We address the problem of predicting the position of a miRNA duplex on a microRNA hairpin via the development and application of a novel SVM-based methodology. Our method combines a unique problem representation and an unbiased optimization protocol to learn from mirBase19.0 an accurate predictive model, termed MiRduplexSVM. This is the first model that provides precise information about all four ends of the miRNA duplex.
MicroRNAs (miRNAs) are key regulators of biological processes. To define miRNA function in the eye, it is essential to determine a high-resolution profile of their spatial and temporal distribution.
Endogenous small non-coding RNAs (sRNAs), including microRNAs, PIWI-interacting RNAs and small interfering RNAs, play important gene regulatory roles in animals and plants by pairing to the protein-coding and non-coding transcripts. However, computationally assigning these various sRNAs to their regulatory target genes remains technically challenging. Recently, a high-throughput degradome sequencing method was applied to identify biologically relevant sRNA cleavage sites.
Large-scale transcriptome projects have shown that the number of RNA transcripts not coding for proteins (non-coding RNAs) is much larger than previously recognized. High-throughput technologies, coupled with bioinformatics approaches, have produced increasing amounts of data, highlighting the role of non-coding RNAs (ncRNAs) in biological processes. Data generated by these studies include diverse non-coding RNA classes from organisms of different kingdoms, which were obtained using different experimental and computational assays.
During recent years, miRNAs have been shown to play important roles in the regulation of gene expression. Accordingly, much effort has been put into the discovery of novel uncharacterized miRNAs in various organisms. miRNAs are structurally defined by a hairpin-loop structure recognized by the two-step processing apparatus, Drosha and Dicer, necessary for the production of mature ~ 22-nucleotide miRNA guide strands.
Datasets generated on deep-sequencing platforms have been deposited in various public repositories such as the Gene Expression Omnibus (GEO), Sequence Read Archive (SRA) hosted by the NCBI, or the DNA Data Bank of Japan (ddbj). Despite being rich data sources, they have not been used much due to the difficulty in locating and analyzing datasets of interest.
Several methods exist for the prediction of precursor miRNAs (pre-miRNAs) in genomic or sRNA-seq (small RNA sequences) data produced by NGS (Next Generation Sequencing). One key information used for this task is the characteristic hairpin structure adopted by pre-miRNAs, that in general are identified using RNA folders whose complexity is cubic in the size of the input. The vast majority of pre-miRNA predictors then rely on further information learned from previously validated miRNAs from the same or a closely related genome for the final prediction of new miRNAs.
MicroRNA precursor identification is an important task in bioinformatics. Support Vector Machine (SVM) is one of the most effective machine learning methods used in this field. The performance of SVM-based methods depends on the vector representations of RNAs. However, the discriminative power of the existing feature vectors is limited, and many methods lack an interpretable model for analysis of characteristic sequence features.
The microRNA (miRNA), a small non-coding RNA molecule, plays an important role in transcriptional and post-transcriptional regulation of gene expression. Its abnormal expression, however, has been observed in many cancers and other disease states, implying that the miRNA molecules are also deeply involved in these diseases, particularly in carcinogenesis. Therefore, it is important for both basic research and miRNA-based therapy to discriminate the real pre-miRNAs from the false ones (such as hairpin sequences with similar stem-loops).
Our database aim to make it easy for researchers to find the right tools or data source for their own specific study in miRNA field. Now we have collect >1000 tools. This database will update when every new 100 tools add in. Last update time 22nd April, 2018 (v1.2).
Updates History:
