Title |
Large-scale ligand-based predictive modelling using support vector machines
|
---|---|
Published in |
Journal of Cheminformatics, August 2016
|
DOI | 10.1186/s13321-016-0151-5 |
Pubmed ID | |
Authors |
Jonathan Alvarsson, Samuel Lampa, Wesley Schaal, Claes Andersson, Jarl E. S. Wikberg, Ola Spjuth |
Abstract |
The increasing size of datasets in drug discovery makes it challenging to build robust and accurate predictive models within a reasonable amount of time. In order to investigate the effect of dataset sizes on predictive performance and modelling time, ligand-based regression models were trained on open datasets of varying sizes of up to 1.2 million chemical structures. For modelling, two implementations of support vector machines (SVM) were used. Chemical structures were described by the signatures molecular descriptor. Results showed that for the larger datasets, the LIBLINEAR SVM implementation performed on par with the well-established libsvm with a radial basis function kernel, but with dramatically less time for model building even on modest computer resources. Using a non-linear kernel proved to be infeasible for large data sizes, even with substantial computational resources on a computer cluster. To deploy the resulting models, we extended the Bioclipse decision support framework to support models from LIBLINEAR and made our models of logD and solubility available from within Bioclipse. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Germany | 3 | 16% |
United Kingdom | 2 | 11% |
Sweden | 2 | 11% |
United States | 1 | 5% |
India | 1 | 5% |
Thailand | 1 | 5% |
Unknown | 9 | 47% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 10 | 53% |
Scientists | 8 | 42% |
Science communicators (journalists, bloggers, editors) | 1 | 5% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Sweden | 1 | 2% |
Unknown | 53 | 98% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 12 | 22% |
Student > Bachelor | 8 | 15% |
Student > Ph. D. Student | 7 | 13% |
Student > Master | 6 | 11% |
Professor > Associate Professor | 4 | 7% |
Other | 9 | 17% |
Unknown | 8 | 15% |
Readers by discipline | Count | As % |
---|---|---|
Chemistry | 13 | 24% |
Biochemistry, Genetics and Molecular Biology | 7 | 13% |
Agricultural and Biological Sciences | 6 | 11% |
Pharmacology, Toxicology and Pharmaceutical Science | 5 | 9% |
Computer Science | 4 | 7% |
Other | 6 | 11% |
Unknown | 13 | 24% |