A Bayesian decision fusion approach for microRNA target prediction.
Ontology highlight
ABSTRACT:
SUBMITTER: Yue D
PROVIDER: S-EPMC3535698 | biostudies-literature | 2012
REPOSITORIES: biostudies-literature
Publications
A Bayesian decision fusion approach for microRNA target prediction.
Yue Dong D Guo Maozu M Chen Yidong Y Huang Yufei Y
BMC genomics 20121217
MicroRNAs (miRNAs) are 19-25 nucleotides non-coding RNAs known to have important post-transcriptional regulatory functions. The computational target prediction algorithm is vital to effective experimental testing. However, since different existing algorithms rely on different features and classifiers, there is a poor agreement among the results of different algorithms. To benefit from the advantages of different algorithms, we proposed an algorithm called BCmicrO that combines the prediction of ...[more]
Similar Datasets
Project description:The identification of microRNA (miRNA) target sites is fundamentally important for studying gene regulation. There are dozens of computational methods available for miRNA target site prediction. Despite their existence, we still cannot reliably identify miRNA target sites, partially due to our limited understanding of the characteristics of miRNA target sites. The recently published CLASH (crosslinking ligation and sequencing of hybrids) data provide an unprecedented opportunity to study the characteristics of miRNA target sites and improve miRNA target site prediction methods.Applying four different machine learning approaches to the CLASH data, we identified seven new features of miRNA target sites. Combining these new features with those commonly used by existing miRNA target prediction algorithms, we developed an approach called TarPmiR for miRNA target site prediction. Testing on two human and one mouse non-CLASH datasets, we showed that TarPmiR predicted more than 74.2% of true miRNA target sites in each dataset. Compared with three existing approaches, we demonstrated that TarPmiR is superior to these existing approaches in terms of better recall and better precision.The TarPmiR software is freely available at http://hulab.ucf.edu/research/projects/miRNA/TarPmiR/ CONTACTS: haihu@cs.ucf.edu or xiaoman@mail.ucf.eduSupplementary data are available at Bioinformatics online.
| S-EPMC5018371 | biostudies-literature
Project description:BackgroundVirtually all currently available microRNA target site prediction algorithms require the presence of a (conserved) seed match to the 5' end of the microRNA. Recently however, it has been shown that this requirement might be too stringent, leading to a substantial number of missed target sites.ResultsWe developed TargetSpy, a novel computational approach for predicting target sites regardless of the presence of a seed match. It is based on machine learning and automatic feature selection using a wide spectrum of compositional, structural, and base pairing features covering current biological knowledge. Our model does not rely on evolutionary conservation, which allows the detection of species-specific interactions and makes TargetSpy suitable for analyzing unconserved genomic sequences.In order to allow for an unbiased comparison of TargetSpy to other methods, we classified all algorithms into three groups: I) no seed match requirement, II) seed match requirement, and III) conserved seed match requirement. TargetSpy predictions for classes II and III are generated by appropriate postfiltering. On a human dataset revealing fold-change in protein production for five selected microRNAs our method shows superior performance in all classes. In Drosophila melanogaster not only our class II and III predictions are on par with other algorithms, but notably the class I (no-seed) predictions are just marginally less accurate. We estimate that TargetSpy predicts between 26 and 112 functional target sites without a seed match per microRNA that are missed by all other currently available algorithms.ConclusionOnly a few algorithms can predict target sites without demanding a seed match and TargetSpy demonstrates a substantial improvement in prediction accuracy in that class. Furthermore, when conservation and the presence of a seed match are required, the performance is comparable with state-of-the-art algorithms. TargetSpy was trained on mouse and performs well in human and drosophila, suggesting that it may be applicable to a broad range of species. Moreover, we have demonstrated that the application of machine learning techniques in combination with upcoming deep sequencing data results in a powerful microRNA target site prediction tool http://www.targetspy.org.
| S-EPMC2889937 | biostudies-literature
Project description:microRNAs (miRNAs) are endogenous non-coding RNAs that control gene expression at the posttranscriptional level. These small regulatory molecules play a key role in the majority of biological processes and their expression is also tightly regulated. Both the deregulation of genes controlled by miRNAs and the altered miRNA expression have been linked to many disorders, including cancer, cardiovascular, metabolic and neurodegenerative diseases. Therefore, it is of particular interest to reliably predict potential miRNA targets which might be involved in these diseases. However, interactions between miRNAs and their targets are complex and very often there are numerous putative miRNA recognition sites in mRNAs. Many miRNA targets have been computationally predicted but only a limited number of these were experimentally validated. Although a variety of miRNA target prediction algorithms are available, results of their application are often inconsistent. Hence, finding a functional miRNA target is still a challenging task. In this review, currently available and frequently used computational tools for miRNA target prediction, i.e., PicTar, TargetScan, DIANA-microT, miRanda, rna22 and PITA are outlined and various practical aspects of miRNA target analysis are extensively discussed. Moreover, the performance of three algorithms (PicTar, TargetScan and DIANA-microT) is both demonstrated and evaluated by performing an in-depth analysis of miRNA interactions with mRNAs derived from genes triggering hereditary neurological disorders known as trinucleotide repeat expansion diseases (TREDs), such as Huntington's disease (HD), a number of spinocerebellar ataxias (SCAs), and myotonic dystrophy type 1 (DM1).
| S-EPMC3182075 | biostudies-literature
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.
| S-EPMC2955701 | biostudies-literature
Project description:MicroRNAs (miRNAs) are noncoding small RNA of approximately 22 bases, which suppress expression of target genes through translational block or degradation of a target's transcript. Recent studies uncovered specific miRNA expression profiles in human malignancies. Nevertheless, the mechanisms underlying cancer-specific miRNA expression are largely unknown. miRNA biogenesis consists of a series of steps beginning with generation of a primary transcript, termed pri-miRNA, and continuing into excision of a stem-loop hairpin structure within pri-miRNA by the nuclear RNaseIII enzyme Drosha, transportation to the cytoplasm, and further processing by a second RNaseIII enzyme Dicer, into a 22-base mature duplex RNA. In principle, alteration in any step during this maturation process could affect miRNA production. The ALL-1 (also termed MLL) gene was originally isolated by virtue of its involvement in recurrent chromosome translocations associated with acute leukemias, particularly in infant and therapy-related leukemias. These translocations result in the fusion of ALL-1 with partner genes and the consequent production of chimeric leukemogenic proteins. Here, we identify specific miRNAs up-regulated in leukemias triggered by All1 fusions. Further, we demonstrate coimmunoprecipitation of the All1/Af4 and All1/Af9 fusions with Drosha, disrupted by treatment with DNase I. Finally, we present evidence from ChIP experiments for All1 fusion protein-mediated recruitment of Drosha to target genes encoding miRNAs. Such recruitment may underlie the enhanced expression of the relevant miRNAs.
| S-EPMC1904159 | biostudies-literature
Project description:BACKGROUND: As a reversible and dynamic post-translational modification (PTM) of proteins, phosphorylation plays essential regulatory roles in a broad spectrum of the biological processes. Although many studies have been contributed on the molecular mechanism of phosphorylation dynamics, the intrinsic feature of substrates specificity is still elusive and remains to be delineated. RESULTS: In this work, we present a novel, versatile and comprehensive program, PPSP (Prediction of PK-specific Phosphorylation site), deployed with approach of Bayesian decision theory (BDT). PPSP could predict the potential phosphorylation sites accurately for approximately 70 PK (Protein Kinase) groups. Compared with four existing tools Scansite, NetPhosK, KinasePhos and GPS, PPSP is more accurate and powerful than these tools. Moreover, PPSP also provides the prediction for many novel PKs, say, TRK, mTOR, SyK and MET/RON, etc. The accuracy of these novel PKs are also satisfying. CONCLUSION: Taken together, we propose that PPSP could be a potentially powerful tool for the experimentalists who are focusing on phosphorylation substrates with their PK-specific sites identification. Moreover, the BDT strategy could also be a ubiquitous approach for PTMs, such as sumoylation and ubiquitination, etc.
| S-EPMC1435943 | biostudies-literature
Project description:Target prediction for animal microRNAs (miRNAs) has been hindered by the small number of verified targets available to evaluate the accuracy of predicted miRNA-target interactions. Recently, a dataset of 3,404 miRNA-associated mRNA transcripts was identified by immunoprecipitation of the RNA-induced silencing complex components AIN-1 and AIN-2. Our analysis of this AIN-IP dataset revealed enrichment for defining characteristics of functional miRNA-target interactions, including structural accessibility of target sequences, total free energy of miRNA-target hybridization and topology of base-pairing to the 5' seed region of the miRNA. We used these enriched characteristics as the basis for a quantitative miRNA target prediction method, miRNA targets by weighting immunoprecipitation-enriched parameters (mirWIP), which optimizes sensitivity to verified miRNA-target interactions and specificity to the AIN-IP dataset. MirWIP can be used to capture all known conserved miRNA-mRNA target relationships in Caenorhabditis elegans at a lower false-positive rate than can the current standard methods.
| S-EPMC3092588 | biostudies-literature
Project description:MicroRNAs (miRNAs) play crucial roles in a variety of biological processes via regulating expression of their target genes at the mRNA level. A number of computational approaches regarding miRNAs have been proposed, but most of them focus on miRNA gene finding or target predictions. Little computational work has been done to investigate the effective regulation of miRNAs.We propose a method to infer the effective regulatory activities of miRNAs by integrating microarray expression data with miRNA target predictions. The method is based on the idea that regulatory activity changes of miRNAs could be reflected by the expression changes of their target transcripts measured by microarray. To validate this method, we apply it to the microarray data sets that measure gene expression changes in cell lines after transfection or inhibition of several specific miRNAs. The results indicate that our method can detect activity enhancement of the transfected miRNAs as well as activity reduction of the inhibited miRNAs with high sensitivity and specificity. Furthermore, we show that our inference is robust with respect to false positives of target prediction.A huge amount of gene expression data sets are available in the literature, but miRNA regulation underlying these data sets is largely unknown. The method is easy to be implemented and can be used to investigate the miRNA effective regulation underlying the expression change profiles obtained from microarray experiments.
| S-EPMC2291556 | biostudies-literature
Project description:Mammalian genomes encode for thousands of microRNAs, which can potentially regulate the majority of protein-coding genes. They have been implicated in development and disease, leading to great interest in understanding their function, with computational methods being widely used to predict their targets. Most computational methods rely on sequence features, thermodynamics, and conservation filters; essentially scanning the whole transcriptome to predict one set of targets for each microRNA. This has the limitation of not considering that the same microRNA could have different sets of targets, and thus different functions, when expressed in different types of cells.To address this problem, we combine popular target prediction methods with expression profiles, via machine learning, to produce a new predictor: TargetExpress. Using independent data from microarrays and high-throughput sequencing, we show that TargetExpress outperforms existing methods, and that our predictions are enriched in functions that are coherent with the added expression profile and literature reports.Our method should be particularly useful for anyone studying the functions and targets of miRNAs in specific tissues or cells. TargetExpress is available at: http://targetexpress.ceiabreulab.org/ .
| S-EPMC4869178 | biostudies-literature
Project description:Considering accessibility of the 3'UTR is believed to increase the precision of microRNA target predictions. We show that, contrary to common belief, ranking by the hybridization energy or by the sum of the opening and hybridization energies, used in currently available algorithms, is not an efficient way to rank predictions. Instead, we describe an algorithm which also considers only the accessible binding sites but which ranks predictions according to over-representation. When compared with experimentally validated and refuted targets in the fruit fly and human, our algorithm shows a remarkable improvement in precision while significantly reducing the computational cost in comparison with other free energy based methods. In the human genome, our algorithm has at least twice higher precision than other methods with their default parameters. In the fruit fly, we find five times more validated targets among the top 500 predictions than other methods with their default parameters. Furthermore, using a common statistical framework we demonstrate explicitly the advantages of using the canonical ensemble instead of using the minimum free energy structure alone. We also find that 'naïve' global folding sometimes outperforms the local folding approach.
| S-EPMC3017612 | biostudies-literature