RDBridge: a knowledge graph of rare diseases based on large-scale text mining

Bioinformatics · 5 authors, 5 centres

AI SUMMARY

FIDELITY 100%

This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.

AGENT 01 · STRUCTURED SUMMARY

TRACE TO SOURCE

“

TL;DR

This paper presents RDBridge, a comprehensive knowledge graph and web resource for rare diseases constructed by applying text mining and deep learning models to a large biomedical literature corpus. The framework identified thousands of rare diseases and their associated entities like genes, drugs, and pathways to support research.

Full summary

651 CHARS

The authors developed a framework using text mining and knowledge graphs to address the scarcity of structured data on rare diseases. They fine-tuned deep learning models (BioALBERT, ResNet-50, EfficientNet-B5) on the PMC Open Access Subset to extract entities (diseases, genes, drugs) and relationships. The web interface allows searching for genes, potential drugs, pathways, literature, and medical images. The study's primary contribution is the development of this automated data acquisition and visualization framework. Limitations include the need for experimental verification of mined relationships and that it cannot replace manual curation.

STUDY TYPE

other

SPECIALTY

research methods

SUMMARISED BY

AI pipeline

FIDELITY CHECK

100% · A

ORIGINAL PAPER

PMC10368801

RDBridge: a knowledge graph of rare diseases based on large-scale text mining

Bioinformatics

READ THE FULL PAPER

ABSTRACT

Abstract Motivation Despite low prevalence, rare diseases affect 300 million people worldwide. Research on pathogenesis and drug development lags due to limited commercial potential, insufficient epidemiological data, and a dearth of publications. The unique characteristics of rare diseases, including limited annotated data, intricate processes for extracting pertinent entity relationships, and difficulties in standardizing data, represent challenges for text mining. Results We developed a rare disease data acquisition framework using text mining and knowledge graphs and constructed the most comprehensive rare disease knowledge graph to date, Rare Disease Bridge (RDBridge). RDBridge offers search functions for genes, potential drugs, pathways, literature, and medical imaging data that will support mechanistic research, drug development, diagnosis, and treatment for rare diseases. Availability and implementation RDBridge is freely available at http://rdb.lifesynther.com/ .

CITATION EXPORT

Huadong Xing, Dachuan Zhang, Pengli Cai et al.. RDBridge: a knowledge graph of rare diseases based on large-scale text mining. Bioinformatics. (2023). https://doi.org/10.1093/bioinformatics/btad440

AUTHORS

5 · 5 CENTRES

Huadong Xing, Dachuan Zhang, Pengli Cai, Rui Zhang, Qian-Nan Hu

1 CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China
2 Institute of Environmental Engineering, ETH Zurich, Zurich 8093, Switzerland
3 CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China
4 CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China
5 CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China