Abstract
Since the 2019 novel coronavirus disease (COVID-19) outbreak in 2019 and the pandemic continues for more than one year, a vast amount of drug research has been conducted and few of them got FDA approval. Our objective is to prioritize repurposable drugs using a pipeline that systematically integrates the interaction between COVID-19 and drugs, deep graph neural networks, and in vitro/population-based validations. We first collected all available drugs (n = 3635) related to COVID-19 patient treatment through CTDbase. We built a COVID-19 knowledge graph based on the interactions among virus baits, host genes, pathways, drugs, and phenotypes. A deep graph neural network approach was used to derive the candidate drug’s representation based on the biological interactions. We prioritized the candidate drugs using clinical trial history, and then validated them with their genetic profiles, in vitro experimental efficacy, and population-based treatment effect. We highlight the top 22 drugs including Azithromycin, Atorvastatin, Aspirin, Acetaminophen, and Albuterol. We further pinpointed drug combinations that may synergistically target COVID-19. In summary, we demonstrated that the integration of extensive interactions, deep neural networks, and multiple evidence can facilitate the rapid identification of candidate drugs for COVID-19 treatment.
Highlights
Since the 2019 novel coronavirus disease (COVID-19) outbreak in 2019 and the pandemic continues for more than one year, a vast amount of drug research has been conducted and few of them got FDA approval
After fine-tuning the Drug Repurposing Knowledge Graph (DRKG) embedding to the COVID-19 knowledge graph, we achieved area under the receiver operating curve (AUROC) 0.8121 and area under the precision-recall curve (AUPRC) 0.8524, respectively (Table S1), implying that the node embedding contains the local interaction
We found that the node embedding of SARS-CoV-2 baits, host genes, drugs, and phenotypes were distributed separately (Fig. 2a, Fig. S2)
Summary
Since the 2019 novel coronavirus disease (COVID-19) outbreak in 2019 and the pandemic continues for more than one year, a vast amount of drug research has been conducted and few of them got FDA approval. Addressing the abundant needs to continue the COVID-19 drug development, many researchers have screened thousands of candidate therapeutic a gents[7,8] These agents can be divided into two broad categories: those that directly target the virus replication cycle, and those based on immunotherapy approaches either aimed to boost innate antiviral immune responses (e.g., targeting the host angiotensin-converting enzyme 2 (ACE2) that SARS-CoV-2 directly binds)[9] or to alleviate damage induced by dysregulated inflammatory r esponses[10]. Examples include a network pharmacology study in protein–protein interaction (PPI) n etwork[13], in silico protein d ocking[14], and sequencing analysis[15] Another family of studies has utilized retrospective analysis of clinical data, such as electronic health records (EHRs). This work attempts to identify repurposable drugs from SARS-CoV2-drug interactions and validating the drugs from retrospective in vitro efficacy and large-scale clinical data to prioritize repurposable drugs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
