Intelligent computational model for classification of sub-Golgi protein using oversampling and fisher feature selection methods
作者：
Highlights：
• Computational model is developed for Golgi proteins.
• PSSM-bigram and discrete methods are utilized for features.
• Fisher feature selection approach is applied.
• Three cross validation tests are examined.
• Obtained quite promising results than existing methods.
摘要
•Computational model is developed for Golgi proteins.•PSSM-bigram and discrete methods are utilized for features.•Fisher feature selection approach is applied.•Three cross validation tests are examined.•Obtained quite promising results than existing methods.
论文关键词：Golgi protein,Dipeptide composition,Split pseudo amino acid composition,Bigram position specific scoring matrix,Fisher feature selection,k-nearest neighbor
论文评审过程：Received 26 March 2017, Revised 19 April 2017, Accepted 2 May 2017, Available online 10 May 2017, Version of Record 15 May 2017.
论文官网地址：https://doi.org/10.1016/j.artmed.2017.05.001
