Dataset Information

MicroRNA target prediction using thermodynamic and sequence curves.

ABSTRACT: MicroRNAs (miRNAs) are small regulatory RNA that mediate RNA interference by binding to various mRNA target regions. There have been several computational methods for the identification of target mRNAs for miRNAs. However, these have considered all contributory features as scalar representations, primarily, as thermodynamic or sequence-based features. Further, a majority of these methods solely target canonical sites, which are sites with "seed" complementarity. Here, we present a machine-learning classification scheme, titled Avishkar, which captures the spatial profile of miRNA-mRNA interactions via smooth B-spline curves, separately for various input features, such as thermodynamic and sequence features. Further, we use a principled approach to uniformly model canonical and non-canonical seed matches, using a novel seed enrichment metric.We demonstrate that large number of seed-match patterns have high enrichment values, conserved across species, and that majority of miRNA binding sites involve non-canonical matches, corroborating recent findings. Using spatial curves and popular categorical features, such as target site length and location, we train a linear SVM model, utilizing experimental CLIP-seq data. Our model significantly outperforms all established methods, for both canonical and non-canonical sites. We achieve this while using a much larger candidate miRNA-mRNA interaction set than prior work.We have developed an efficient SVM-based model for miRNA target prediction using recent CLIP-seq data, demonstrating superior performance, evaluated using ROC curves, specifically about 20% better than the state-of-the-art, for different species (human or mouse), or different target types (canonical or non-canonical). To the best of our knowledge we provide the first distributed framework for microRNA target prediction based on Apache Hadoop and Spark.All source code and data is publicly available at https://bitbucket.org/cellsandmachines/avishkar.

SUBMITTER: Ghoshal A

PROVIDER: S-EPMC4658802 | biostudies-literature | 2015 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

MicroRNA target prediction using thermodynamic and sequence curves.

Ghoshal Asish A Shankar Raghavendran R Bagchi Saurabh S Grama Ananth A Chaterji Somali S

BMC genomics 20151125

<h4>Background</h4>MicroRNAs (miRNAs) are small regulatory RNA that mediate RNA interference by binding to various mRNA target regions. There have been several computational methods for the identification of target mRNAs for miRNAs. However, these have considered all contributory features as scalar representations, primarily, as thermodynamic or sequence-based features. Further, a majority of these methods solely target canonical sites, which are sites with "seed" complementarity. Here, we prese ...[more]

PMID: 26608597

Similar Datasets

Project description:BackgroundMicroRNAs are known to be generated from primary transcripts mainly through the sequential cleavages by two enzymes, Drosha and Dicer. The sequence of a mature microRNA, especially the 'seeding sequence', largely determines its binding ability and specificity to target mRNAs. Therefore, methods that predict mature microRNA sequences with high accuracy will benefit the identification and characterization of novel microRNAs and their targets, and contribute to inferring the post-transcriptional regulation network at a genome scale.Methodology/principal findingsWe have developed a method, MiRmat, to predict the mature microRNA sequence. MiRmat is essentially composed of two parts: the prediction of Drosha processing site and the identification of Dicer processing site. Based on the analysis of microRNAs from 12 species, we found that the patterns of free energy profiles are conserved among vertebrate microRNA hairpins. Therefore, we introduced in our method the free energy distribution pattern of the downstream part of pri-microRNA secondary structure and Random Forest algorithm to predict the mature microRNA sequence. Based on the evaluation on an independent test dataset from 10 vertebrates, MiRmat was shown to identify 77.8% of the Drosha processing sites and 92.8% of the Dicer sites within a deviation of 2 nt. In a more stringent evaluation by excluding the microRNAs sharing the same family between the training set and test set, MiRmat kept a rather well performance of 71.9% and 87.2% of the identification rate on the Drosha and Dicer site respectively, which represents the ability to deal with the novel microRNA family. MiRmat outperforms other state-of-the-art methods and has a high degree of efficacy for the prediction of mature microRNA sequences of vertebrates.ConclusionMiRmat was developed for identifying microRNA mature sequence(s) by introducing the free energy distribution of RNA stem-loop structure and the Random Forest algorithm. We prove that MiRmat has better performance than the existing tools and is applicable among vertebrates. MiRmat is freely available at http://mcube.nju.edu.cn/jwang/lab/soft/MiRmat/.

Project description:MicroRNAs (miRNAs) are single-stranded non-coding RNAs known to regulate a wide range of cellular processes by silencing the gene expression at the protein and/or mRNA levels. Computational prediction of miRNA targets is essential for elucidating the detailed functions of miRNA. However, the prediction specificity and sensitivity of the existing algorithms are still poor to generate meaningful, workable hypotheses for subsequent experimental testing. Constructing a richer and more reliable training data set and developing an algorithm that properly exploits this data set would be the key to improve the performance current prediction algorithms.A comprehensive training data set is constructed for mammalian miRNAs with its positive targets obtained from the most up-to-date miRNA target depository called miRecords and its negative targets derived from 20 microarray data. A new algorithm SVMicrO is developed, which assumes a 2-stage structure including a site support vector machine (SVM) followed by a UTR-SVM. SVMicrO makes prediction based on 21 optimal site features and 18 optimal UTR features, selected by training from a comprehensive collection of 113 site and 30 UTR features. Comprehensive evaluation of SVMicrO performance has been carried out on the training data, proteomics data, and immunoprecipitation (IP) pull-down data. Comparisons with some popular algorithms demonstrate consistent improvements in prediction specificity, sensitivity and precision in all tested cases. All the related materials including source code and genome-wide prediction of human targets are available at http://compgenomics.utsa.edu/svmicro.html.A 2-stage SVM based new miRNA target prediction algorithm called SVMicrO is developed. SVMicrO is shown to be able to achieve robust performance. It holds the promise to achieve continuing improvement whenever better training data that contain additional verified or high confidence positive targets and properly selected negative targets are available.

Dataset Information

MicroRNA target prediction using thermodynamic and sequence curves.

Publications

MicroRNA target prediction using thermodynamic and sequence curves.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets