Cargando…

Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes

A lot of studies indicated that aberrant expression of long non-coding RNA genes (lncRNAs) is closely related to human diseases. Identifying disease-related lncRNAs (disease lncRNAs) is critical for understanding the pathogenesis and etiology of diseases. Most of the previous methods focus on priori...

Descripción completa

Detalles Bibliográficos
Autores principales: Xuan, Ping, Cao, Yangkun, Zhang, Tiangang, Kong, Rui, Zhang, Zhaogong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6509943/
https://www.ncbi.nlm.nih.gov/pubmed/31130990
http://dx.doi.org/10.3389/fgene.2019.00416
_version_ 1783417350766198784
author Xuan, Ping
Cao, Yangkun
Zhang, Tiangang
Kong, Rui
Zhang, Zhaogong
author_facet Xuan, Ping
Cao, Yangkun
Zhang, Tiangang
Kong, Rui
Zhang, Zhaogong
author_sort Xuan, Ping
collection PubMed
description A lot of studies indicated that aberrant expression of long non-coding RNA genes (lncRNAs) is closely related to human diseases. Identifying disease-related lncRNAs (disease lncRNAs) is critical for understanding the pathogenesis and etiology of diseases. Most of the previous methods focus on prioritizing the potential disease lncRNAs based on shallow learning methods. The methods fail to extract the deep and complex feature representations of lncRNA-disease associations. Furthermore, nearly all the methods ignore the discriminative contributions of the similarity, association, and interaction relationships among lncRNAs, disease, and miRNAs for the association prediction. A dual convolutional neural networks with attention mechanisms based method is presented for predicting the candidate disease lncRNAs, and it is referred to as CNNLDA. CNNLDA deeply integrates the multiple source data like the lncRNA similarities, the disease similarities, the lncRNA-disease associations, the lncRNA-miRNA interactions, and the miRNA-disease associations. The diverse biological premises about lncRNAs, miRNAs, and diseases are combined to construct the feature matrix from the biological perspectives. A novel framework based on the dual convolutional neural networks is developed to learn the global and attention representations of the lncRNA-disease associations. The left part of the framework exploits the various information contained by the feature matrix to learn the global representation of lncRNA-disease associations. The different connection relationships among the lncRNA, miRNA, and disease nodes and the different features of these nodes have the discriminative contributions for the association prediction. Hence we present the attention mechanisms from the relationship level and the feature level respectively, and the right part of the framework learns the attention representation of associations. The experimental results based on the cross validation indicate that CNNLDA yields superior performance than several state-of-the-art methods. Case studies on stomach cancer, lung cancer, and colon cancer further demonstrate CNNLDA's ability to discover the potential disease lncRNAs.
format Online
Article
Text
id pubmed-6509943
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-65099432019-05-24 Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes Xuan, Ping Cao, Yangkun Zhang, Tiangang Kong, Rui Zhang, Zhaogong Front Genet Genetics A lot of studies indicated that aberrant expression of long non-coding RNA genes (lncRNAs) is closely related to human diseases. Identifying disease-related lncRNAs (disease lncRNAs) is critical for understanding the pathogenesis and etiology of diseases. Most of the previous methods focus on prioritizing the potential disease lncRNAs based on shallow learning methods. The methods fail to extract the deep and complex feature representations of lncRNA-disease associations. Furthermore, nearly all the methods ignore the discriminative contributions of the similarity, association, and interaction relationships among lncRNAs, disease, and miRNAs for the association prediction. A dual convolutional neural networks with attention mechanisms based method is presented for predicting the candidate disease lncRNAs, and it is referred to as CNNLDA. CNNLDA deeply integrates the multiple source data like the lncRNA similarities, the disease similarities, the lncRNA-disease associations, the lncRNA-miRNA interactions, and the miRNA-disease associations. The diverse biological premises about lncRNAs, miRNAs, and diseases are combined to construct the feature matrix from the biological perspectives. A novel framework based on the dual convolutional neural networks is developed to learn the global and attention representations of the lncRNA-disease associations. The left part of the framework exploits the various information contained by the feature matrix to learn the global representation of lncRNA-disease associations. The different connection relationships among the lncRNA, miRNA, and disease nodes and the different features of these nodes have the discriminative contributions for the association prediction. Hence we present the attention mechanisms from the relationship level and the feature level respectively, and the right part of the framework learns the attention representation of associations. The experimental results based on the cross validation indicate that CNNLDA yields superior performance than several state-of-the-art methods. Case studies on stomach cancer, lung cancer, and colon cancer further demonstrate CNNLDA's ability to discover the potential disease lncRNAs. Frontiers Media S.A. 2019-05-03 /pmc/articles/PMC6509943/ /pubmed/31130990 http://dx.doi.org/10.3389/fgene.2019.00416 Text en Copyright © 2019 Xuan, Cao, Zhang, Kong and Zhang. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Genetics
Xuan, Ping
Cao, Yangkun
Zhang, Tiangang
Kong, Rui
Zhang, Zhaogong
Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes
title Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes
title_full Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes
title_fullStr Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes
title_full_unstemmed Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes
title_short Dual Convolutional Neural Networks With Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes
title_sort dual convolutional neural networks with attention mechanisms based method for predicting disease-related lncrna genes
topic Genetics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6509943/
https://www.ncbi.nlm.nih.gov/pubmed/31130990
http://dx.doi.org/10.3389/fgene.2019.00416
work_keys_str_mv AT xuanping dualconvolutionalneuralnetworkswithattentionmechanismsbasedmethodforpredictingdiseaserelatedlncrnagenes
AT caoyangkun dualconvolutionalneuralnetworkswithattentionmechanismsbasedmethodforpredictingdiseaserelatedlncrnagenes
AT zhangtiangang dualconvolutionalneuralnetworkswithattentionmechanismsbasedmethodforpredictingdiseaserelatedlncrnagenes
AT kongrui dualconvolutionalneuralnetworkswithattentionmechanismsbasedmethodforpredictingdiseaserelatedlncrnagenes
AT zhangzhaogong dualconvolutionalneuralnetworkswithattentionmechanismsbasedmethodforpredictingdiseaserelatedlncrnagenes