Identification Of MicroRNA Precursors Of The Human Genome Sequence Using Increment Of Diversity Approach

microRNA, a non-coding single-stranded RNA, with the length of 21-26 bp, could participate in a series of important life processes, such as development, hematopoiesis, organogenesis, apoptosis, cell proliferation, and even tumors. microRNA has important influences from cancer, heart disease, AIDS to various of diseases.According to recent research, RNA initial transcript (pri-RNA) molecules are cut into the microRNA precursor (pre-microRNA, about 70-90 bases with hairpin) by the RNaseâ…¢Drosha. The pre-microRNA will be transit from the nucleus to the cytoplasm by the Exportin-5, then processed into microRNA by Dicer enzyme. The most significant feature of pre-microRNA is the hairpin structure. The special hairpin structure is the necessary structure of pre-microRNA binding with Exportin-5 and Dicer enzyme. These two points make hairpin structure very important for the microRNA and pre-microRNA. Based on the conservation and secondary structural characteristic of MicroRNAs precursor sequences (pre-miRNAs), the method of increment of diversity (ID methods) and support vector machine (SVM) was applied to analysis and classification of human pre-miRNAs. Using the characteristic parameters of the number of 3-mer,4-mer,5-mer, MicroRNAs precursor sequences were identified from negative sequences that have the stem-loop structure, separately in intron, exon and intergenic region. The sensitivity,overall accuracy and specificity were more than 89%. The correlation coefficients were 0.7 upwards.