Artificial intelligence approach fighting COVID-19 with repurposing drugs

Area of Science:

• Drug discovery and repurposing
• Artificial intelligence in medicine
• Virology

Background:

• The COVID-19 pandemic necessitates rapid identification of effective treatments.
• Repurposing existing drugs with prior patient use offers a faster therapeutic route.
• Artificial intelligence (AI) can accelerate the identification of potential drug candidates.

Purpose of the Study:

• To apply artificial intelligence to identify existing, marketed drugs with potential for treating COVID-19.
• To screen drugs for activity against coronaviruses, specifically feline infectious peritonitis (FIP) virus as a model.
• To leverage AI for rapid drug repurposing in response to the pandemic.

Main Methods:

• An AI platform was developed using databases of anti-coronavirus compounds and protease inhibitors.
• AI predictions were validated through in vitro cell-based assays against a feline coronavirus.
• Assay results were used to refine the AI model for iterative drug screening.

Main Results:

• The AI system identified 80 potential drug candidates.
• Eight drugs, including bedaquiline and celecoxib, demonstrated in vitro activity against FIP virus.
• Five additional drugs, such as chloroquine, also showed activity in AI-guided screening.

Conclusions:

• AI successfully identified existing drugs with activity against FIP coronavirus.
• Further in vitro and in vivo studies are needed to confirm activity against SARS-CoV-2.
• Repurposed drugs, if effective against SARS-CoV-2, could be rapidly deployed to combat COVID-19.