Artificial intelligence tool identifies current drugs for future pandemics

By Elissa Wolfson, The Science Advisory Board assistant editor

March 6, 2023 -- Researchers have created an artificial intelligence (AI)-based algorithmic tool that calculates how to effectively repurpose current drugs to combat both COVID-19 and future pandemics.

The work, reported March 6 in Heliyon, may enable a quicker response to public health crises, the researchers said.

SARS-CoV-2 -- the virus that causes COVID-19 -- has proven to be a daunting medical and social challenge over the past three years. Although vaccines and hygienic practices have lessened its severity, COVID-19 continues to spread, causing illness and fatalities. This is due in part to the virus's ability to rapidly diversify its variants, immune response pathways, and modes of transmission. These traits make traditional approaches to vaccine and drug design less effective than they have been for previous diseases.

While the current pandemic has accelerated the need for efficient identification of potential COVID-19 drug candidates, knowledge about the host-immune response to SARS-CoV-2 infection remains limited, with few drugs approved to date.

The team investigated an approach aimed at closing the preparedness gap in the event of future pandemics -- i.e., repurposing existing drugs in advance. Identifying and selecting the best drug candidates ahead of time can potentially help defer costly and time-consuming in vitro and in vivo experiments and clinical trials, facilitating disease-specific drug development.

To accomplish this, the researchers developed a systems biology tool: the Phenotype Simulator (Phensim). Phensim simulates the tissue-specific infection of SARS-CoV-2 host cells. By leveraging available transcriptomic and proteomic databases, the tool allows modeling of SARS-CoV-2 infection in host cells, then performs a series of computer -- in silico -- experiments to determine the viral effects on the cellular host-immune response with high sensitivity and specificity, resulting in specific cellular SARS-CoV-2 signatures. It then utilizes these cell-specific signatures to identify the best candidate drugs for repurposing.

Utilizing Phensim, along with domain expertise, the researchers identified several potential COVID-19 drugs, including methylprednisolone and metformin. They further discerned key cellular SARS-CoV-2-affected pathways as potential druggable targets for COVID-19. They confirmed the validity of the tool by comparing their results with recently published in vitro studies, and concluded that Phensim and other drug repurposing strategies can potentially provide an effective approach for quickly targeting potential new interventions.

Medical immunologist and lead author Naomi Maria, PhD, is part of RxCovea, a multidisciplinary group that seeks to develop innovative strategies to address COVID-19. "There is no silver bullet to defeat the COVID-19 pandemic as it takes us over a public health roller coaster of deaths and devastation," noted Maria in a statement. "However, using this AI tool, coupled with in vitro data and other resources, we've been able to model the SARS-CoV-2 infection and identify several currently available COVID-19 drugs as potentially effective in battling the next outbreak."

Investors double down on AI drug development
Funding for artificial intelligence (AI) in drug development hit $4.1 billion in 2021, a 36% increase from the year before, according to Emersion...
AI drug development market projected to reach $5.1B by 2025
The world market for AI applications in drug development is projected to reach $5.1 billion by 2025, an increase of more than $3.6 billion from the market...
COVID-19 therapies could come from existing drugs
At least four drugs that have already been approved by the U.S. Food and Drug Administration may be effective as COVID-19 therapies, according to a study...
Machine learning improves COVID-19 drug repurposing efforts
A novel machine-learning technique leverages gene expression data to improve drug repurposing and can even predict interactions between drug candidates...
Validating drug repurposing workflows may help identify new COVID-19 treatments
A research team has strengthened COVID-19 drug repurposing workflows through independent in vitro validation followed by clinical pharmacology data assessments,...
New in vitro models reveal importance of lung stem cells in SARS-CoV-2 infection
Researchers have developed a new 2D lung organoid in vitro model as a physiologically relevant platform to aid drug development and explore the pathogenesis...
Addressing the COVID-19 challenge with computer modeling & simulation
Each day, we wake up hoping for positive news about vaccines and therapies to combat COVID-19. More than 70 candidate molecules are being evaluated for...

Copyright © 2023

Science Advisory Board on LinkedIn
Science Advisory Board on Facebook
Science Advisory Board on Twitter