Researchers use AI to help repurpose drugs to treat rare diseases
Rare and undiagnosed diseases affect over 300 million people globally, posing an immense human and economic burden. These conditions, while individually rare, collectively represent a massive health challenge. Despite the urgency, only 5 to 7 percent of these diseases have an FDA-approved drug, leaving many patients without effective treatment options. A groundbreaking artificial intelligence (AI) tool offers a new pathway to address this gap. Developed by researchers at Harvard Medical School and published in the journal, Nature Medicine, the AI model, called TxGNN, has demonstrated unprecedented potential to discover therapies for rare and neglected diseases. By repurposing existing drugs, TxGNN identified treatment candidates for over 17,000 diseases, including those with no current treatments. This achievement marks a significant leap forward in drug discovery. The AI Revolution in Drug Repurposing TxGNN is a graph-based AI model specifically designed for drug repurposing. Unlike traditional approaches that focus narrowly on diseases with existing therapies, this tool analyzes shared features across diseases to identify novel drug candidates. It uses a vast dataset, including genomic information, cell signaling data, and …