There are more than 9,000 rare and neglected diseases affecting millions globally, but information and resources are often scarce. The Therapeutics for Rare and Neglected Diseases Program, part of the National Center for Advancing Translational Sciences (NCATS), has formed a collaboration with the Advanced Biomedical Computational Science group at the Frederick National Laboratory to create a user-friendly platform for rare disease information. The main objective for the project, named RARe-SOURCE™, is to provide an innovative application and searchable interface for data mining, by integrating various bioinformatics databases and enabling users to navigate the wealth of information quickly and efficiently. 

Our contributions 

  • Manually curated variants for 2 rare diseases - Creatine Transporter Deficiency and Farber disease. 

  • Customized large language models to identify rare diseases and associated genes from published literature. 

  • Annotated rare disease gene variants with information from many knowledge sources. 

  • Deployed the first production version of RARe-SOURCETM. 

  • Co-presented RARe-SOURCETM at the 2023 NIH rare disease day.