A research team at MIT have created a machine-learning strategy to identify existing drugs that could be repurposed to fight COVID-19 in elderly patients
In an unrelated study, the Viterbi School of Engineering at the University of Southern California created an AI framework that can significantly speed-up the analysis of COVID vaccine candidates and also find the best preventative medical therapies.
AI and machine-learning techniques are becoming crucial to the speed of drug development.
This comes at a time when more and more COVID mutations are emerging, bringing existing vaccine efficiencies into question.
This team was led by Caroline Uhler, a computational biologist in MIT’s Department of Electrical Engineering and Computer Science and the Institute for Data, Systems and Society.
“Making new drugs takes forever,” Uhler explained. “Really, the only expedient option is to repurpose existing drugs.”
Creating drug candidates for more clinical trials
Researchers at the Massachusetts Institute of Technology (MIT) have created a system that scans existing drugs to understand which ones can significantly help elderly patients of COVID-19.
The machine-learning based approach accounts for changes in gene expression caused by the disease and aging, especially in lung cells.
The drugs they identify could then go to clinical trial stage, after the researchers share this information with pharmaceutical companies.
What is their machine-learning based approach?
The researchers pinpointed the protein RIPK1 as a promising target for COVID-19 drugs, and they identified three approved drugs that act on the expression of RIPK1.
The autoencoder used by the team relied on two key datasets of gene expression patterns. One dataset showed how expression in various cell types responded to a range of drugs already on the market, and the other showed how expression responded to infection with SARS-CoV-2.
PhD student Adityanarayanan Radhakrishnan explained: “This application of autoencoders was challenging and required foundational insights into the working of these neural networks, which we developed in a paper recently published in PNAS.”
The autoencoder scoured the datasets to highlight drugs whose impacts on gene expression appeared to counteract the effects of SARS-CoV-2.
They found that aging tissue in the lungs made COVID worse
“The prevalent hypothesis is the aging immune system,” Radhakrishnan said.
Uhler and GV Shivashankar of ETH Zurich in Switzerland further explained: “One of the main changes in the lung that happens through aging is that it becomes stiffer.”
The stiffening lung tissue shows different patterns of gene expression than in younger people, even in response to the same signal.
Uhler said: “Earlier work by the Shivashankar lab showed that if you stimulate cells on a stiffer substrate with a cytokine, similar to what the virus does, they actually turn on different genes. So, that motivated this hypothesis. We need to look at aging together with SARS-CoV-2 -what are the genes at the intersection of these two pathways?”
To select approved drugs that might act on these pathways, the team turned to big data and artificial intelligence.
A single drug that has an effect on all expressed genes
“We want to identify a drug that has an effect on all of these differentially expressed genes downstream,” said PhD student Anastasiya Belyaeva.
So the team used algorithms that infer causality in interacting systems to turn their undirected network into a causal network. The final causal network identified RIPK1 as a target gene/protein for potential COVID-19 drugs, since it has numerous downstream effects.
The researchers identified a list of the approved drugs that act on RIPK1 and may have potential to treat Covid-19. Previously these drugs have been approved for the use in cancer.
Other drugs that were also identified, including ribavirin and quinapril, are already in clinical trials for COVID-19.
Radhakrishnan furhter commented: “The more data we have in this space, the better this could work.”