Accurate prediction of potential druggable proteins based on genetic algorithm and Bagging-SVM ensemble classifier
作者：
Highlights：
• A new method (GA-Bagging-SVM) to predict druggable proteins accurately.
• The protein sequence features are extracted by fusing the PseAAC, DPC and reduced sequence methods.
• Genetic algorithm can effectively remove the redundant information and select the useful feature in the protein sequences.
• The SVM classifier improved by Bagging ensemble learning can effectively reach excellent results.
• The proposed method increases the prediction performance over several methods.
摘要
•A new method (GA-Bagging-SVM) to predict druggable proteins accurately.•The protein sequence features are extracted by fusing the PseAAC, DPC and reduced sequence methods.•Genetic algorithm can effectively remove the redundant information and select the useful feature in the protein sequences.•The SVM classifier improved by Bagging ensemble learning can effectively reach excellent results.•The proposed method increases the prediction performance over several methods.
论文关键词：Druggable proteins,Feature extraction,Genetic algorithm,Support vector machine,Bagging,Ensemble classifier
论文评审过程：Received 23 June 2018, Revised 3 March 2019, Accepted 18 July 2019, Available online 19 July 2019, Version of Record 26 July 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2019.07.005
