Deep neural networks for human microRNA precursor detection

• Published in: BMC bioinformatics 2020-01, Vol.21 (1), p.17-17, Article 17
• Main Authors: Zheng, Xueming, Fu, Xingli, Wang, Kaicheng, Wang, Meng
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial neural networks; Base Sequence; Benchmarking; Biochemistry; Biological activity; Biological research; Biosynthesis; Cable television broadcasting industry; Classification; Computer applications; Convolution; Databases, Genetic; Datasets; Deep Learning; Detection; DNN; Enzymes; Feature extraction; Gene expression; Gene sequencing; Genes; Humans; International economic relations; Learning algorithms; Machine Learning; Methodology; MicroRNA; MicroRNAs; MicroRNAs - chemistry; MicroRNAs - genetics; miRNA; miRNAs; Natural language processing; Neural networks; Neural Networks, Computer; Post-transcription; Precursors; Predictions; Protein Structure, Secondary; Recurrent neural networks; Regularization; Regularization methods; Research methodology; Ribonucleic acid; RNA; RNA Precursors - chemistry; RNA Precursors - genetics; Software; Subject specialists; Support vector machines; Time; Transcription (Genetics)
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-020-3339-7

MicroRNAs (miRNAs) play important roles in a variety of biological processes by regulating gene expression at the post-transcriptional level. So, the discovery of new miRNAs has become a popular task in biological research. Since the experimental identification of miRNAs is time-consuming, many computational tools have been developed to identify miRNA precursor (pre-miRNA). Most of these computation methods are based on traditional machine learning methods and their performance depends heavily on the selected features which are usually determined by domain experts. To develop easily implemented methods with better performance, we investigated different deep learning architectures for the pre-miRNAs identification. In this work, we applied convolution neural networks (CNN) and recurrent neural networks (RNN) to predict human pre-miRNAs. We combined the sequences with the predicted secondary structures of pre-miRNAs as input features of our models, avoiding the feature extraction and selection process by hand. The models were easily trained on the training dataset with low generalization error, and therefore had satisfactory performance on the test dataset. The prediction results on the same benchmark dataset showed that our models outperformed or were highly comparable to other state-of-the-art methods in this area. Furthermore, our CNN model trained on human dataset had high prediction accuracy on data from other species. Deep neural networks (DNN) could be utilized for the human pre-miRNAs detection with high performance. Complex features of RNA sequences could be automatically extracted by CNN and RNN, which were used for the pre-miRNAs prediction. Through proper regularization, our deep learning models, although trained on comparatively small dataset, had strong generalization ability.