Author(s)

Favorisen Rosyking Lumbanraja¹, Ngoc Giang Nguyen¹, Dau Phan¹, Mohammad Reza Faisal¹, Bahriddin Abapihi¹, Bedy Purnama¹, Mera Kartika Delimayanti¹, Mamoru Kubo², Kenji Satou²

¹Graduate School of Natural Science and Technology, Kanazawa University, Kanazawa, Japan.
²Institute of Science and Engineering, Kanazawa University, Kanazawa, Japan.

Phosphorylation of protein is an important post-translational modification that enables activation of various enzymes and receptors included in signaling pathways. To reduce the cost of identifying phosphorylation site by laborious experiments, computational prediction of it has been actively studied. In this study, by adopting a new set of features and applying feature selection by Random Forest with grid search before training by Support Vector Machine, our method achieved better or comparable performance of phosphorylation site prediction for two different data sets.

Protein Phosphorylation, Phosphorylation Site Prediction, Sequence Feature, Feature Selection with Grid Search

Lumbanraja, F. , Nguyen, N. , Phan, D. , Faisal, M. , Abapihi, B. , Purnama, B. , Delimayanti, M. , Kubo, M. and Satou, K. (2018) Improved Protein Phosphorylation Site Prediction by a New Combination of Feature Set and Feature Selection. Journal of Biomedical Science and Engineering, 11, 144-157. doi: 10.4236/jbise.2018.116013.