Could Artificial Intelligence be our way out of antibiotic resistance? Old hands on LSS will instantly recall a blog of ours (LSS 28 4 2020) in which we reported the use of AI to develop a new antibiotic called Halicin. Today we’re happy to report that it’s been done again, this time to produce a really exciting new compound called abaucin.
We’ve got two links for you. James Gallagher of the BBC has a nice layman-friendly explanation, but it’ll be on your media feeds somewhere today [1] But, for those who like a drop of the hard stuff, we reproduce the original paper from Nature Chemical Biology [2] The summary’s got some good graphics which explain what the authors have been up to rather well, we suggest.
Do we think this is significant? Yes, we do. That’s at least twice that AI has been trained up to produce a result. And when you consider that abaucin is due to be targeted at Acinetobacter baumannii, one of the top three on the WHO list of dangerously resistant organisms, we’re even more cheered. But for us the real good news is in the methodology. Read what James says here
……To find a new antibiotic, the researchers first had to train the AI. They took thousands of drugs where the precise chemical structure was known, and manually tested them on Acinetobacter baumannii to see which could slow it down or kill it.This information was fed into the AI so it could learn the chemical features of drugs that could attack the problematic bacterium.The AI was then unleashed on a list of 6,680 compounds whose effectiveness was unknown. The results – published in Nature Chemical Biology – showed it took the AI an hour and a half to produce a shortlist. The researchers tested 240 in the laboratory, and found nine potential antibiotics. One of them was the incredibly potent antibiotic abaucin…..
In other words, it’s repeatable. Potentially the AI techniques could be used to design other compounds. We’ve had a few blogs talking about the alpha-fold programme and protein design.(LSS passim) Potentially, we may be about to witness one of those intellectual explosions where progress crosses rapidly between different areas, and the there is an exponential leap in design and technique. We’ve been on the antibiotics story for years now, and this time it feels as if something may be about to change.
[1]https://www.bbc.co.uk/news/health-65709834
[2]https://www.nature.com/articles/s41589-023-01349-8
#AI #antibiotic resistance #abaucin #medicine #alphafold
Learning, Science and Society 