Deep learning–enabled discovery of antibiotics effective against <i>Neisseria gonorrhoeae</i>

Neisseria gonorrhoeae is a common Gram-negative pathogen with increasing resistance to all recommended antibiotics. There is a critical need to improve the efficiency of the antibiotic hit discovery process to replenish the drug development pipeline. Here, we show that deep learning models can augment high-throughput screens to identify readily available molecules with narrow-spectrum activity against difficult-to-treat strains of N. gonorrhoeae . We phenotypically tested 38,650 small molecules for N. gonorrhoeae growth inhibition to train a predictive graph neural network (GNN) model. We benchmarked the model’s performance against other architectures, including a large language model, and found that GNNs more accurately identify active, drug-like molecules that are structurally distinct from the training set and known antibiotics. Using the model to virtually screen ~6 million compounds, we identified 213 compounds for experimental validation and found that 83 (39%) inhibited N. gonorrhoeae growth. Two of these compounds were structurally dissimilar to existing antibiotics, maintained potency against multidrug-resistant N. gonorrhoeae strains in vitro, exhibited promising selectivity indices, and were rapidly bactericidal with low frequencies of resistance. Proteomic studies revealed their distinct mechanisms of action, with one compound targeting alanine racemase, an enzyme involved in the essential process of peptidoglycan synthesis. Furthermore, the compounds showed early promise in reducing N. gonorrhoeae titers in a human vagina-on-a-chip infection model and a mouse vaginal infection model. Our work establishes the deep learning–enabled discovery of selective antibacterial compounds against N. gonorrhoeae as a much-needed hit discovery tool to address the growing crisis of antimicrobial resistance for this pathogen.

Authors

Institutions

Publication Details

Journal
Science Translational Medicine
Published
2026-06-17
DOI
https://doi.org/10.1126/scitranslmed.ads4699
Primary Topic
Reproductive tract infections research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deep learning–enabled discovery of antibiotics effective against Neisseria gonorrhoeae

Marie‐Stéphanie Aschtgen, Aarti Krishnan, Donald E. Ingber, Amir Ata Saei et al.
Science Translational Medicine
Reproductive tract infections research
article

Deep learning–enabled discovery of antibiotics effective against Neisseria gonorrhoeae

Marie‐Stéphanie Aschtgen, Aarti Krishnan, Donald E. Ingber, Amir Ata Saei, Melis N. Anahtar, Nina M. Donghia, Yonatan H. Grad, Erica J. Zheng, Samantha G. Palace, Andreas Luttens, Massimiliano Gaetani, Marion Gaborieau, Edmund Loh, Abidemi Junaid, Felix Wong, Parijat Bandyopadhyay, Jacqueline A. Valeri, James J. Collins, Paige Edwards, Seyed Majed Modaresi, Aakanksha Gulati, Yu Zhang, Danilo Ritz, Krishna Suresh, Alicia Jorgenson
article en

Abstract

Neisseria gonorrhoeae is a common Gram-negative pathogen with increasing resistance to all recommended antibiotics. There is a critical need to improve the efficiency of the antibiotic hit discovery process to replenish the drug development pipeline. Here, we show that deep learning models can augment high-throughput screens to identify readily available molecules with narrow-spectrum activity against difficult-to-treat strains of N. gonorrhoeae . We phenotypically tested 38,650 small molecules for N. gonorrhoeae growth inhibition to train a predictive graph neural network (GNN) model. We benchmarked the model’s performance against other architectures, including a large language model, and found that GNNs more accurately identify active, drug-like molecules that are structurally distinct from the training set and known antibiotics. Using the model to virtually screen ~6 million compounds, we identified 213 compounds for experimental validation and found that 83 (39%) inhibited N. gonorrhoeae growth. Two of these compounds were structurally dissimilar to existing antibiotics, maintained potency against multidrug-resistant N. gonorrhoeae strains in vitro, exhibited promising selectivity indices, and were rapidly bactericidal with low frequencies of resistance. Proteomic studies revealed their distinct mechanisms of action, with one compound targeting alanine racemase, an enzyme involved in the essential process of peptidoglycan synthesis. Furthermore, the compounds showed early promise in reducing N. gonorrhoeae titers in a human vagina-on-a-chip infection model and a mouse vaginal infection model. Our work establishes the deep learning–enabled discovery of selective antibacterial compounds against N. gonorrhoeae as a much-needed hit discovery tool to address the growing crisis of antimicrobial resistance for this pathogen.

Science Translational MedicineVol. 18(854)
Broad Institute (US), Boston Children's Hospital (US), Karolinska University Hospital (SE), Harvard University (US), University of Basel (CH), Science for Life Laboratory (SE), Karolinska Institutet (SE), Massachusetts General Hospital (US), Coherus BioSciences (United States) (US), Whitehead Institute for Biomedical Research (US), Massachusetts Institute of Technology (US)
Bill and Melinda Gates Foundation, Siebel Scholars Foundation, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Knut och Alice Wallenbergs Stiftelse, Vetenskapsrådet, Novo Nordisk Fonden, National Institutes of Health, Defense Threat Reduction Agency
Openalex Percentile: Top 9%
Reproductive tract infections research
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.