Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Microbial Named Entity Recognition and Normalisation for AI-assisted Literature Review and Meta-Analysis.

Dhylan Patel^1,2, Antoine D Lain¹, Avish Vijayaraghavan^1,3

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

Bioinformatics (Oxford, England)

|June 21, 2026

Summary

Related Concept Videos

Automated Microbial Diagnostics

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 Spectrometry

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

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

Same author

Development of a predictive nomogram for perioperative lower extremity deep vein thrombosis in patients with breast cancer and the efficacy of dextran 40 prophylaxis.

American journal of cancer research·2026

Same author

Spatially Decoupled Redox Activities Enable High Capacity and Fast Kinetics in Co-Free Li-Rich Cathodes.

ACS applied materials & interfaces·2026

Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026

Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026

Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026

Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026

Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026

Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026

See all related articles

This summary is machine-generated.

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.

Keywords:

AI-assisted literature review biomedical literature corpus deep learning microbiome named entity normalisation named entity recognition natural language processing text mining

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.