Merging enzymatic and synthetic chemistry with computational synthesis planning
<jats:title>Abstract</jats:title><jats:p>Synthesis planning programs trained on chemical reaction data can design efficient routes to new molecules of interest, but are limited in their ability to leverage rare chemical transformations. This challenge is acute for enzymatic reactio...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2023
|
| Online Access: | https://hdl.handle.net/1721.1/147933 |
| _version_ | 1811091581130768384 |
|---|---|
| author | Levin, Itai Liu, Mengjie Voigt, Christopher A Coley, Connor W |
| author2 | Massachusetts Institute of Technology. Department of Biological Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Biological Engineering Levin, Itai Liu, Mengjie Voigt, Christopher A Coley, Connor W |
| author_sort | Levin, Itai |
| collection | MIT |
| description | <jats:title>Abstract</jats:title><jats:p>Synthesis planning programs trained on chemical reaction data can design efficient routes to new molecules of interest, but are limited in their ability to leverage rare chemical transformations. This challenge is acute for enzymatic reactions, which are valuable due to their selectivity and sustainability but are few in number. We report a retrosynthetic search algorithm using two neural network models for retrosynthesis–one covering 7984 enzymatic transformations and one 163,723 synthetic transformations–that balances the exploration of enzymatic and synthetic reactions to identify hybrid synthesis plans. This approach extends the space of retrosynthetic moves by thousands of uniquely enzymatic one-step transformations, discovers routes to molecules for which synthetic or enzymatic searches find none, and designs shorter routes for others. Application to (-)-Δ<jats:sup>9</jats:sup> tetrahydrocannabinol (THC) (dronabinol) and R,R-formoterol (arformoterol) illustrates how our strategy facilitates the replacement of metal catalysis, high step counts, or costly enantiomeric resolution with more elegant hybrid proposals.</jats:p> |
| first_indexed | 2024-09-23T15:04:39Z |
| format | Article |
| id | mit-1721.1/147933 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:04:39Z |
| publishDate | 2023 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1479332023-02-08T03:09:22Z Merging enzymatic and synthetic chemistry with computational synthesis planning Levin, Itai Liu, Mengjie Voigt, Christopher A Coley, Connor W Massachusetts Institute of Technology. Department of Biological Engineering <jats:title>Abstract</jats:title><jats:p>Synthesis planning programs trained on chemical reaction data can design efficient routes to new molecules of interest, but are limited in their ability to leverage rare chemical transformations. This challenge is acute for enzymatic reactions, which are valuable due to their selectivity and sustainability but are few in number. We report a retrosynthetic search algorithm using two neural network models for retrosynthesis–one covering 7984 enzymatic transformations and one 163,723 synthetic transformations–that balances the exploration of enzymatic and synthetic reactions to identify hybrid synthesis plans. This approach extends the space of retrosynthetic moves by thousands of uniquely enzymatic one-step transformations, discovers routes to molecules for which synthetic or enzymatic searches find none, and designs shorter routes for others. Application to (-)-Δ<jats:sup>9</jats:sup> tetrahydrocannabinol (THC) (dronabinol) and R,R-formoterol (arformoterol) illustrates how our strategy facilitates the replacement of metal catalysis, high step counts, or costly enantiomeric resolution with more elegant hybrid proposals.</jats:p> 2023-02-07T17:24:48Z 2023-02-07T17:24:48Z 2022-12-14 2023-02-07T16:51:42Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/147933 Levin, Itai, Liu, Mengjie, Voigt, Christopher A and Coley, Connor W. 2022. "Merging enzymatic and synthetic chemistry with computational synthesis planning." Nature Communications, 13 (1). en 10.1038/s41467-022-35422-y Nature Communications Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Nature |
| spellingShingle | Levin, Itai Liu, Mengjie Voigt, Christopher A Coley, Connor W Merging enzymatic and synthetic chemistry with computational synthesis planning |
| title | Merging enzymatic and synthetic chemistry with computational synthesis planning |
| title_full | Merging enzymatic and synthetic chemistry with computational synthesis planning |
| title_fullStr | Merging enzymatic and synthetic chemistry with computational synthesis planning |
| title_full_unstemmed | Merging enzymatic and synthetic chemistry with computational synthesis planning |
| title_short | Merging enzymatic and synthetic chemistry with computational synthesis planning |
| title_sort | merging enzymatic and synthetic chemistry with computational synthesis planning |
| url | https://hdl.handle.net/1721.1/147933 |
| work_keys_str_mv | AT levinitai mergingenzymaticandsyntheticchemistrywithcomputationalsynthesisplanning AT liumengjie mergingenzymaticandsyntheticchemistrywithcomputationalsynthesisplanning AT voigtchristophera mergingenzymaticandsyntheticchemistrywithcomputationalsynthesisplanning AT coleyconnorw mergingenzymaticandsyntheticchemistrywithcomputationalsynthesisplanning |