Improved understanding of aqueous solubility modeling through topological data analysis
- Submitting institution
-
University of Southampton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 54504936
- Type
- D - Journal article
- DOI
-
10.1186/s13321-018-0308-5
- Title of journal
- Journal of Cheminformatics
- Article number
- 54
- First page
- -
- Volume
- 10
- Issue
- -
- ISSN
- 1758-2946
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2018
- 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
- Yes
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is an applied part of a substantive theme in Southampton on understanding theoretically, the performance seen in data-driven deep neural networks with Topological Data Analysis as the mathematical substrate (https://arxiv.org/abs/1906.01507). The work resulted from an EPSRC project “Joining the Dots: From Data to Insight, EP/N014189/1 (https://tinyurl.com/r9gre6b). The chemistry application in this paper, and the inter-disciplinary theme of work surrounding it, directly resulted in a Network of Excellence: Artificial and Augmented Intelligence for Automated Scientific Discovery, EP/S000356/1 (https://tinyurl.com/rcax8d8). The novelty is not merely in accurate predictions, but in deriving an intuition of the topology of the chemical space.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -