A Model to Search for Synthesizable Molecules
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 16232
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Advances in Neural Information Processing Systems
- First page
- 7937
- Volume
- 32
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Technical exception
- Month of publication
- December
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Previous work from the machine learning community on de novo design of molecules did not take into account the challenges of actually synthesizing proposed molecules in a lab. This paper proposed one of the first deep learning models which explicitly generates molecules via a synthetic route. Synthesizability has since been called out as one of the major obstacles to adopting machine learning approaches to drug design in subject area journals (J. Chem. Inf. Model., 2020, DOI 10.1021/acs.jcim.0c00174), which cites this paper.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -