AI identifies potential new antibiotic candidates
Researchers used AI to screen 40.6 million peptide sequences and identified 386 novel candidates. Laboratory testing predicted antibacterial activity in 53 of 58 candidates tested.
By DoomRadar · Published on DoomRadar .
Why it matters
New antibiotic candidates could help address the global threat of antimicrobial resistance.
Related source links
These links were collected with this event. Recorded source dates may reflect when a link was found. Article publication dates are shown only when available from the source. Open the originals for their full context.
- Antibiotic resistance directly kills more than a million people annually, while antibiotic discovery has stagnated. In 2025, a Penn AI screened 40.6 million peptide sequences generated from venom proteins in only hours, shortlisted 386 unusually novel candidates and successfully predicted antibacterial activity in 53 of the 58 subsequently tested in the laboratory. ↗scienceblog.com · Recorded source date: Aug 25, 2026, 11:16 PM UTC
AI-assisted, source-based analysis. Methodology · Report a correction