Show simple item record

dc.contributor.authorStokes, Jonathan
dc.contributor.authorYang, Kevin
dc.contributor.authorSwanson, Kyle
dc.contributor.authorJin, Wengong
dc.contributor.authorCubillos, Andres Fernando
dc.contributor.authorDonghia, Nina
dc.contributor.authorMacNair, Craig R.
dc.contributor.authorFrench, Shawn
dc.contributor.authorCarfrae, Lindsey A.
dc.contributor.authorBloom-Ackermann, Zohar
dc.contributor.authorTran, Victoria M.
dc.contributor.authorChiappino-Pepe, Anush
dc.contributor.authorBadran, Ahmed
dc.contributor.authorAndrews, Ian W.
dc.contributor.authorChory, Emma J
dc.contributor.authorChurch, George M.
dc.contributor.authorBrown, Eric D.
dc.contributor.authorJaakkola, Tommi S.
dc.contributor.authorBarzilay, Regina
dc.contributor.authorCollins, James J.
dc.date.accessioned2020-07-13T19:06:42Z
dc.date.available2020-07-13T19:06:42Z
dc.date.issued2020-02
dc.identifier.issn0092-8674
dc.identifier.urihttps://hdl.handle.net/1721.1/126162
dc.description.abstractDue to the rapid emergence of antibiotic-resistant bacteria, there is a growing need to discover new antibiotics. To address this challenge, we trained a deep neural network capable of predicting molecules with antibacterial activity. We performed predictions on multiple chemical libraries and discovered a molecule from the Drug Repurposing Hub—halicin—that is structurally divergent from conventional antibiotics and displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae. Halicin also effectively treated Clostridioides difficile and pan-resistant Acinetobacter baumannii infections in murine models. Additionally, from a discrete set of 23 empirically tested predictions from >107 million molecules curated from the ZINC15 database, our model identified eight antibacterial compounds that are structurally distant from known antibiotics. This work highlights the utility of deep learning approaches to expand our antibiotic arsenal through the discovery of structurally distinct antibacterial molecules. A trained deep neural network predicts antibiotic activity in molecules that are structurally different from known antibiotics, among which Halicin exhibits efficacy against broad-spectrum bacterial infections in mice.en_US
dc.description.sponsorshipDefence Threat Reduction Agency (Grant HDTRA1-15- 1-0051)en_US
dc.language.isoen
dc.publisherElsevier BVen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.cell.2020.01.021en_US
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivs Licenseen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/en_US
dc.sourceProf. Collins via Howard Silveren_US
dc.titleA Deep Learning Approach to Antibiotic Discoveryen_US
dc.typeArticleen_US
dc.identifier.citationStokes, Jonathan M. et al. "A Deep Learning Approach to Antibiotic Discovery." 180, 4 (February 2020): 688-702 © 2020 Elsevieren_US
dc.contributor.departmentMassachusetts Institute of Technology. Institute for Medical Engineering and Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.relation.journalCellen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2020-07-09T14:06:39Z
dspace.date.submission2020-07-09T14:06:43Z
mit.journal.volume180en_US
mit.journal.issue4en_US
mit.licensePUBLISHER_CC


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record