DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing
The rapid spread of novel coronavirus pneumonia (COVID-19) has led to a dramatically increased mortality rate worldwide. Despite many efforts, the rapid development of an effective vaccine for this novel virus will take considerable time and relies on the identification of drug-target (DT) interacti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9197589/ |
| _version_ | 1819111602386894848 |
|---|---|
| author | Mohamed Abdel-Basset Hossam Hawash Mohamed Elhoseny Ripon K. Chakrabortty Michael Ryan |
| author_facet | Mohamed Abdel-Basset Hossam Hawash Mohamed Elhoseny Ripon K. Chakrabortty Michael Ryan |
| author_sort | Mohamed Abdel-Basset |
| collection | DOAJ |
| description | The rapid spread of novel coronavirus pneumonia (COVID-19) has led to a dramatically increased mortality rate worldwide. Despite many efforts, the rapid development of an effective vaccine for this novel virus will take considerable time and relies on the identification of drug-target (DT) interactions utilizing commercially available medication to identify potential inhibitors. Motivated by this, we propose a new framework, called DeepH-DTA, for predicting DT binding affinities for heterogeneous drugs. We propose a heterogeneous graph attention (HGAT) model to learn topological information of compound molecules and bidirectional ConvLSTM layers for modeling spatio-sequential information in simplified molecular-input line-entry system (SMILES) sequences of drug data. For protein sequences, we propose a squeezed-excited dense convolutional network for learning hidden representations within amino acid sequences; while utilizing advanced embedding techniques for encoding both kinds of input sequences. The performance of DeepH-DTA is evaluated through extensive experiments against cutting-edge approaches utilising two public datasets (Davis, and KIBA) which comprise eclectic samples of the kinase protein family and the pertinent inhibitors. DeepH-DTA attains the highest Concordance Index (CI) of 0.924 and 0.927 and also achieved a mean square error (MSE) of 0.195 and 0.111 on the Davis and KIBA datasets respectively. Moreover, a study using FDA-approved drugs from the Drug Bank database is performed using DeepH-DTA to predict the affinity scores of drugs against SARS-CoV-2 amino acid sequences, and the results show that that the model can predict some of the SARS-Cov-2 inhibitors that have been recently approved in many clinical studies. |
| first_indexed | 2024-12-22T04:00:13Z |
| format | Article |
| id | doaj.art-9e698290feb0446fa383624edbade314 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T04:00:13Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9e698290feb0446fa383624edbade3142022-12-21T18:39:45ZengIEEEIEEE Access2169-35362020-01-01817043317045110.1109/ACCESS.2020.30242389197589DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug RepurposingMohamed Abdel-Basset0https://orcid.org/0000-0002-2794-3936Hossam Hawash1https://orcid.org/0000-0001-9925-3232Mohamed Elhoseny2https://orcid.org/0000-0001-6347-8368Ripon K. Chakrabortty3https://orcid.org/0000-0002-7373-0149Michael Ryan4https://orcid.org/0000-0002-6335-3773Faculty of Computers and Informatics, Zagazig University, Zagazig, EgyptFaculty of Computers and Informatics, Zagazig University, Zagazig, EgyptDepartment of Computer Science, College of Computer Information Technology, American University in the Emirates, Dubai, United Arab EmiratesCapability Systems Centre, School of Engineering and IT, University of New South Wales Canberra, Canberra, ACT, AustraliaCapability Systems Centre, School of Engineering and IT, University of New South Wales Canberra, Canberra, ACT, AustraliaThe rapid spread of novel coronavirus pneumonia (COVID-19) has led to a dramatically increased mortality rate worldwide. Despite many efforts, the rapid development of an effective vaccine for this novel virus will take considerable time and relies on the identification of drug-target (DT) interactions utilizing commercially available medication to identify potential inhibitors. Motivated by this, we propose a new framework, called DeepH-DTA, for predicting DT binding affinities for heterogeneous drugs. We propose a heterogeneous graph attention (HGAT) model to learn topological information of compound molecules and bidirectional ConvLSTM layers for modeling spatio-sequential information in simplified molecular-input line-entry system (SMILES) sequences of drug data. For protein sequences, we propose a squeezed-excited dense convolutional network for learning hidden representations within amino acid sequences; while utilizing advanced embedding techniques for encoding both kinds of input sequences. The performance of DeepH-DTA is evaluated through extensive experiments against cutting-edge approaches utilising two public datasets (Davis, and KIBA) which comprise eclectic samples of the kinase protein family and the pertinent inhibitors. DeepH-DTA attains the highest Concordance Index (CI) of 0.924 and 0.927 and also achieved a mean square error (MSE) of 0.195 and 0.111 on the Davis and KIBA datasets respectively. Moreover, a study using FDA-approved drugs from the Drug Bank database is performed using DeepH-DTA to predict the affinity scores of drugs against SARS-CoV-2 amino acid sequences, and the results show that that the model can predict some of the SARS-Cov-2 inhibitors that have been recently approved in many clinical studies.https://ieeexplore.ieee.org/document/9197589/Deep learningdrug-target interactionSARS-CoV-2 |
| spellingShingle | Mohamed Abdel-Basset Hossam Hawash Mohamed Elhoseny Ripon K. Chakrabortty Michael Ryan DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing IEEE Access Deep learning drug-target interaction SARS-CoV-2 |
| title | DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing |
| title_full | DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing |
| title_fullStr | DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing |
| title_full_unstemmed | DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing |
| title_short | DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing |
| title_sort | deeph dta deep learning for predicting drug target interactions a case study of covid 19 drug repurposing |
| topic | Deep learning drug-target interaction SARS-CoV-2 |
| url | https://ieeexplore.ieee.org/document/9197589/ |
| work_keys_str_mv | AT mohamedabdelbasset deephdtadeeplearningforpredictingdrugtargetinteractionsacasestudyofcovid19drugrepurposing AT hossamhawash deephdtadeeplearningforpredictingdrugtargetinteractionsacasestudyofcovid19drugrepurposing AT mohamedelhoseny deephdtadeeplearningforpredictingdrugtargetinteractionsacasestudyofcovid19drugrepurposing AT riponkchakrabortty deephdtadeeplearningforpredictingdrugtargetinteractionsacasestudyofcovid19drugrepurposing AT michaelryan deephdtadeeplearningforpredictingdrugtargetinteractionsacasestudyofcovid19drugrepurposing |