MiRTDL: A Deep Learning Approach for miRNA Target Prediction

Abstract Background microRNAs (miRNAs) have been shown to play essential roles in a wide range of biological processes. Many computational methods have been developed to identify targets of miRNAs. However, the majority of these methods depend on pre-defined features that require considerable efforts and resources to compute and often prove suboptimal at predicting miRNA targets. Results We developed a novel hybrid deep learning-based (DL-based) approach that is capable of predicting miRNA targets at a higher accuracy. This approach integrates convolutional neural networks (CNNs) that excel in learning spatial features and recurrent neural networks (RNNs) that discern sequential features. Therefore, our approach has the advantages of learning both the intrinsic spatial and sequential features of miRNA:target. The inputs for our approach are raw sequences of miRNAs and genes that can be obtained effortlessly. We applied our approach on two human datasets from recently miRNA target prediction studies and trained two models. We demonstrated that the two models consistently outperform the previous methods according to evaluation metrics on test datasets. Comparing our approach with currently available alternatives on independent datasets shows that our approach delivers substantial improvements in performance. We also show with multiple evidences that our approach is more robust than other methods on small datasets. Our study is the first study to perform comparisons across multiple existing DL-based approaches on miRNA target prediction. Furthermore, we examined the contribution of a Max pooling layer in between the CNN and RNN and demonstrated that it improves the performance of all our models. Finally, a unified model was developed that is robust on fitting different input datasets. Conclusions We present a new DL-based approach for predicting miRNA targets and demonstrate that our approach outperforms the current alternatives. We supplied an easy-to-use tool, miTAR, at https://github.com/tjgu/miTAR. Furthermore, our analysis results support that Max Pooling generally benefits the hybrid models and potentially prevents overfitting for hybrid models.

Download Full-text

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

10.1101/2020.04.02.022608 ◽

2020 ◽

Author(s):

Tongjun Gu ◽

Xiwu Zhao ◽

William Bradley Barbazuk ◽

Ji-Hyun Lee

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Mirna Target ◽

Target Prediction ◽

Unified Model ◽

Brier Score ◽

Mirna Target Prediction ◽

Learning Methods ◽

Mirna Targets ◽

Wide Range

AbstractmicroRNAs (miRNAs) are a major type of small RNA that alter gene expression at the post-transcriptional 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 pre-defined 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 learning-based 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 higher than the current methods (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.

Download Full-text

A machine learning approach for miRNA target prediction

2008 IEEE International Workshop on Genomic Signal Processing and Statistics ◽

10.1109/gensips.2008.4555655 ◽

2008 ◽

Cited By ~ 1

Author(s):

Hui Liu ◽

Dong Yue ◽

Lin Zhang ◽

Shou-Jiang Gao ◽

Yufei Huang

Keyword(s):

Machine Learning ◽

Mirna Target ◽

Target Prediction ◽

Learning Approach ◽

Mirna Target Prediction ◽

Machine Learning Approach

Download Full-text

A Novel Approach for Mirna Target Prediction Using Deep Learning

2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT) ◽

10.1109/icicct.2018.8473308 ◽

2018 ◽

Author(s):

Shaina Paulson ◽

T.S Jyothis

Keyword(s):

Deep Learning ◽

Mirna Target ◽

Target Prediction ◽

Mirna Target Prediction ◽

Novel Approach

Download Full-text

Identification of BAP1-associated MicroRNAs and Implications in Cancer Development

10.31487/j.ijcst.2019.01.01 ◽

2019 ◽

pp. 1-4

Author(s):

Tikam Chand ◽

Tikam Chand

Keyword(s):

Gene Regulation ◽

In Silico ◽

Mirna Target ◽

Target Prediction ◽

Differential Regulation ◽

Cancer Development ◽

Mirna Target Prediction ◽

Cancer Types ◽

In Silico Tools

Having role in gene regulation and silencing, miRNAs have been implicated in development and progression of a number of diseases, including cancer. Herein, I present potential miRNAs associated with BAP1 gene identified using in-silico tools such as TargetScan and Exiqon miRNA Target Prediction. I identified fifteen highly conserved miRNA (hsa-miR-423-5p, hsa-miR-3184-5p, hsa-miR-4319, hsa-miR125b-5p, hsa-miR-125a-5p, hsa-miR-6893-3p, hsa-miR-200b-3p, hsa-miR-200c-3p, hsa-miR-505-3p.1, hsa-miR-429, hsa-miR-370-3p, hsa-miR-125a-5p, hsa-miR-141-3p, hsa-miR-200a-3p, and hsa-miR-429) associated with BAP1 gene. We also predicted the differential regulation of these twelve miRNAs in different cancer types.

Download Full-text

Beyond seed match: Improving miRNA target prediction using PAR-CLIP data

2011 IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS) ◽

10.1109/gensips.2011.6169461 ◽

2011 ◽

Author(s):

Mingzhu Lu ◽

C. L. Philip Chen ◽

Yufei Huang

Keyword(s):

Mirna Target ◽

Target Prediction ◽

Mirna Target Prediction ◽

Seed Match

Download Full-text

Comprehensive Overview and Assessment of microRNA Target Prediction Tools in Homo sapiens and Drosophila melanogaster

Current Bioinformatics ◽

10.2174/1574893614666190103101033 ◽

2019 ◽

Vol 14 (5) ◽

pp. 432-445 ◽

Cited By ~ 3

Author(s):

Muniba Faiza ◽

Khushnuma Tanveer ◽

Saman Fatihi ◽

Yonghua Wang ◽

Khalid Raza

Keyword(s):

Drosophila Melanogaster ◽

Mirna Target ◽

Homo Sapiens ◽

Target Prediction ◽

Computational Prediction ◽

Transcriptional Level ◽

Mirna Target Prediction ◽

Microrna Target ◽

Prediction Tools ◽

Mirna Targets

Background: MicroRNAs (miRNAs) are small non-coding RNAs that control gene expression at the post-transcriptional level through complementary base pairing with the target mRNA, leading to mRNA degradation and blocking translation process. Many dysfunctions of these small regulatory molecules have been linked to the development and progression of several diseases. Therefore, it is necessary to reliably predict potential miRNA targets. Objective: A large number of computational prediction tools have been developed which provide a faster way to find putative miRNA targets, but at the same time, their results are often inconsistent. Hence, finding a reliable, functional miRNA target is still a challenging task. Also, each tool is equipped with different algorithms, and it is difficult for the biologists to know which tool is the best choice for their study. Methods: We analyzed eleven miRNA target predictors on Drosophila melanogaster and Homo sapiens by applying significant empirical methods to evaluate and assess their accuracy and performance using experimentally validated high confident mature miRNAs and their targets. In addition, this paper also describes miRNA target prediction algorithms, and discusses common features of frequently used target prediction tools. Results: The results show that MicroT, microRNA and CoMir are the best performing tool on Drosopihla melanogaster; while TargetScan and miRmap perform well for Homo sapiens. The predicted results of each tool were combined in order to improve the performance in both the datasets, but any significant improvement is not observed in terms of true positives. Conclusion: The currently available miRNA target prediction tools greatly suffer from a large number of false positives. Therefore, computational prediction of significant targets with high statistical confidence is still an open challenge.

Download Full-text