HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step Rule
Identifying new treatments for existing drugs can help reduce drug development costs and explore novel indications of drugs. The prediction of associations between drugs and diseases is challenging because their similarities and relations are complicated and non-linear. We propose a HeteroDualNet mo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-11-01
|
| Series: | Frontiers in Pharmacology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fphar.2019.01301/full |
| _version_ | 1818285122596634624 |
|---|---|
| author | Ping Xuan Hui Cui Tonghui Shen Nan Sheng Tiangang Zhang |
| author_facet | Ping Xuan Hui Cui Tonghui Shen Nan Sheng Tiangang Zhang |
| author_sort | Ping Xuan |
| collection | DOAJ |
| description | Identifying new treatments for existing drugs can help reduce drug development costs and explore novel indications of drugs. The prediction of associations between drugs and diseases is challenging because their similarities and relations are complicated and non-linear. We propose a HeteroDualNet model to address this issue. Firstly, three types of matrices are extracted to represent intra-drug similarities, intra-disease similarity and drug-disease associations. The intra-drug similarities consider three drug features and a newly introduced drug-related disease correlation. Secondly, an embedding mechanism is proposed to integrate these matrices in a heterogenous drug-disease association layer (hetero-layer). Further, a neighbouring heterogeneous layer (hetero-layer-N) is constructed to incorporate the biological premise that similar drugs can often treat related diseases. Finally, a dual convolutional neural network is built with hetero-layer and hetero-layer-N as two branches to learn from characteristics of drug-disease and the relations of their neighbours simultaneously. HeteroDualNet outperformed the other four methods in comparison over a public dataset of 763 drugs and 681 diseases in terms of Areas Under the Curves of Receiver Operating Characteristics and Precision-Recall, and recall rate at top k. Case study of five drugs further proved the capacity of HeteroDualNet in finding reliable disease candidates of drugs as validated by database records or literature. Our findings show that the embedded heterogenous layers of original and neighbouring drug-disease representations in a dual neural network improved the association prediction performance. |
| first_indexed | 2024-12-13T01:03:41Z |
| format | Article |
| id | doaj.art-80a573a8c1a649a7b9ce5d5f3da3978d |
| institution | Directory Open Access Journal |
| issn | 1663-9812 |
| language | English |
| last_indexed | 2024-12-13T01:03:41Z |
| publishDate | 2019-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pharmacology |
| spelling | doaj.art-80a573a8c1a649a7b9ce5d5f3da3978d2022-12-22T00:04:36ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122019-11-011010.3389/fphar.2019.01301479982HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step RulePing Xuan0Hui Cui1Tonghui Shen2Nan Sheng3Tiangang Zhang4School of Computer Science and Technology, Heilongjiang University, Harbin, ChinaDepartment of Computer Science and Information Technology, La Trobe University, Bundoora, VIC, AustraliaSchool of Computer Science and Technology, Heilongjiang University, Harbin, ChinaSchool of Computer Science and Technology, Heilongjiang University, Harbin, ChinaSchool of Mathematical Science, Heilongjiang University, Harbin, ChinaIdentifying new treatments for existing drugs can help reduce drug development costs and explore novel indications of drugs. The prediction of associations between drugs and diseases is challenging because their similarities and relations are complicated and non-linear. We propose a HeteroDualNet model to address this issue. Firstly, three types of matrices are extracted to represent intra-drug similarities, intra-disease similarity and drug-disease associations. The intra-drug similarities consider three drug features and a newly introduced drug-related disease correlation. Secondly, an embedding mechanism is proposed to integrate these matrices in a heterogenous drug-disease association layer (hetero-layer). Further, a neighbouring heterogeneous layer (hetero-layer-N) is constructed to incorporate the biological premise that similar drugs can often treat related diseases. Finally, a dual convolutional neural network is built with hetero-layer and hetero-layer-N as two branches to learn from characteristics of drug-disease and the relations of their neighbours simultaneously. HeteroDualNet outperformed the other four methods in comparison over a public dataset of 763 drugs and 681 diseases in terms of Areas Under the Curves of Receiver Operating Characteristics and Precision-Recall, and recall rate at top k. Case study of five drugs further proved the capacity of HeteroDualNet in finding reliable disease candidates of drugs as validated by database records or literature. Our findings show that the embedded heterogenous layers of original and neighbouring drug-disease representations in a dual neural network improved the association prediction performance.https://www.frontiersin.org/article/10.3389/fphar.2019.01301/fulldrug-disease association predictionmultiple kinds of similaritiesneighbouring heterogeneous layerdeep learningdual convolutional neural network |
| spellingShingle | Ping Xuan Hui Cui Tonghui Shen Nan Sheng Tiangang Zhang HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step Rule Frontiers in Pharmacology drug-disease association prediction multiple kinds of similarities neighbouring heterogeneous layer deep learning dual convolutional neural network |
| title | HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step Rule |
| title_full | HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step Rule |
| title_fullStr | HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step Rule |
| title_full_unstemmed | HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step Rule |
| title_short | HeteroDualNet: A Dual Convolutional Neural Network With Heterogeneous Layers for Drug-Disease Association Prediction via Chou’s Five-Step Rule |
| title_sort | heterodualnet a dual convolutional neural network with heterogeneous layers for drug disease association prediction via chou s five step rule |
| topic | drug-disease association prediction multiple kinds of similarities neighbouring heterogeneous layer deep learning dual convolutional neural network |
| url | https://www.frontiersin.org/article/10.3389/fphar.2019.01301/full |
| work_keys_str_mv | AT pingxuan heterodualnetadualconvolutionalneuralnetworkwithheterogeneouslayersfordrugdiseaseassociationpredictionviachousfivesteprule AT huicui heterodualnetadualconvolutionalneuralnetworkwithheterogeneouslayersfordrugdiseaseassociationpredictionviachousfivesteprule AT tonghuishen heterodualnetadualconvolutionalneuralnetworkwithheterogeneouslayersfordrugdiseaseassociationpredictionviachousfivesteprule AT nansheng heterodualnetadualconvolutionalneuralnetworkwithheterogeneouslayersfordrugdiseaseassociationpredictionviachousfivesteprule AT tiangangzhang heterodualnetadualconvolutionalneuralnetworkwithheterogeneouslayersfordrugdiseaseassociationpredictionviachousfivesteprule |