The Library
Leveraging genetic algorithms to maximise the predictive capabilities of the SOAP descriptor
Tools
Tools
Tools
Barnard, Trent, Tseng, Steven, Darby, James, Bartók, Albert P., Broo, Anders and Sosso, Gabriele C. (2023) Leveraging genetic algorithms to maximise the predictive capabilities of the SOAP descriptor. Molecular Systems Design & Engineering . doi:10.1039/D2ME00149G ISSN 2058-9689.
|
PDF
WRAP-Leveraging-genetic-algorithms-maximise-predictive-capabilities-22.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution. Download (4Mb) | Preview |
Official URL: https://doi.org/10.1039/D2ME00149G
Abstract
The Smooth Overlap of Atomic Positions (SOAP) descriptor represents an increasingly common approach to encode local atomic environments in a form readily digestible to machine learning algorithms. The SOAP descriptor is obtained by using a local expansion of a Gaussian smeared atomic density with orthonormal functions based on spherical harmonics and radial basis functions. To construct this representation, one has to choose a number of parameters. Whilst the knowledge of the dataset of interest can and should guide this choice, more often than not some optimisation method is required to pinpoint the most effective combinations of SOAP parameters in terms of both accuracy and computational cost. In this work, we present SOAP_GAS, a simple, freely available computational tool that leverages genetic algorithms to optimise the parameters relative to any given SOAP descriptor. To explore the capabilities of the algorithm, we have applied SOAP_GAS to a prototypical molecular dataset of relevance for drug design. In this process, we have realised that a diverse portfolio of different combinations of SOAP parameters can result in equally substantial improvements in terms of the accuracy of the SOAP descriptor. This is especially true when dealing with the concurrent optimisation of the SOAP parameters for multiple SOAP descriptors, which we found it often leads to further accuracy gains. Overall, we show that SOAP_GAS offers an often superior alternative to e.g. randomised grid search approaches to enhanced the predictive capabilities of SOAP descriptors in a largely automatised fashion.
| Item Type: | Journal Article | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QC Physics | ||||||||||||||||||
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Chemistry Faculty of Science, Engineering and Medicine > Engineering > Engineering Faculty of Science, Engineering and Medicine > Science > Physics Faculty of Science, Engineering and Medicine > Science > Chemistry > Computational and Theoretical Chemistry Centre |
||||||||||||||||||
| Library of Congress Subject Headings (LCSH): | Machine learning, Molecules, Atoms | ||||||||||||||||||
| Journal or Publication Title: | Molecular Systems Design & Engineering | ||||||||||||||||||
| Publisher: | Royal Society of Chemistry (RSC) | ||||||||||||||||||
| ISSN: | 2058-9689 | ||||||||||||||||||
| Official Date: | 2023 | ||||||||||||||||||
| Dates: |
|
||||||||||||||||||
| DOI: | 10.1039/D2ME00149G | ||||||||||||||||||
| Status: | Peer Reviewed | ||||||||||||||||||
| Publication Status: | Published | ||||||||||||||||||
| Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||||||||
| Date of first compliant deposit: | 9 November 2022 | ||||||||||||||||||
| Date of first compliant Open Access: | 9 November 2022 | ||||||||||||||||||
| RIOXX Funder/Project Grant: |
|
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
Downloads
Downloads per month over past year
