miRNAs are small non coding RNA structures which play important roles in biological processes. Finding miRNA precursors in genomes is therefore an important task, where computational methods are required.
A computational procedure to identify miRNA genes conserved in more than one genome. Applying this program together with molecular identification and validation methods, most of the miRNA genes in the nematode Caenorhabditis elegans have been identified.
A web server dedicated for miRNA precursors identification at a large scale in genomes. It is based on an algorithm called miRNAFold that allows predicting miRNA hairpin structures quickly with high sensitivity. miRNAFold is implemented as a web server with an intuitive and user-friendly interface, as well as a standalone version. miRNAFold was about five times faster than Mirinho for a sequence of 30 500 pb and almost nine times faster on a sequence of ∼1 Mb.
A SVM-based software tool for prediction of most probable microRNA coding regions in genome scale sequences. miRPara is an effective tool for locating miRNAs coding regions in genome sequences and can be used as a screening step prior to HTS experiments.
A program for the identification of miRNA genes in plant genomes. It uses a series of filter steps and a statistical model to discriminate a pre-miRNA from other RNAs and does rely neither on prior knowledge of a miRNA target nor on comparative genomics.
A probabilistic co-learning model for miRNA gene finding that simultaneously considers the structure and sequence of miRNA precursors (pre-miRNAs). On 5-fold cross-validation with 136 referenced human datasets, the efficiency of the classification shows 73% sensitivity and 96% specificity.
Aims users to compare existing ab initio pre-miRNA detection tools. izMiR is a data analysis workflow allowing comparison of data sets, feature groups and classifiers. It can serve for development of new tools about pre-miRNA detection topic. This tool can treat different species, and is useful to identify pre-miRNAs in large eukaryotic genomes.
Aims at the inference of miRNA targets and miRNA-regulated gene networks by integrating expression data from hundreds of cellular and tissue conditions. The website includes the CoMeTa corank lists and additional targets for all of the human miRNAs, their associated pathways resulting from COOL analysis, and miRNA communities with their corresponding enriched functional categories. The CoMeTa website is searchable by miRNA, target gene, or biological function of interest, and represents a unique resource to gain insight into miRNA-controlled gene networks and functions.
Classification of real and pseudo microRNA precursors using random forest prediction model with combined features. Given a sequence, MiPred decides whether it is a pre-miRNA-like hairpin sequence or not. If the sequence is a pre-miRNA-like hairpin, the RF classifier will predict whether it is a real pre-miRNA or a pseudo one.
An ensemble classifier approach for microRNA precursor (pre-miRNA) classification was proposed based upon combining a set of heterogeneous algorithms including support vector machine (SVM), k-nearest neighbors (kNN) and random forest (RF), then aggregating their prediction through a voting system. Additionally, the proposed algorithm, the classification performance was also improved using discriminative features, self-containment and its derivatives, which have shown unique structural robustness characteristics of pre-miRNAs. These are applicable across different species.
A framework for creating species-specific miRNA prediction systems, leveraging sequence conservation and phylogenetic distance information. Significant improvements in specificity and precision are obtained for non-human hold-out test species when SMIRP is applied to existing prediction systems. To make a prediction using SMIRP, enter an RNA sequence into the Sequence field, choose the model which best matches the species you are working with, and hit "Make a prediction". DNA sequences entered into the sequence field will be converted into RNA sequences by replacing all T characters with U. Due to the computational requirements of generating feature data, the webserver only allows one prediction at a time using pre-computed models. If you wish to predict large datasets, the SMIRP source code is freely available.
A genome-wide computational approach to detect miRNAs in animals based on both sequence and structure alignment. Experiments show this approach has higher sensitivity and comparable specificity than other reported homologue searching methods.
Allows de novo support vector machine (SVM) classification of precursor microRNAs (miRNAs). miPred is a de novo SVM classifier model whose original intent is to distinguish precursor miRNAs (pre-miRs) spanning diverse species from genomic pseudo hairpins, according to the classifier model trained solely on human data sets. It aims to validate significantly fewer false-positives.
Effective classification of pre-miRNAs for human miRNA gene prediction by using appropriate machine learning techniques. The microPred classifier could be used to predict novel human pre-miRNAs in both comparative and non-comparative ways. The non-comparative prediction is straightforward, while the comparative prediction requires additional conservation analysis.
A ranking algorithm based on random walks to propagate information of known miRNAs to candidates. The miRank method has the following properties. First, it does not require information of genome annotation. This is particularly important because many sequenced genomes have not been well annotated, and their closely related species are yet to be sequenced. Thus, a large number of false positive candidates with hairpinned secondary structures cannot be filtered out with genome annotation or by phylogenetic conservation. miRank can be applied to such newly sequenced genomes with little annotation. Second, it does not rely on cross-species conservation so that it can identify species-specific miRNAs. Third, miRank is able to accommodate a small number of known miRNAs while enjoys a high-prediction accuracy. Hence, miRank is a useful tool for many species including most viruses that have a very few reported miRNAs.
Learns the latent distribution of hairpin features of the genome under analysis. miRNAss takes advantage of unknown sequences to improve the prediction rates. It can automatically search for negative examples if user is unable to provide them. This application also automatically optimizes the threshold that defines the class boundaries and thus can separate the pre-miRNAs from other groups of sequences.
Estimates premiRNAs, miRNAs, and their binding sites. “Ab initio human pre-miRNA and miRNA prediction by HMMs” employs stochastic models and regularities of the secondary structures of miRNA precursors to work. It can considerate the conservation of candidate site sequences, local secondary mRNA structure, and the nucleotide composition of the duplex to improve its prediction.
Uses a boosting technique with support vector machine components to deal with imbalanced training data. Classification is performed following a feature selection on 187 novel and existing features. miRBoost performed better in comparison with state-of-the-art methods on imbalanced human and cross-species data. It also showed the highest ability among the tested methods for discovering novel miRNA precursors. In addition, miRBoost was over 1400 times faster than the second most accurate tool tested and was significantly faster than most of the other tools. miRBoost thus provides a good compromise between prediction efficiency and execution time, making it highly suitable for use in genome-wide miRNA precursor prediction.
A computational method for pre-miRNA identification. iMiRNA-SSF employs the sequence and structure features trained with an updated benchmark dataset. This dataset was constructed with the positive samples extracted from the miRBase35–37, and the negative samples selected from existing datasets with different data distributions. Experimental results showed that iMiRNA-SSF outperforms three state-of-the-art computational methods.
Allows analyses of high-throughput small RNA (sRNA) sequence data in model and non-model plants, from raw data to identified and annotated conserved and novel sequences. miRPursuit is a pipeline performing a series of sRNA analyses. The software minimizes the need to perform manual repetitive tasks allowing to run several libraries in parallel, for comparing differences in sRNA read accumulation among sRNA libraries. It can directly analyze the sRNA sequencing raw data from any sequencer.
A web-server developed for identifying the real microRNA precursors and false microRNA precursors. iMcRNA contains two predictors: iMcRNA-PseSSC and iMcRNA-ExPseSSC based on the concept of pseudo amino acid composition or Chou’s PseAAC. They were proposed for identifying the human pre-microRNAs by incorporating the global or long-range structure-order information. Rigorous cross-validations on a much larger and more stringent newly constructed benchmark dataset showed that the two new predictors outperformed or were highly comparable with the best existing predictors in this area.