mirMark: a site-level and UTR-level classifier for miRNA target prediction

Menor, Mark; Ching, Travers; Zhu, Xun; Garmire, David; Garmire, Lana X.

doi:10.1186/preaccept-1016030070136510

Cited by 11 publications

(26 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first dataset was downloaded from the supplementary tables of the DeepMirTar study, which contains 3,963 positive pairs of miRNA:target and 3,905 negative pairs of miRNA:target. The positive pairs in the DeepMirTar dataset were obtained from three resources: mirMark data (Menor, et al, 2014), CLASH data (Helwak, et al, 2013), and PAR-CLIP data (Hafner, et al, 2010). And only the target sites located in 3'UTRs, and the target sites with canonical seeds (exact W-C pairing of 2-7 or 3-8 nts of the miRNA) and non-canonical seeds (pairing at positions 2-7 or 3-8, allowing G-U pairs and up to one bulged or mis-matched nucleotide) were included.…”

Section: Datasetsmentioning

confidence: 99%

“…They were developed earlier, hence, the training datasets they used are much smaller. 507 target site-level and 2,891 gene-level miRNA:target pairs from mirMark repository (Menor, et al, 2014) were taken as the positive training dataset in the deepTarget study. mirMark repository is part of the DeepMirTar dataset, subsequently, we compared miTAR1 with the results reported from deepTarget study.…”

Section: Performance Comparison With Earlier Studies Using Test Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

miTAR: a hybrid deep learning-based approach for predicting miRNA targets

Zhao

Barbazuk

et al. 2020

Preprint

View full text Add to dashboard Cite

microRNAs (miRNAs) are a major type of small RNA that alter gene expression at the posttranscriptional or translational level. They have been shown to play important roles in a wide range of biological processes. Many computational methods have been developed to predict targets of miRNAs in order to understand miRNAs' function. However, the majority of the methods depend on a set of predefined features that require considerable effort and resources to compute, and these methods often do not effectively on the prediction of miRNA targets. Therefore, we developed a novel hybrid deep learningbased approach that is capable to predict miRNA targets at a higher accuracy. Our approach integrates two deep learning methods: convolutional neural networks (CNNs) that excel in learning spatial features, and recurrent neural networks (RNNs) that discern sequential features. By combining CNNs and RNNs, our approach has the advantages of learning both the intrinsic spatial and sequential features of miRNA:target. The inputs for the approach are raw sequences of miRNA and gene sequences. Data from two latest miRNA target prediction studies were used in our study: the DeepMirTar dataset and the miRAW dataset. Two models were obtained by training on the two datasets separately. The models achieved a higher accuracy than the methods developed in the previous studies: 0.9787 vs. 0.9348 for the DeepMirTar dataset; 0.9649 vs. 0.935 for the miRAW dataset. We also calculated a series of model evaluation metrics including sensitivity, specificity, F-score and Brier Score. Our approach consistently outperformed the current methods. In addition, we compared our approach with earlier developed deep learning methods, resulting in an overall better performance. Lastly, a unified model for both datasets was developed with an accuracy of 0.9545. We named the unified model miTAR for miRNA target prediction. The source code and executable are available at https://github.com/tjgu/miTAR. Advances in our understanding of the interactions between miRNAs and their targets has led to the development of many computational methods/tools to predict miRNA targets. The majority of these tools are based on common features of the miRNA:target interaction. Four features are widely used: sequence complement (especially in the seed region that is generally defined as a 6 or 7 nts sequence starting at the second or third nucleotide(nt) of the miRNA sequence), thermodynamic stability, target site accessibility and sequence conservation among species (Peterson, et al., 2014). Several widely used tools have been developed based on these features. For example, miRanda (Enright, et al., 2003) relies on sequence complementarity and binding energy; TargetScanS (Lewis, et al., 2005) relies on sequence complementarity in seed region; while PITA (Kertesz, et al., 2007) relies on target site accessibility. However, miRNA targets predicted by different methods and tools are inconsistent with one another. Furthermore, using known features limits the ability to predict novel o...

show abstract

Section: Datasetsmentioning

confidence: 99%

Section: Performance Comparison With Earlier Studies Using Test Datasetsmentioning

confidence: 99%

miTAR: a hybrid deep learning-based approach for predicting miRNA targets

Zhao

Barbazuk

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Menor et al [31] described 151 site-level features between miRNAtarget pairs for target prediction, categorizing them into seven groups: binding energy, the type of seed matching, miRNA pairing, target site accessibility, target site composition, target site conservation, and the location of target sites. To relieve these feature engineering required for target prediction in conventional approaches, deepTarget exploits the unsupervised feature learning using the RNN encoder-decoder model [44].…”

Section: Modeling Rnas Using Rnn Based Autoencodermentioning

confidence: 99%

“…To boost the sensitivity of miRNA target prediction, a variety of features have been proposed. According to Menor et al [31], as many as 151 kinds of features appear in the literature, which can be broadly grouped into four common types [37]: the degree of Watson-Crick matches of a seed sequence (see Figure 2); the degree of sequence conservation across species; Gibbs free energy, which measures the stability of the binding of a miRNA-mRNA pair, and the site accessibility, which measures the hybridization possibility of a pair from their secondary structures.…”

Section: Introductionmentioning

confidence: 99%

deepTarget

Lee

Baek

Park

et al. 2016

Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

View full text Add to dashboard Cite

MicroRNAs (miRNAs) are short sequences of ribonucleic acids that control the expression of target messenger RNAs (mRNAs) by binding them. Robust prediction of miRNA-mRNA pairs is of utmost importance in deciphering gene regulation but has been challenging because of high false positive rates, despite a deluge of computational tools that normally require laborious manual feature extraction. This paper presents an end-to-end machine learning framework for miRNA target prediction. Leveraged by deep recurrent neural networks-based auto-encoding and sequence-sequence interaction learning, our approach not only delivers an unprecedented level of accuracy but also eliminates the need for manual feature extraction. The performance gap between the proposed method and existing alternatives is substantial (over 25% increase in F-measure), and deepTarget delivers a quantum leap in the longstanding challenge of robust miRNA target prediction. [availability: http://data.snu.ac.kr/pub/deepTarget ]

show abstract

“…The trainees should be able to creatively transform data, by taking advantage of prior biological knowledge such as pathway or network information 4,5 . The trainees should have courses in statistics to thoroughly understand issues such as sample size, power, multiple hypothesis testing, classification (unsupervised learning), and generalized regression techniques (supervised learning) 6,7 . Training in multi-omics data integration (from the same population cohort) and meta-omics data integration (from heterogeneous populations) will be paramount to derive meaningful discoveries on molecular subtypes of diseases 8 .…”

Section: Areas Of Biomedical Data Science Demanding New Workforcementioning

confidence: 99%