The U.S. Department of Health and Human Services (HHS), through the Advanced Research Projects Agency for Health (ARPA-H), has announced funding for the Transforming Antibiotic R&D with Generative AI to stop Emerging Threats (TARGET) project. This initiative aims to use artificial intelligence to accelerate the discovery and development of new classes of antibiotics, addressing the growing threat of antimicrobial resistance (AMR).

"Antibiotic resistance is a real and urgent threat affecting millions of people. We need to prevent infections and conserve the antibiotics we have. We also urgently need new drugs to treat these increasingly resistant infections. This project will use AI to speed this needed innovation and help ensure we have the medicines we need to keep people alive," said Secretary Xavier Becerra.

Bacterial infections are a leading cause of death worldwide, and there is an urgent need for new antibiotics as antibiotic-resistant bacteria become more prevalent. Traditional methods for identifying and developing new antibiotics involve extensive manual screening and testing, with many compounds failing to show antibiotic activity. TARGET aims to address this issue by using deep learning techniques to identify biomolecules with antibiotic potential and generative AI to expand the pool of candidate molecules.

"The rise of antibiotic resistance threatens to turn once-treatable infections into life-threatening ones, but with AI, we can accelerate the discovery of new antibiotics to address this threat like never before," said ARPA-H Director Dr. Renee Wegrzyn. "With TARGET, ARPA-H is bringing together experts across antibiotic discovery, AI, and clinical testing to ensure we can refill the global pipeline of antibiotics and stop people from becoming seriously ill due to treatable infections."

The TARGET project will be led by Phare Bio in collaboration with the Collins Lab at MIT and Harvard’s Wyss Institute, with a budget up to $27 million. The research team will focus on three main areas:

1. Use generative AI: TARGET will expand the number of molecules screened for antibiotic activity by including libraries such as Broad Institute’s Drug Repurposing Hub and ZINC15 library, which collectively hold 107 million molecule candidates.

2. Use deep learning: The project will develop digital screening tools using deep learning techniques to assess each molecule's effectiveness as an antibiotic.

3. Validate discoveries: Each promising discovery will be validated for antibiotic activity and drug-like properties, aiming to identify 15 promising leads for new antibiotics.

This initiative exemplifies U.S leadership in combating AMR through collaboration with governments, non-governmental organizations, private sector entities, and other partners.

TARGET follows ARPA-H's Defeating Antibiotic Resistance through Transformative Solutions (DARTS) project announced last year.

To learn more about awarded projects visit the project awardee page.