SVM-RFE with Laplacian kernel for classification of signaling proteins based on molecular star graph descriptors using machine-learning models

Paper is available at: http://dx.doi.org/10.1016/j.jtbi.2015.07.038 Please cite: Carlos Fernandez-Lozano, Rubén F. Cuiñas, José A. Seoane, Enrique Fernández-Blanco, Julian Dorado, Cristian R. Munteanu, Classification of signaling proteins based on molecular star graph descriptors using Machine Learning models, Journal of Theoretical Biology, Volume 384, 7 November 2015, Pages 50-58, ISSN 0022-5193, http://dx.doi.org/10.1016/j.jtbi.2015.07.038.(http://www.sciencedirect.com/science/article/pii/S0022519315003999) RFE-LAP selected features to improve the classification results with only 11 out of 42 features calculated with S2SNet. Therefore, these results can help to predict signaling function-related proteins using only a reduced amount of molecular information encoded into the protein sequence. We achieved an AUROC of 0.961 ± 0.11% in our 5 runs, and only 11 features: X5, H, S6, X4, eS6, eH, eTr3, eX5, eTr5, eTr0, Tr0