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

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/.

Figure 1.

Framework of RDBridge. The workflow comprises a comprehensive series of stages designed to systematically process scientific documents to extract rare disease information. These stages encompass several critical processes, including document downloading, pre-processing, named entity recognition, relation extraction, data matching, binary classification model training, model retraining, knowledge discovery, and the use of web servers.