Title :
Features in Identification Approaches for MicroRNA Precursors Based on Machine Learning
Author :
Zheng Hongjun ; Pu Haiqing ; Wang Xiuqin ; Li Yongqiang
Author_Institution :
Coll. of Inf. Sci. & Eng., Yanshan Univ., Qinhuangdao, China
Abstract :
MicroRNAs (miRNAs) are a group of non-coding small RNA of ~ 22 nucleotides in length. They play important roles in gene regulation in animals and plants. The machine learning approach has become an important way to discover miRNAs, which is complement to experimental approaches. Feature selection is the key step of machine learning approaches to discover miRNA precursors. The performance and generalization ability of classifier is affected by the feature set. Features of miRNA precursors used in machine learning approaches were summarized in this review. According to the properties of features to distinguish the miRNA precursors and the non-miRNA precursors, features were categorized into three classes: sequence features, structure features, structure sequence features.
Keywords :
RNA; feature selection; generalisation (artificial intelligence); genetics; learning (artificial intelligence); MicroRNA precursors; animals; feature selection; feature set; gene regulation; generalization ability; identification approach; machine learning approach; noncoding small RNA; nucleotides; plants; structure-sequence features; Bioinformatics; Feature extraction; Genomics; Periodic structures; RNA; Sequential analysis; Support vector machines; features; machine learning approaches; miRNA precursor; microRNA;
Conference_Titel :
Intelligent Systems Design and Engineering Applications (ISDEA), 2014 Fifth International Conference on
Conference_Location :
Hunan
Print_ISBN :
978-1-4799-4262-6
DOI :
10.1109/ISDEA.2014.116