A Deep Learning Approach to Antibiotic Discovery
Due 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 disco...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2020
|
| Online Access: | https://hdl.handle.net/1721.1/126162 |
| _version_ | 1826216678145392640 |
|---|---|
| author | Stokes, Jonathan Yang, Kevin Swanson, Kyle Jin, Wengong Cubillos, Andres Fernando Donghia, Nina MacNair, Craig R. French, Shawn Carfrae, Lindsey A. Bloom-Ackermann, Zohar Tran, Victoria M. Chiappino-Pepe, Anush Badran, Ahmed Andrews, Ian W. Chory, Emma J Church, George M. Brown, Eric D. Jaakkola, Tommi S. Barzilay, Regina Collins, James J. |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Stokes, Jonathan Yang, Kevin Swanson, Kyle Jin, Wengong Cubillos, Andres Fernando Donghia, Nina MacNair, Craig R. French, Shawn Carfrae, Lindsey A. Bloom-Ackermann, Zohar Tran, Victoria M. Chiappino-Pepe, Anush Badran, Ahmed Andrews, Ian W. Chory, Emma J Church, George M. Brown, Eric D. Jaakkola, Tommi S. Barzilay, Regina Collins, James J. |
| author_sort | Stokes, Jonathan |
| collection | MIT |
| description | Due 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. |
| first_indexed | 2024-09-23T16:51:40Z |
| format | Article |
| id | mit-1721.1/126162 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:51:40Z |
| publishDate | 2020 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1261622022-10-03T08:46:21Z A Deep Learning Approach to Antibiotic Discovery Stokes, Jonathan Yang, Kevin Swanson, Kyle Jin, Wengong Cubillos, Andres Fernando Donghia, Nina MacNair, Craig R. French, Shawn Carfrae, Lindsey A. Bloom-Ackermann, Zohar Tran, Victoria M. Chiappino-Pepe, Anush Badran, Ahmed Andrews, Ian W. Chory, Emma J Church, George M. Brown, Eric D. Jaakkola, Tommi S. Barzilay, Regina Collins, James J. Massachusetts Institute of Technology. Institute for Medical Engineering & Science Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Due 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. Defence Threat Reduction Agency (Grant HDTRA1-15- 1-0051) 2020-07-13T19:06:42Z 2020-07-13T19:06:42Z 2020-02 2020-07-09T14:06:39Z Article http://purl.org/eprint/type/JournalArticle 0092-8674 https://hdl.handle.net/1721.1/126162 Stokes, Jonathan M. et al. "A Deep Learning Approach to Antibiotic Discovery." 180, 4 (February 2020): 688-702 © 2020 Elsevier en http://dx.doi.org/10.1016/j.cell.2020.01.021 Cell Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV Prof. Collins via Howard Silver |
| spellingShingle | Stokes, Jonathan Yang, Kevin Swanson, Kyle Jin, Wengong Cubillos, Andres Fernando Donghia, Nina MacNair, Craig R. French, Shawn Carfrae, Lindsey A. Bloom-Ackermann, Zohar Tran, Victoria M. Chiappino-Pepe, Anush Badran, Ahmed Andrews, Ian W. Chory, Emma J Church, George M. Brown, Eric D. Jaakkola, Tommi S. Barzilay, Regina Collins, James J. A Deep Learning Approach to Antibiotic Discovery |
| title | A Deep Learning Approach to Antibiotic Discovery |
| title_full | A Deep Learning Approach to Antibiotic Discovery |
| title_fullStr | A Deep Learning Approach to Antibiotic Discovery |
| title_full_unstemmed | A Deep Learning Approach to Antibiotic Discovery |
| title_short | A Deep Learning Approach to Antibiotic Discovery |
| title_sort | deep learning approach to antibiotic discovery |
| url | https://hdl.handle.net/1721.1/126162 |
| work_keys_str_mv | AT stokesjonathan adeeplearningapproachtoantibioticdiscovery AT yangkevin adeeplearningapproachtoantibioticdiscovery AT swansonkyle adeeplearningapproachtoantibioticdiscovery AT jinwengong adeeplearningapproachtoantibioticdiscovery AT cubillosandresfernando adeeplearningapproachtoantibioticdiscovery AT donghianina adeeplearningapproachtoantibioticdiscovery AT macnaircraigr adeeplearningapproachtoantibioticdiscovery AT frenchshawn adeeplearningapproachtoantibioticdiscovery AT carfraelindseya adeeplearningapproachtoantibioticdiscovery AT bloomackermannzohar adeeplearningapproachtoantibioticdiscovery AT tranvictoriam adeeplearningapproachtoantibioticdiscovery AT chiappinopepeanush adeeplearningapproachtoantibioticdiscovery AT badranahmed adeeplearningapproachtoantibioticdiscovery AT andrewsianw adeeplearningapproachtoantibioticdiscovery AT choryemmaj adeeplearningapproachtoantibioticdiscovery AT churchgeorgem adeeplearningapproachtoantibioticdiscovery AT brownericd adeeplearningapproachtoantibioticdiscovery AT jaakkolatommis adeeplearningapproachtoantibioticdiscovery AT barzilayregina adeeplearningapproachtoantibioticdiscovery AT collinsjamesj adeeplearningapproachtoantibioticdiscovery AT stokesjonathan deeplearningapproachtoantibioticdiscovery AT yangkevin deeplearningapproachtoantibioticdiscovery AT swansonkyle deeplearningapproachtoantibioticdiscovery AT jinwengong deeplearningapproachtoantibioticdiscovery AT cubillosandresfernando deeplearningapproachtoantibioticdiscovery AT donghianina deeplearningapproachtoantibioticdiscovery AT macnaircraigr deeplearningapproachtoantibioticdiscovery AT frenchshawn deeplearningapproachtoantibioticdiscovery AT carfraelindseya deeplearningapproachtoantibioticdiscovery AT bloomackermannzohar deeplearningapproachtoantibioticdiscovery AT tranvictoriam deeplearningapproachtoantibioticdiscovery AT chiappinopepeanush deeplearningapproachtoantibioticdiscovery AT badranahmed deeplearningapproachtoantibioticdiscovery AT andrewsianw deeplearningapproachtoantibioticdiscovery AT choryemmaj deeplearningapproachtoantibioticdiscovery AT churchgeorgem deeplearningapproachtoantibioticdiscovery AT brownericd deeplearningapproachtoantibioticdiscovery AT jaakkolatommis deeplearningapproachtoantibioticdiscovery AT barzilayregina deeplearningapproachtoantibioticdiscovery AT collinsjamesj deeplearningapproachtoantibioticdiscovery |