuned BioBERT model achieved a 96% F1-score for NER, outperforming the pipeline (94%).
    • Deep learning models demonstrated superior accuracy for EL (91%) compared to the pipeline (69%).
    • Models can annotate a full-text document in approximately 7 seconds, processing 6,927 documents across 14 domains.

    Conclusions:

    • The developed deep learning models provide accurate and efficient tools for analyzing microbiome literature.
    • The microbiome-specific corpus and trained models facilitate automated meta-analysis, overcoming limitations of manual curation.
    • The resources, including code and datasets, are publicly available to support further research and application.