Combined Use of k-Mer Numerical Features and Position-Specific Categorical Features in Fixed-Length DNA Sequence Classification  

作　　者：Dau Phan Ngoc Giang Nguyen Favorisen Rosyking Lumbanraja Mohammad Reza Faisal Bahriddin Abapihi Bedy Purnama Mera Kartika Delimayanti Mamoru Kubo Kenji Satou 

机构地区：[1]Graduate School of Natural Science and Technology, Kanazawa University, Kanazawa, Japan [2]Institute of Science and Engineering, Kanazawa University, Kanazawa, Japan

出　　处：《Journal of Biomedical Science and Engineering》2017年第8期390-401,共12页生物医学工程（英文）

摘　　要：To classify DNA sequences, k-mer frequency is widely used since it can convert variable-length sequences into fixed-length and numerical feature vectors. However, in case of fixed-length DNA sequence classification, subsequences starting at a specific position of the given sequence can also be used as categorical features. Through the performance evaluation on six datasets of fixed-length DNA sequences, our algorithm based on the above idea achieved comparable or better performance than other state-of-the art algorithms.To classify DNA sequences, k-mer frequency is widely used since it can convert variable-length sequences into fixed-length and numerical feature vectors. However, in case of fixed-length DNA sequence classification, subsequences starting at a specific position of the given sequence can also be used as categorical features. Through the performance evaluation on six datasets of fixed-length DNA sequences, our algorithm based on the above idea achieved comparable or better performance than other state-of-the art algorithms.

关 键 词：Sequence CLASSIFICATION NUMERICAL and CATEGORICAL FEATURES Feature Selection 

分 类 号：R73[医药卫生—肿瘤]