Optimization of Spaced K-mer Frequency Feature Extraction using Genetic Algorithms for Metagenome Fragment Classification

Journal of ICT Research and Applications

Wisnu Ananta Kusuma¹  Arini Pekuwali² 

[1] Department of Computer Science, Faculty of Mathematics and Natural Science, Bogor Agricultural University, Jalan Meranti, Kampus IPB Darmaga, Bogor 16680,;Department of Informatics Engineering, Faculty of Science and Engineering, Universitas Kristen Wira Wacana, Jalan R. Suprapto No. 35, Prailiu, Waingapu, Sumba Timur, 87113,

关键词: genetic algorithm;    k-mers;    metagenome;    naïve Bayesian classifier;    spaced k-mers;   

DOI  :  10.5614/itbj.ict.res.appl.2018.12.2.2

学科分类：电子、光学、磁材料

来源: Institute for Research and Community Services ITB

【 摘 要 】

K -mer frequencies are commonly used in extracting features from metagenome fragments. In spite of this, researchers have found that their use is still inefficient. In this research, a genetic algorithm was employed to find optimally spacedk -mers. These were obtained by generating the possible combinations of match positions and don’t care positions (written as *). This approach was adopted from the concept of spaced seeds in PatternHunter. The use of spacedk -mers could reduce the size of thek -mer frequency feature’s dimension. To measure the accuracy of the proposed method we used the naïve Bayesian classifier (NBC). The result showed that the chromosome 111111110001, representing spacedk -mer model [111 1111 10001], was the best chromosome, with a higher fitness (85.42) than that of thek -mer frequency feature. Moreover, the proposed approach also reduced the feature extraction time. 

【 授权许可】

CC BY