Scientists have used machine learning to find drugs that are already on the market that can also fight the elderly with COVID-19.
“Making new drugs lasts forever,” said co-author Caroline Uhler, an accountant at MIT. “The only beneficial option is to reuse existing drugs.”
The study team looked for potential treatments by analyzing changes in gene expression in lung cells caused by the disease and aging.
Uhler said this combination could help medical experts find drugs to test older people:
Together with SARS-CoV-2, we need to look at aging – what are the genes at the intersection of these two pathways?
The researchers tried to answer this question through a three-step process
[Read: How Polestar is using blockchain to increase transparency]
First, they generated a list of candidate drugs using an autocoder, a type of neural network that represents unforeseen data.
The autocoder analyzed two data sets of gene expression patterns to identify drugs that appear to counteract the virus.
Subsequently, the researchers narrowed the list by the interactions of proteins associated with aging and infection pathways. They then identified areas of overlap between the two maps.
It determined the gene expression network that a drug should target to fight COVID-19 in elderly patients.
A causal framework
Finally, the team used statistical algorithms to analyze causality in the network. This enabled them to identify the specific genes that a drug should target to reduce the impact of infection.
The system highlights the RIPK1 gene as a promising target for the COVID-19 drugs. The researchers then found a list of approved drugs that act on RIPK1.
Some of these have been approved for the treatment of cancer, while others are already being tested on COVID-19 patients.
The researchers note that rigorous in vitro experiments and clinical trials are still needed to determine their effectiveness. But they also aim to extend their framework to other infections:
While applying our computing platform in the context of SARS-CoV-2, our algorithms integrate data modalities available to many diseases, making them generally applicable.
You can read the study paper in Nature communication.
Published on February 15, 2021 – 17:21 UTC