A recent study, published in Medicine Drug Discovery, has used AI-driven drug discovery screening to identify repurposing candidates among FDA-approved drugs, based on their predicted antiviral activity against SARS-CoV-2.
The novel SARS-CoV-2 virus belongs to the family of Coronaviridae and uses ACE2 receptors for entry into host cells. Complications associated with infection of SARS-CoV-2 include acute cardiac injury, acute respiratory distress syndrome, and a cytokine storm that researchers predict to be associate with the severity of infection.
SARS-CoV-2 3CL protease (3CLpro) is an integral component of viral replication and exhibits over 96% sequence identity to the SARS-CoV 3CLpro. This suggests that the implementation of drugs that are effective against SARS-CoV could be used for the treatment of SARS-CoV-2. However, the higher transmission rates of SARS-CoV-2 suggests that the new virus uses attachment-promoting factors in cells more effectively than SARS-CoV, and is more effective in immune surveillance evasion. Therefore, for effective treatment of COVID-19, new therapeutic options need to be explored.
AI Drug Discovery Screening
At present, little research has been done to investigate the uses of AI in the identification of drug candidates for the treatment of SARS-CoV2. This study specifically aimed to identify the best repurposing candidates among the Food and Drug Administration (FDA)- approved drugs, based on their predicted antiviral activity against SARS-CoV-2.
To ascertain this, they trained a supervised machine learning model based on gradient-boosted tree ensembles, operating on in vitro data encoded in chemical fingerprints, that represent specific molecular substructures. Their dataset focused on the known sequence identity of SARS-CoV-2 3CLpro. They also trained their machine learning model to predict antiviral activity by identifying compounds that inhibit SARS-CoV-2 3CLpro.
Zafirlukast is an oral leukotriene receptor antagonist (LTRA) that experts use to treat asthma. The drug specifically blocks the action of the cysteinyl leukotrienes D4 and E4 on the cysteinyl leukotriene receptors, reducing inflammation, and the production of mucus in the lungs. This study identified zafirlukast as the best repurposing candidate against SARS-CoV-2 infection, as it was found to bind with the greatest affinity to SARS-CoV-2 3CLpro, thereby inhibiting viral replication.
Complementing these findings, another study found that a different LTRA drug, known as montelukast, attenuates the hyperinflammatory cytokine profile or so-called cytokine storm through suppression of a protein complex (nuclear factor kappa-light-chain-enhancer of activated B cells), which is the same mechanism of action as zafirlukast. This also suggests that Zafirlukast could prevent two critical mechanisms of action resulting in a novel and promising pharmacotherapy in the current pandemic.
Overall, these findings demonstrate the utility of AI drug discovery screening approaches as a useful tool for identifying drug repurposing candidates for the treatment of COVID-19.
Image credit: FreePik