miRTar2GO: a novel rule-based model learning method for cell line specific microRNA target prediction that integrates Ago2 CLIP-Seq and validated microRNA-target interaction data

Abstract

MicroRNAs (miRNAs) are ∼19-22 nucleotides (nt) long regulatory RNAs that regulate gene expression by recognizing and binding to complementary sequences on mRNAs. The key step in revealing the function of a miRNA, is the identification of miRNA target genes. Recent biochemical advances including PAR-CLIP and HITS-CLIP allow for improved miRNA target predictions and are widely used to validate miRNA targets. Here, we present miRTar2GO, which is a model, trained on the common rules of miRNA-target interactions, Argonaute (Ago) CLIP-Seq data and experimentally validated miRNA target interactions. miRTar2GO is designed to predict miRNA target sites using more relaxed miRNA-target binding characteristics. More importantly, miRTar2GO allows for the prediction of cell-type specific miRNA targets. We have evaluated miRTar2GO against other widely used miRNA target prediction algorithms and demonstrated that miRTar2GO produced significantly higher F1 and G scores. Target predictions, binding specifications, results of the pathway analysis and gene ontology enrichment of miRNA targets are freely available at http://www.mirtar2go.org.

Figure 1.

Pipeline of miRTar2GO. In the data processing step, the genomic coordinates of the Ago2 CLIP-Seq reads in different cell lines are mapped to the mRNAs to identify 3΄UTRs which are enriched in Ago2 interaction sites. In the miRNA–mRNA allocation step, the 6mer seed region of all known miRNAs are aligned to the reverse complementary sequence of Ago2 CLIPed sites in the 3΄ UTRs. At the prediction categorization step, the whole miRNA sequence of each miRNA–tmRNA pair is folded upon its allocated Ago2 CLIPed sequence to calculate hybridization energy. At this step, interactions with a MFE >−15 kcal/mol are discarded. At the result population step, four different sets of results are generated. The interactions in the unseen set with a MFE <−20 kcal/mol are the result of miRTar2GO sensitive. Interaction scores are calculated for all pairs of the unseen sets introducing the highly sensitive miRTar2GO result. The interactions of the unseen set that have hybridization energy <−20 kcal/mol and less than the maximum MFE value associated to the miRNA are shown as miRTar2GO highly specific results. The interactions of the unseen set that have hybridization energy of less than the maximum energy associated with their corresponding miRNA are defined as miRTar2GO specific results. The result of this step is a set of miRNA target candidates, where the miRNA seed region of each candidate has a perfect complementary to the associated mRNA. The miRNA–tmRNA interactions that are not experimentally verified are selected to generate the unseen set. The miRNA–tmRNA interactions that are experimentally verified are used to calculate hybridization energy values for each miRNA including the minimum and the maximum of MFEs.

Figure 2.

The number of downregulated and non downregulated transcripts in a pSILAC experiment generated by overexpressing miRNAs. Let-7b, miR-155, miR-30a, miR-16 and miR-1 were overexpressed in HeLa cells and the changes in protein levels were quantified by pSILAC. Each blue bar represents the number of transcripts which are downregulated with a log₂-fold change <−0.1 as the corresponding miRNA is introduced in the cell. Each red bar represents the number of non downregulated transcripts in each experiment.

Figure 3.

let-7c is predicted to target the RAS signaling pathway and miR-98. The figure shows the modified diagram of the RAS signaling pathway generated by hiPathDB. * indicates experimentally validated let-7c targets in RAS signaling pathway used in training of miRTar2GO. The Green colored boxes indicate let-7c targets in RAS signaling pathway predicted by miRTar2GO. miR-98, a member of the let-7 miRNA family, is added to the figure.

Figure 4.

Comparison of different miRNA target prediction tools. The total number of transcripts predicted as miRNA target by popular miRNA target prediction tools from the downregulated transcripts identified by pSILAC followed by the overexpression of five miRNAs in HeLa cells.

Figure 5.

Evaluation of miRTar2GO. (A) The number of correctly identified miRNA targets by different target prediction tools using the pSILAC experiments (blue bars). The Red bars represent the correctly identified non tmRNAs. (B) Comparison of F₁ scores of different miRNA target prediction methods using the pSILAC data set. The x-axis represents the precision and the y-axis represents the recall. Each spectrum in the figure represents one sub-range of the averaged value for the precision and the recall. (C) Comparison of G scores of different miRNA prediction tools using the pSILAC dataset.