A new structural class of antibiotic candidates against MRSA
Graph neural networks trained on 39,312 assayed compounds and applied to 12 million molecules surfaced a chemical class active against MRSA in mice, with the substructures driving each prediction made explicit rather than left opaque.
- Model
- Ensembles of graph neural networks with substructure attribution
- Field
- Chemistry
- Date
- 2023-12-20
- Human collaborators
- Felix Wong, Erica Zheng, James Collins
What was found
The team measured antibiotic activity and human-cell cytotoxicity for 39,312 compounds, trained network ensembles on that data, and predicted both properties for over 12 million molecules. Rather than reading off top scores, they extracted the chemical substructures the models were keying on, which let them pick a class rather than isolated hits. Two lead compounds cleared MRSA infection in mouse models, topically and systemically, and appear to kill by collapsing the electrochemical gradient across the bacterial membrane. Published in Nature.
Novelty check
This is the same group's follow-up to the 2020 halicin work and to abaucin (2023); the new element is selecting a structural class via model interpretation instead of screening for individual hits. "New structural class" is a claim about scaffold novelty relative to clinical antibiotics, checked against known antibiotic chemotypes in the paper.
Caveats and known objections
These are candidates, not drugs: mouse models only, with no clinical development at the time of this entry. The mechanism, disrupting membrane potential, is the same one halicin uses, so the novelty is structural rather than mechanistic, and membrane-active compounds carry a known mammalian-toxicity risk. The screening library, assays and interpretation were human-run; the model scored and explained.
Nobody outside the lab has checked this yet.
Reading the primary source closely enough to say whether it supports the claim counts as a check, and you are credited on the entry.
Or on GitHub: submit a check challenge the grade send a correction or send a pull request
Flag this for triage
Signals order the review queue and nothing else. They are never published, and they never move a grade: that takes a citation.
Entry history (1 event)
- AddedEntered the registry graded Peer reviewed and Search scaffold.
Entries are never deleted. A grade that does not hold up is downgraded on the record, with the reason beside it.
Graded peer reviewed for verification and search scaffold for autonomy. What these mean.
Cite this entry
whataifound.org. (2023). A new structural class of antibiotic candidates against MRSA. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2023-12-20-antibiotic-structural-classBibTeX
@misc{whataifound-mit-2023-class,
title = {A new structural class of antibiotic candidates against MRSA},
author = {{whataifound.org}},
year = {2023},
howpublished = {whataifound.org: A Registry of AI Scientific and Mathematical Discoveries},
note = {Result by MIT / Broad Institute / Harvard. Verification: Peer reviewed. Autonomy: Search scaffold.},
url = {https://whataifound.org/finding/2023-12-20-antibiotic-structural-class}
}