A review of SARS-CoV-2 drug repurposing: databases and machine learning models

Abstract

The emergence of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) posed a serious worldwide threat and emphasized the urgency to find efficient solutions to combat the spread of the virus. Drug repurposing has attracted more attention than traditional approaches due to its potential for a time- and cost-effective discovery of new applications for the existing FDA-approved drugs. Given the reported success of machine learning (ML) in virtual drug screening, it is warranted as a promising approach to identify potential SARS-CoV-2 inhibitors. The implementation of ML in drug repurposing requires the presence of reliable digital databases for the extraction of the data of interest. Numerous databases archive research data from studies so that it can be used for different purposes. This article reviews two aspects: the frequently used databases in ML-based drug repurposing studies for SARS-CoV-2, and the recent ML models that have been developed for the prospective prediction of potential inhibitors against the new virus. Both types of ML models, Deep Learning models and conventional ML models, are reviewed in terms of introduction, methodology, and its recent applications in the prospective predictions of SARS-CoV-2 inhibitors. Furthermore, the features and limitations of the databases are provided to guide researchers in choosing suitable databases according to their research interests.

Recent advances in chemometric modelling of inhibitors against SARS-CoV-2

“…In addition to the 3CLpro target, PLpro is also a popular target for antiviral inhibitors; Calleja et al and Amin et al detailed the development of theoretical calculations for potential inhibitors of PLpro in their reviews [ 125 , 126 ]. Elkashlan et al described several large databases for studying potential inhibitors of SARS-CoV-2 as well as the application and development of machine learning models [ 127 ]. Our review focuses on chemometric modelling as an important point, focusing on the protein targets 3CLpro, hACE2/S protein, and PPI, we detailed a series of studies on QSAR modelling, molecular docking, molecular dynamics, and ADMET around chemical potential inhibitors of these targets.…”

“… Ref. Target Number of Inhibitors Inhibitor type Method [ 121 ] 3CLpro 2 Chemical Experimental [ 122 ] 3CLpro Massive Chemical Theoretical (Docking/MD) Experimental [ 123 ] 3CLpro/S protein/RdRp/PLpro Massive Chemical/Biological Theoretical (QSAR/Docking/MD/Machine Learning) [ 124 ] 3CLpro/S protein/N-NTD 7 Chemical (Methylxanthines) Theoretical (Docking/MD/ADMET) [ 125 ] PLpro 14 Chemical Theoretical (SAR) [ 126 ] 3CLpro/PLpro Massive Chemical Theoretical (QSAR) [ 127 ] SARS-CoV-2 Massive Chemical Theoretical (Machine Learning) This Review 3CLpro/hACE2/S protein/PPI Massive Chemical Theoretical (QSAR/Docking/MD/ADMET) …”

Assessing the Potential Contribution of In Silico Studies in Discovering Drug Candidates That Interact with Various SARS-CoV-2 Receptors

“…In silico studies have been an increasingly valuable tool for drug development in recent years, providing an efficient and cost-effective method of identifying prospective therapeutic candidates against SARS-CoV-2 [46]. They employ a variety of approaches and tools, such as molecular docking, virtual screening, molecular dynamics simulations, and quantitative structure-activity relationship (QSAR) modelling (See Figure 3) [46,47]. Those approaches enable researchers to anticipate possible drug candidates' binding affinity, pharmacokinetics, and toxicity, offering vital insights into their potential efficacy and safety [7,46].…”

“…They employ a variety of approaches and tools, such as molecular docking, virtual screening, molecular dynamics simulations, and quantitative structure-activity relationship (QSAR) modelling (See Figure 3) [46,47]. Those approaches enable researchers to anticipate possible drug candidates' binding affinity, pharmacokinetics, and toxicity, offering vital insights into their potential efficacy and safety [7,46].…”

“…They employ a variety of approaches and tools, such as molecular docking, virtual screening, molecular dynamics simulations, and quantitative structure-activity relationship (QSAR) modelling (See Figure 3) [46,47]. Those approaches enable researchers to anticipate possible drug candidates' binding affinity, pharmacokinetics, and toxicity, offering vital insights into their potential efficacy and safety [7,46]. These approaches enable us to swiftly screen a large number of compounds, optimize therapeutic candidates, and minimize the time and cost associated with traditional drug development procedures [15,47].…”