PHDcleav: a SVM based method for predicting human Dicer cleavage sites using sequence and secondary structure of miRNA precursors

Abstract

BackgroundDicer, an RNase III enzyme, plays a vital role in the processing of pre-miRNAs for generating the miRNAs. The structural and sequence features on pre-miRNA which can facilitate position and efficiency of cleavage are not well known. A precise cleavage by Dicer is crucial because an inaccurate processing can produce miRNA with different seed regions which can alter the repertoire of target genes.ResultsIn this study, a novel method has been developed to predict Dicer cleavage sites on pre-miRNAs using Support Vector Machine. We used the dataset of experimentally validated human miRNA hairpins from miRBase, and extracted fourteen nucleotides around Dicer cleavage sites. We developed number of models using various types of features and achieved maximum accuracy of 66% using binary profile of nucleotide sequence taken from 5p arm of hairpin. The prediction performance of Dicer cleavage site improved significantly from 66% to 86% when we integrated secondary structure information. This indicates that secondary structure plays an important role in the selection of cleavage site. All models were trained and tested on 555 experimentally validated cleavage sites and evaluated using 5-fold cross validation technique. In addition, the performance was also evaluated on an independent testing dataset that achieved an accuracy of ~82%.ConclusionBased on this study, we developed a webserver PHDcleav (http://www.imtech.res.in/raghava/phdcleav/) to predict Dicer cleavage sites in pre-miRNA. This tool can be used to investigate functional consequences of genetic variations/SNPs in miRNA on Dicer cleavage site, and gene silencing. Moreover, it would also be useful in the discovery of miRNAs in human genome and design of Dicer specific pre-miRNAs for potent gene silencing.

LBSizeCleav: improved support vector machine (SVM)-based prediction of Dicer cleavage sites using loop/bulge length

“…We used these cleavage sites as positive examples using windows of size 8,10,12,14 nt, where each window was selected so that a cleavage site is located at the center of the window, and we generated negative examples on the same sequence so that both centers of the positive and negative examples were 6 nt away from each other, as in the previous study [14]. This approach is based on the assumption that for most pre-miRNAs, the Dicer cleavage site is seldom selected at the center of the hairpin structure.…”

“…Thus, it is imperative to explore the factors affecting the accuracy of Dicer cleavage to gain better insights into the mechanism of Dicer cleavage. Recently, a support vector machine (SVM)-based method (PHDCleav) was developed to predict selection of Dicer cleavage sites [14]. They proposed feature space mappings from pre-miRNA nucleotide sequences on the basis of existence of a predicted loop/bulge structure.…”

Association and in silico investigations of miR‐302c insertion/deletion variant as a novel biomarker with susceptibility to gastric cancer

“…RNAfold web server and RNAstructure web tool were used to predict the RNA secondary structure of the insertion and deletion allele based on minimum free energy (MFE). Moreover, PHDcleave website was utilized to predict Dicer processing sites in pre‐miRNA for both insertion and deletion alleles. Furthermore, miRmap web tool and STarMir web software were used to estimate the effect of ins/del within the seed site of miR‐302c on the messenger RNA (mRNA)–miRNA interaction.…”

Bioinformatics prediction and experimental validation of a novel microRNA: hsa‐miR‐B43 within human CDH4 gene with a potential metastasis‐related function in breast cancer

“…Dicer recognition sites in the novel miRNA precursor were recognized by PHDcleav. 35 Until now, no identical or similar miRNA with hsa-miR-B43 has been reported in the miRbase database.…”