FDA announcements, peer-reviewed publications, or official press releases from the Kempner Institute or Harvard Medical School

Open-Access AI Model TxGNN Repurposes Drugs for Rare Diseases Affecting 300 Million

Sep 25, 2024, 01:26 PM

Artificial intelligence (AI) is making significant strides in the field of drug discovery, particularly in repurposing existing drugs for rare diseases. A new, open-access AI model, TxGNN, developed by researchers at the Kempner Institute and Harvard Medical School, has been highlighted in a study published in Nature Medicine. This model is designed to identify potential therapies from existing medicines for thousands of diseases, including those with no or limited treatment options. TxGNN has been trained on data from 17,080 diseases and 7,957 drugs, enabling it to predict drug candidates for conditions that currently lack FDA-approved treatments. The model's ability to repurpose drugs is seen as a breakthrough, potentially benefiting the 300 million people worldwide affected by rare diseases.