A two-stream convolutional neural network for microRNA transcription start site feature integration and identification
Abstract MicroRNAs (miRNAs) play important roles in post-transcriptional gene regulation and phenotype development. Understanding the regulation of miRNA genes is critical to understand gene regulation. One of the challenges to study miRNA gene regulation is the lack of condition-specific annotation...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-03-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-021-85173-x |
id |
doaj-ccdabcc9c3b34b83b49ec129f7e069ba |
---|---|
record_format |
Article |
spelling |
doaj-ccdabcc9c3b34b83b49ec129f7e069ba2021-03-11T12:22:26ZengNature Publishing GroupScientific Reports2045-23222021-03-0111111310.1038/s41598-021-85173-xA two-stream convolutional neural network for microRNA transcription start site feature integration and identificationMingyu Cha0Hansi Zheng1Amlan Talukder2Clayton Barham3Xiaoman Li4Haiyan Hu5Department of Computer Science, University of Central FloridaDepartment of Computer Science, University of Central FloridaDepartment of Computer Science, University of Central FloridaDepartment of Computer Science, University of Central FloridaBurnett School of Biomedical Science, College of Medicine, University of Central FloridaDepartment of Computer Science, University of Central FloridaAbstract MicroRNAs (miRNAs) play important roles in post-transcriptional gene regulation and phenotype development. Understanding the regulation of miRNA genes is critical to understand gene regulation. One of the challenges to study miRNA gene regulation is the lack of condition-specific annotation of miRNA transcription start sites (TSSs). Unlike protein-coding genes, miRNA TSSs can be tens of thousands of nucleotides away from the precursor miRNAs and they are hard to be detected by conventional RNA-Seq experiments. A number of studies have been attempted to computationally predict miRNA TSSs. However, high-resolution condition-specific miRNA TSS prediction remains a challenging problem. Recently, deep learning models have been successfully applied to various bioinformatics problems but have not been effectively created for condition-specific miRNA TSS prediction. Here we created a two-stream deep learning model called D-miRT for computational prediction of condition-specific miRNA TSSs ( http://hulab.ucf.edu/research/projects/DmiRT/ ). D-miRT is a natural fit for the integration of low-resolution epigenetic features (DNase-Seq and histone modification data) and high-resolution sequence features. Compared with alternative computational models on different sets of training data, D-miRT outperformed all baseline models and demonstrated high accuracy for condition-specific miRNA TSS prediction tasks. Comparing with the most recent approaches on cell-specific miRNA TSS identification using cell lines that were unseen to the model training processes, D-miRT also showed superior performance.https://doi.org/10.1038/s41598-021-85173-x |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mingyu Cha Hansi Zheng Amlan Talukder Clayton Barham Xiaoman Li Haiyan Hu |
spellingShingle |
Mingyu Cha Hansi Zheng Amlan Talukder Clayton Barham Xiaoman Li Haiyan Hu A two-stream convolutional neural network for microRNA transcription start site feature integration and identification Scientific Reports |
author_facet |
Mingyu Cha Hansi Zheng Amlan Talukder Clayton Barham Xiaoman Li Haiyan Hu |
author_sort |
Mingyu Cha |
title |
A two-stream convolutional neural network for microRNA transcription start site feature integration and identification |
title_short |
A two-stream convolutional neural network for microRNA transcription start site feature integration and identification |
title_full |
A two-stream convolutional neural network for microRNA transcription start site feature integration and identification |
title_fullStr |
A two-stream convolutional neural network for microRNA transcription start site feature integration and identification |
title_full_unstemmed |
A two-stream convolutional neural network for microRNA transcription start site feature integration and identification |
title_sort |
two-stream convolutional neural network for microrna transcription start site feature integration and identification |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2021-03-01 |
description |
Abstract MicroRNAs (miRNAs) play important roles in post-transcriptional gene regulation and phenotype development. Understanding the regulation of miRNA genes is critical to understand gene regulation. One of the challenges to study miRNA gene regulation is the lack of condition-specific annotation of miRNA transcription start sites (TSSs). Unlike protein-coding genes, miRNA TSSs can be tens of thousands of nucleotides away from the precursor miRNAs and they are hard to be detected by conventional RNA-Seq experiments. A number of studies have been attempted to computationally predict miRNA TSSs. However, high-resolution condition-specific miRNA TSS prediction remains a challenging problem. Recently, deep learning models have been successfully applied to various bioinformatics problems but have not been effectively created for condition-specific miRNA TSS prediction. Here we created a two-stream deep learning model called D-miRT for computational prediction of condition-specific miRNA TSSs ( http://hulab.ucf.edu/research/projects/DmiRT/ ). D-miRT is a natural fit for the integration of low-resolution epigenetic features (DNase-Seq and histone modification data) and high-resolution sequence features. Compared with alternative computational models on different sets of training data, D-miRT outperformed all baseline models and demonstrated high accuracy for condition-specific miRNA TSS prediction tasks. Comparing with the most recent approaches on cell-specific miRNA TSS identification using cell lines that were unseen to the model training processes, D-miRT also showed superior performance. |
url |
https://doi.org/10.1038/s41598-021-85173-x |
work_keys_str_mv |
AT mingyucha atwostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT hansizheng atwostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT amlantalukder atwostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT claytonbarham atwostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT xiaomanli atwostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT haiyanhu atwostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT mingyucha twostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT hansizheng twostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT amlantalukder twostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT claytonbarham twostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT xiaomanli twostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification AT haiyanhu twostreamconvolutionalneuralnetworkformicrornatranscriptionstartsitefeatureintegrationandidentification |
_version_ |
1724224403489685504 |