10.1021/acsomega.7b01079
https://zenodo.org/records/1005103
oai:zenodo.org:1005103
Rodríguez-Pérez, Raquel
Raquel
Rodríguez-Pérez
Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universitaẗ,Dahlmannstr.2,D-53113Bonn,Germany
Vogt, Martin
Martin
Vogt
Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universitaẗ,Dahlmannstr.2,D-53113Bonn,Germany
Bajorath, Jürgen
Jürgen
Bajorath
Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universitaẗ,Dahlmannstr.2,D-53113Bonn,Germany
Support Vector Machine Classification and Regression Prioritize Different Structural Features for Binary Compound Activity and Potency Value Prediction
Zenodo
2017
"Marie Sklodowska-Curie Actions"
2017-10-04
eng
https://zenodo.org/communities/bigchem
https://zenodo.org/communities/eu
Creative Commons Attribution Non Commercial 4.0 International
In computational chemistry and chemoinformatics, the support vector machine (SVM) algorithm is among the most widely used machine learning methods for the identification of new active compounds. In addition, support vector regression (SVR) has become a preferred approach for modeling nonlinear structure−activity relationships and predicting compound potency values. For the closely related SVM and SVR methods, fingerprints (i.e., bit string or feature set representations of chemical structure and properties) are generally preferred descriptors. Herein, we have compared SVM and SVR calculations for the same compound data sets to evaluate which features are responsible for predictions. On the basis of systematic feature weight analysis, rather surprising results were obtained. Fingerprint features were frequently identified that contributed differently to the corresponding SVM and SVR models. The overlap between feature sets determining the predictive performance of SVM and SVR was only very small. Furthermore, features were identified that had opposite effects on SVM and SVR predictions. Feature weight analysis in combination with feature mapping made it also possible to interpret individual predictions, thus balancing the black box character of SVM/SVR modeling.
European Commission
10.13039/501100000780
676434
Big Data in Chemistry