Meta-QSAR: a large-scale application of meta-learning to drug design and discovery
- Submitting institution
-
Goldsmiths' College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 3180
- Type
- D - Journal article
- DOI
-
10.1007/s10994-017-5685-x
- Title of journal
- Machine Learning
- Article number
- -
- First page
- 285
- Volume
- 107
- Issue
- 1
- ISSN
- 0885-6125
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2017
- URL
-
http://research.gold.ac.uk/id/eprint/27134/
- 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
-
6
- Research group(s)
-
-
- Citation count
- 19
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The reported results advance Machine Learning by an unprecedented large-scale analysis of Machine Learning approached and data representations. The novelty is in the formal encoding of background knowledge about Machine Learning approaches and data and their utilization in the proposed meta-QSAR approach. The paper presents the key results of the EPSRC-funded project ‘learning to learn how to design drugs’ (EP/K030582/1) led by the University of Manchester; Soldatova was Principle Investigator in the partner organization. The meta-QSAR approach is of significance to pharmaceutical industry, because it recommends the most effective Machine Learning approach for a chosen drug target and data representation.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -