PuSH - Publication Server of Helmholtz Zentrum München

Olayo-Alarcon, R. ; Amstalden, M.K.* ; Zannoni, A.* ; Bajramovic, M. ; Sharma, C.M.* ; Brochado, A.R.* ; Rezaei, M.* ; Müller, C.L.

Pre-trained molecular representations enable antimicrobial discovery.

Nat. Commun. 16, 15:3420 (2025)
Publ. Version/Full Text DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
The rise in antimicrobial resistance poses a worldwide threat, reducing the efficacy of common antibiotics. Determining the antimicrobial activity of new chemical compounds through experimental methods remains time-consuming and costly. While compound-centric deep learning models promise to accelerate this search and prioritization process, current strategies require large amounts of custom training data. Here, we introduce a lightweight computational strategy for antimicrobial discovery that builds on MolE (Molecular representation through redundancy reduced Embedding), a self-supervised deep learning framework that leverages unlabeled chemical structures to learn task-independent molecular representations. By combining MolE representation learning with available, experimentally validated compound-bacteria activity data, we design a general predictive model that enables assessing compounds with respect to their antimicrobial potential. Our model correctly identifies recent growth-inhibitory compounds that are structurally distinct from current antibiotics. Using this approach, we discover de novo, and experimentally confirm, three human-targeted drugs as growth inhibitors of Staphylococcus aureus. This framework offers a viable, cost-effective strategy to accelerate antibiotic discovery.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Corresponding Author
Keywords Drugs
ISSN (print) / ISBN 2041-1723
e-ISSN 2041-1723
Journal Nature Communications
Quellenangaben Volume: 16, Issue: 1, Pages: 15, Article Number: 3420 Supplement: ,
Publisher Nature Publishing Group
Publishing Place London
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Institute of Computational Biology (ICB)
Grants This work was funded by a grant for the "StressRegNet" consortium within the Bavarian research network bayresq.net funded through the Bavarian State Ministry of Science and Arts, Germany
Bavarian State Ministry of Science and Arts, Germany