MIT team uses generative AI to design new antibiotics active against gonorrhoea and MRSA
James Collins's group generated and screened more than 36 million candidate molecules, then synthesised a small set. Two structurally novel compounds, NG1 against drug-resistant Neisseria gonorrhoeae and DN1 against MRSA, worked in mouse infection models by disrupting bacterial membranes; the work appeared in Cell and Phare Bio is taking both into preclinical development.
Why it matters
It is among the clearest demonstrations of generative chemistry producing new-scaffold antibiotics that work in animals, a field starved of new drug classes.
Line of Thought
Follow this story
Pick any item to keep going. Your path builds up above as a line you can share.
What led here
Earlier developments on the same thread
- DevelopmentGoogle unveils Gemini-based 'AI co-scientist' with lab-validated hypotheses19 Feb 2025 · Research · US, GB
What happened next
Later developments on the same thread
- DevelopmentFDA and EMA issue ten joint principles for AI in drug development14 Jan 2026 · Policy · US, EU
- DevelopmentDeepMind releases AlphaGenome Atlas scoring all 9bn single-letter human DNA changes8 Sep 2026 · Launch · GB, US
- DevelopmentAnthropic says Claude agents found a new CRISPR-like enzyme system in phage DNA23 Sep 2026 · Research · US
- DevelopmentGoogle DeepMind publishes SynthID Bio watermarking for AI-designed proteins in Nature30 Sep 2026 · Research · GB, US
Same story elsewhere
What other countries and bodies did on this
- DevelopmentInsilico doses first patients in Phase III trial of AI-discovered drug rentosertib10 Sep 2026 · Research · CN
- DevelopmentIsomorphic Labs raises $2.1bn for its AI drug-design engine12 May 2026 · Deal · GB
Threads by topic: Drug discovery Biology Materials