Peer-Reviewed Publication
Cell2025;188(21):5962-5979.e22.October 16, 2025Journal Article

A generative deep learning approach to de novo antibiotic design.

Aarti Krishnan1, Melis N Anahtar2, Jacqueline A Valeri3, Wengong Jin4, Nina M Donghia5, Leif Sieben6, Andreas Luttens7, Yu Zhang3, Seyed Majed Modaresi3, Andrew Hennes8, Jenna Fromer9, Parijat Bandyopadhyay7, Jonathan C Chen7, Danyal Rehman10, Ronak Desai11, Paige Edwards7, Ryan S Lach12, Marie-Stéphanie Aschtgen13, Margaux Gaborieau13, Massimiliano Gaetani14, Samantha G Palace15, Satotaka Omori12, Lutete Khonde16, Yurii S Moroz17, Bruce Blough18, Chunyang Jin18, Edmund Loh19, Yonatan H Grad15, Amir Ata Saei13, Connor W Coley20, Felix Wong21, James J Collins22
1Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Institute for Medical Engineering & Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Whitehead Institute for Biomedical Research, Cambridge, MA 02142, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA.
2Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Institute for Medical Engineering & Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA; Departments of Pathology and Medicine, Massachusetts General Hospital, Boston, MA 02114, USA.
3Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Institute for Medical Engineering & Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA.
4Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, USA.
5Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA.
6Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Institute for Medical Engineering & Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA; Department of Chemistry and Applied Biosciences, ETH Zürich, 8093 Zürich, Switzerland.
7Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Institute for Medical Engineering & Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
8Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA.
9Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
10Mila-Quebec AI Institute, Montréal, QC H2S 3H1, Canada.
11Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Harvard Medical School, Boston, MA 02115, USA.
12Integrated Biosciences, Inc., Redwood City, CA 94065, USA.
13Department of Microbiology, Tumor and Cell Biology, Karolinska Institute, 171 77 Stockholm, Sweden.
14Division of Chemistry I, Department of Medical Biochemistry and Biophysics, Karolinska Institute, 17 177 Stockholm, Sweden; Chemical Proteomics Unit, Science for Life Laboratory (SciLifeLab), 171 77Stockholm, Sweden.
15Department of Immunology and Infectious Diseases, Harvard T. H. Chan School of Public Health, Boston, MA 02115, USA.
16Center for the Development of Therapeutics, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA.
17Enamine Ltd., 67 Winston Churchill Street, Kyiv 02094, Ukraine; Chemspace LLC, 85 Winston Churchill Street, Kyiv 02094, Ukraine; Department of Chemistry, Taras Shevchenko National University of Kyiv, 60 Volodymyrska Street, Kyiv 01601, Ukraine.
18Center for Drug Discovery, RTI International, Research Triangle Park, Durham, NC 27713, USA.
19Department of Microbiology, Tumor and Cell Biology, Karolinska Institute, 171 77 Stockholm, Sweden; Clinical Microbiology, Karolinska University Hospital, 171 76 Stockholm, Sweden.
20Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
21Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Institute for Medical Engineering & Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Integrated Biosciences, Inc., Redwood City, CA 94065, USA.
22Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Institute for Medical Engineering & Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA. Electronic address: jimjc@mit.edu.

Abstract

The antimicrobial resistance crisis necessitates structurally distinct antibiotics. While deep learning approaches can identify antibacterial compounds from existing libraries, structural novelty remains limited. Here, we developed a generative artificial intelligence framework for designing de novo antibiotics through two approaches: a fragment-based method to comprehensively screen >107 chemical…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.