DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association Prediction
A growing number of studies have shown that aberrant microRNA (miRNA) expression is closely associated with the evolution and development of various complex human diseases. These key biomarkers’ identification and observation are significant for gaining a deeper understanding of disease pathogenesis...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/13/10/1514 |
| _version_ | 1797574508373082112 |
|---|---|
| author | Benzhi Dong Weidong Sun Dali Xu Guohua Wang Tianjiao Zhang |
| author_facet | Benzhi Dong Weidong Sun Dali Xu Guohua Wang Tianjiao Zhang |
| author_sort | Benzhi Dong |
| collection | DOAJ |
| description | A growing number of studies have shown that aberrant microRNA (miRNA) expression is closely associated with the evolution and development of various complex human diseases. These key biomarkers’ identification and observation are significant for gaining a deeper understanding of disease pathogenesis and therapeutic mechanisms. Consequently, pinpointing potential miRNA–disease associations (MDA) has become a prominent bioinformatics subject, encouraging several new computational methods given the advances in graph neural networks (GNN). Nevertheless, these existing methods commonly fail to exploit the network nodes’ global feature information, leaving the generation of high-quality embedding representations using graph properties as a critical unsolved issue. Addressing these challenges, we introduce the DAEMDA, a computational method designed to optimize the current models’ efficacy. First, we construct similarity and heterogeneous networks involving miRNAs and diseases, relying on experimentally corroborated miRNA–disease association data and analogous information. Then, a newly-fashioned parallel dual-channel feature encoder, designed to better comprehend the global information within the heterogeneous network and generate varying embedding representations, follows this. Ultimately, employing a neural network classifier, we merge the dual-channel embedding representations and undertake association predictions between miRNA and disease nodes. The experimental results of five-fold cross-validation and case studies of major diseases based on the HMDD v3.2 database show that this method can generate high-quality embedded representations and effectively improve the accuracy of MDA prediction. |
| first_indexed | 2024-03-10T21:24:30Z |
| format | Article |
| id | doaj.art-6a147ebc87a34821aef52f6e7a3d000f |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-10T21:24:30Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-6a147ebc87a34821aef52f6e7a3d000f2023-11-19T15:50:20ZengMDPI AGBiomolecules2218-273X2023-10-011310151410.3390/biom13101514DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association PredictionBenzhi Dong0Weidong Sun1Dali Xu2Guohua Wang3Tianjiao Zhang4College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, ChinaA growing number of studies have shown that aberrant microRNA (miRNA) expression is closely associated with the evolution and development of various complex human diseases. These key biomarkers’ identification and observation are significant for gaining a deeper understanding of disease pathogenesis and therapeutic mechanisms. Consequently, pinpointing potential miRNA–disease associations (MDA) has become a prominent bioinformatics subject, encouraging several new computational methods given the advances in graph neural networks (GNN). Nevertheless, these existing methods commonly fail to exploit the network nodes’ global feature information, leaving the generation of high-quality embedding representations using graph properties as a critical unsolved issue. Addressing these challenges, we introduce the DAEMDA, a computational method designed to optimize the current models’ efficacy. First, we construct similarity and heterogeneous networks involving miRNAs and diseases, relying on experimentally corroborated miRNA–disease association data and analogous information. Then, a newly-fashioned parallel dual-channel feature encoder, designed to better comprehend the global information within the heterogeneous network and generate varying embedding representations, follows this. Ultimately, employing a neural network classifier, we merge the dual-channel embedding representations and undertake association predictions between miRNA and disease nodes. The experimental results of five-fold cross-validation and case studies of major diseases based on the HMDD v3.2 database show that this method can generate high-quality embedded representations and effectively improve the accuracy of MDA prediction.https://www.mdpi.com/2218-273X/13/10/1514miRNA–disease association predictiontransformergraph encodinggraph attention network |
| spellingShingle | Benzhi Dong Weidong Sun Dali Xu Guohua Wang Tianjiao Zhang DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association Prediction Biomolecules miRNA–disease association prediction transformer graph encoding graph attention network |
| title | DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association Prediction |
| title_full | DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association Prediction |
| title_fullStr | DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association Prediction |
| title_full_unstemmed | DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association Prediction |
| title_short | DAEMDA: A Method with Dual-Channel Attention Encoding for miRNA–Disease Association Prediction |
| title_sort | daemda a method with dual channel attention encoding for mirna disease association prediction |
| topic | miRNA–disease association prediction transformer graph encoding graph attention network |
| url | https://www.mdpi.com/2218-273X/13/10/1514 |
| work_keys_str_mv | AT benzhidong daemdaamethodwithdualchannelattentionencodingformirnadiseaseassociationprediction AT weidongsun daemdaamethodwithdualchannelattentionencodingformirnadiseaseassociationprediction AT dalixu daemdaamethodwithdualchannelattentionencodingformirnadiseaseassociationprediction AT guohuawang daemdaamethodwithdualchannelattentionencodingformirnadiseaseassociationprediction AT tianjiaozhang daemdaamethodwithdualchannelattentionencodingformirnadiseaseassociationprediction |