Combined Deep Learning and Molecular Docking Simulations Approach Identifies Potentially Effective FDA Approved Drugs for Repurposing Against SARS-CoV-2

Muhammad U Anwar, Farjad Adnan, Asma Abro, Rayyan A Khan, Asad U Rehman, Muhammad Osama, Saad Javed, Ahmadullah Baig , Muhammad R Shabbir, Muhammad Z Assir

10.26434/chemrxiv.12227363.v1

Research curated

Abstract

The ongoing pandemic of Coronavirus Disease 2019 (COVID-19), the disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has posed a serious threat to global public health. Currently no approved drug or vaccine exists against SARS-CoV-2. Drug repurposing, represented as an effective drug discovery strategy from existing drugs, is a time efficient approach to find effective drugs against SARS-CoV-2 in this emergency situation. Both experimental and computational approaches are being employed in drug repurposing with computational approaches becoming increasingly popular and efficient. In this study, we present a robust experimental design combining deep learning with molecular docking experiments to identify most promising candidates from the list of FDA approved drugs that can be repurposed to treat COVID-19. We have employed a deep learning based Drug Target Interaction (DTI) model, called DeepDTA, with few improvements to predict drug-protein binding affinities, represented as KIBA scores, for 2,440 FDA approved and 8,168 investigational drugs against 24 SARS-CoV-2 viral proteins. FDA approved drugs with the highest KIBA scores were selected for molecular docking simulations. We ran docking simulations for 168 selected drugs against 285 total predicted and/or experimentally proven active sites of all 24 SARS-CoV-2 viral proteins. We used a recently published open source AutoDock based high throughput screening platform virtualflow to reduce the time required to run around 50,000 docking simulations. A list of 49 most promising FDA approved drugs with best consensus KIBA scores and AutoDock vina binding affinity values against selected SARS-CoV-2 viral proteins is generated. Most importantly, anidulafungin, velpatasvir, glecaprevir, rifabutin, procaine penicillin G, tadalafil, riboflavin 5’-monophosphate, flavin adenine dinucleotide, terlipressin, desmopressin, elbasvir, oxatomide, enasidenib, edoxaban and selinexor demonstrate highest predicted inhibitory potential against key SARS-CoV-2 viral proteins.

Source: ChemRxiv

Related molecules

Name	Synonyms	Genes
Uridylate-specific endoribonuclease	NSP15, Non-structural protein 15, Nonstructural protein 15, NendoU, endoRNAse	rep, ORF1a-1b
Exoribonuclease	ExoN, Non-structural protein14, Nonstructural protein14, nsp14, 5‘-to-3‘ exonuclease	rep, ORF1a-1b
RNA dependent RNA polymerase	RDR, viral RNA polymerase, RdRp, nsp12	rep, ORF1a-1b, RdRp
3C-like protease	3CLpro, Mpro, SARS coronavirus main peptidase, 3CLpro-SARS-CoV-2	rep, ORF1a-1b
Spike glycoprotein	Spike protein, S glycoprotein, S-Protein, S1, S2, S3, Peplomer protein, E2	S, ORF2
Velpatasvir
Flavin adenine dinucleotide
Terlipressin
Desmopressin
Elbasvir
Anidulafungin

Related interactions

Target	Drug	Type	Result
Spike glycoprotein	Anidulafungin	Computational	positive
RNA dependent RNA polymerase	Anidulafungin	Computational	positive
Exoribonuclease	Anidulafungin	Computational	positive
Uridylate-specific endoribonuclease	Anidulafungin	Computational	positive
Spike glycoprotein	Velpatasvir	Computational	positive
Exoribonuclease	Velpatasvir	Computational	positive
RNA dependent RNA polymerase	Flavin adenine dinucleotide	Computational	positive
Exoribonuclease	Flavin adenine dinucleotide	Computational	positive
Spike glycoprotein	Flavin adenine dinucleotide	Computational	positive
Spike glycoprotein	Terlipressin	Computational	positive
RNA dependent RNA polymerase	Desmopressin	Computational	positive
RNA dependent RNA polymerase	Terlipressin	Computational	positive
3C-like protease	Velpatasvir	Computational	positive
Spike glycoprotein	Elbasvir	Computational	positive
Exoribonuclease	Elbasvir	Computational	positive
RNA dependent RNA polymerase	Elbasvir	Computational	positive