DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

Abstract

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.

Deep drug-target binding affinity prediction with multiple attention blocks

“…We just hope that the experiment will reflect the way to use our model in practical applications. Moreover, like studies [ 1 , 3 ], we hope our work can provide scientists with some ideas for new drugs.…”

“…Based on studies [ 1 , 3 ], we extract the genome sequences, 3C-like proteinase, RNA-dependent RNA polymerase, helicase, 3’-to-5’ exonuclease, endoRNAse and 2’-O-ribose methyltransferase of SARS-CoV-2 from the National Center for Biotechnology Information database; 3137 FDA-approved drugs are included in this section. Table 6 lists parts of the FDA-approval antiviral drugs with top binding affinity values predicted by our MATT_DTI with weights trained by KIBA dataset and existing approaches [ 1 ].…”

“…Based on studies [ 1 , 3 ], we extract the genome sequences, 3C-like proteinase, RNA-dependent RNA polymerase, helicase, 3’-to-5’ exonuclease, endoRNAse and 2’-O-ribose methyltransferase of SARS-CoV-2 from the National Center for Biotechnology Information database; 3137 FDA-approved drugs are included in this section. Table 6 lists parts of the FDA-approval antiviral drugs with top binding affinity values predicted by our MATT_DTI with weights trained by KIBA dataset and existing approaches [ 1 ]. The full lists of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$6$\end{document} genome sequences could be found at supplementary data, see Supplementary Data available online at http://bib.oxfordjournals.org/.…”

De novo design of novel protease inhibitor candidates in the treatment of SARS-CoV-2 using deep learning, docking, and molecular dynamic simulations

“…As a result, the current study focused on the de novo design of novel antiviral agents for SARS-CoV-2. Deep learning methods such as ConvLSTM and CNN were used to predict binding affinities, and Drug-Target Interaction (DTI) values between existing compounds and the SARS-CoV-2 Mpro protein [ 41 , 42 ]. The KIBA dataset, which contains 52,498 chemical entities, was used as a repository for these studies.…”

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

“…https://github.com/GIST-CSBL/DeepConv-DTI Deep learning Prediction model for detecting local residue patterns of target proteins successfully enriches the protein features of a raw protein sequence, yielding better prediction results than previous approaches [ 392 ] DeepH-DTA Predicting Drug-Target Interactions. https://github.com/Hawash-AI/deepH-DTA Deep learning 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 [ 393 ] Neg Stacking Drug-target interaction prediction. https://github.com/Open-ss/NegStacking Ensemble learning and logistic regression NegStacking can improve the performance of predictive DTIs, and it has broad application prospects for improving the drug discovery process [ 394 ] SPIDR Small-molecule peptide-influenced drug repurposing Genetic algorithm and heuristic search procedure SPIDR has been generalized and integrated into DockoMatic v 2.1 [ 395 ] DeepPurpose Library for drug-target interaction prediction.…”