Jump to main content
Jump to site search


MicroRNA precursors identification using reduced and hybrid features

Abstract

The MicroRNAs (also called miRNAs) are a group of short non-coding RNA molecules. They have a vital role in a gene expression of transcriptional and post-transcriptional processes. However, the abnormality of its expression has been observed in cancer, heart diseases and nervous system disorder. Therefore for basic research and microRNA based therapy, it is imperative to separate real pre-miRNAs from false ones (hairpins sequences similar to pre-miRNA stem loops). Different conservation and machine learning methods have been applied for identification of miRNAs. However, Machine learning algorithms gain popularity than conservative based algorithms in term of sensitivity and overall performance. Due to avalanche of RNAs sequences discovered in post-genomics age, it is critical to construct a predictor for identifying pre-microRNAs of human. We have developed a predictor called MicroR-Pred in which RNA sequences are formulated by hybrid feature vector. The novelty of the new predictor is the use of partial least square technique followed by random forest and SVM (Support Vector Machine) algorithms for dimension reduction and classification. The performance of MicroR-Pred model is quite promising compared to other state of the art miRNA predictors. It has achieved 88.40% and 93.90% accuracies for RF and SVM.

Back to tab navigation

Supplementary files

Publication details

The article was received on 24 Feb 2017, accepted on 15 Jun 2017 and first published on 15 Jun 2017


Article type: Paper
DOI: 10.1039/C7MB00115K
Citation: Mol. BioSyst., 2017, Accepted Manuscript
  •   Request permissions

    MicroRNA precursors identification using reduced and hybrid features

    A. Khan, S. Shah, F. Wahid, F. G. khan and S. Jabeen, Mol. BioSyst., 2017, Accepted Manuscript , DOI: 10.1039/C7MB00115K

Search articles by author

Spotlight

Advertisements