When the COVID-19 pandemic struck in early 2020, doctors and researchers rushed to find effective treatments, and since developing new drugs takes time, there was little of it to spare. In the short term, the most expedient option was to repurpose existing drugs.
The subject drew the interest of Caroline Uhler, a computational biologist in MIT's Department of Electrical Engineering and Computer Science and the Institute for Data, Systems and Society, and an associate member of the Broad Institute of MIT and Harvard. Her team has now developed a machine learning-based approach to identify drugs already on the market that could potentially be repurposed to fight COVID-19, particularly in the elderly.
The system accounts for changes in gene expression in lung cells caused by both the disease and aging. That combination could allow medical experts to more quickly seek drugs for clinical testing in elderly patients, who tend to experience more severe symptoms.
The researchers pinpointed the protein RIPK1 as a promising target for coronavirus drugs, and they identified three approved drugs that act on the expression of RIPK1. The findings appear in Nature Communications.
WHAT'S THE IMPACT
Early in the pandemic, it grew clear that COVID-19 harmed older patients more than younger ones, on average. Uhler's team wondered why. The prevalent hypothesis had been the aging immune system, but there's likely an additional factor: The lungs become stiffer as they age.
The stiffening lung tissue shows different patterns of gene expression than in younger people, even in response to the same signal. Essentially, that means the same treatment could "turn on" different genes on two substrates of differing stiffness. That in turn led the team to examine drugs that act on genes that sit at the intersection of COVID-19 and aging.
They looked to big data and artificial intelligence, zeroing in on the most promising drug repurposing candidates in three broad steps. First, they generated a large list of possible drugs using a machine learning technique called an autoencoder. They next mapped the network of genes and proteins involved in both aging and SARS-CoV-2 infection.
Finally, they used statistical algorithms to understand causality in that network, allowing them to pinpoint "upstream" genes that caused cascading effects throughout the network. In principle, drugs targeting those upstream genes and proteins should be promising candidates for clinical trials.
To generate an initial list of potential drugs, the team's autoencoder 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 the virus. The autoencoder scoured the datasets to highlight drugs whose impacts on gene expression appeared to counteract the effects of the coronavirus.
Next, the researchers narrowed the list of potential drugs by homing in on key genetic pathways. They mapped the interactions of proteins involved in the aging and SARS-CoV-2 infection pathways. Then they identified areas of overlap among the two maps. That effort pinpointed the precise gene expression network that a drug would need to target to combat COVID-19 in elderly patients.
Uhler plans to share the team's findings with pharmaceutical companies. She emphasizes that before any of the drugs they identified can be approved for repurposed use in elderly COVID-19 patients, clinical testing is needed to determine efficacy.
THE LARGER TREND
While efforts are still ongoing to vaccinate the public against the virus – which ultimately will be necessary to end the pandemic – various treatments for those already infected have emerged, including Carrimycin, which in January became the world's first synthetic biological drug treatment for severe COVID-19 to receive U.S. Food and Drug Administration approval for Phase III trials.
Testing has shown that Carrimycin is effective in treating patients who have been hospitalized with severe coronavirus symptoms, helping them recover within 14 days from the worst impacts of the disease.
Meanwhile, a clinical trial involving COVID-19 patients hospitalized at UT Health San Antonio and University Health, among roughly 100 sites globally, found that a combination of the drugs baricitinib and remdesivir reduced time to recovery.
As of Dec. 31, 2020, the Johns Hopkins University coronavirus tracker showed more than 27.6 million confirmed cases of the virus in the U.S., with the death toll climbing to over 485,000. Both figures lead the world.
Twitter: @JELagasse
Email the writer: jeff.lagasse@himssmedia.com
"machine" - Google News
February 16, 2021 at 04:24AM
https://ift.tt/3anD35d
A new machine learning approach may find treatment options for COVID-19 - Healthcare Finance News
"machine" - Google News
https://ift.tt/2VUJ7uS
https://ift.tt/2SvsFPt
Bagikan Berita Ini
0 Response to "A new machine learning approach may find treatment options for COVID-19 - Healthcare Finance News"
Post a Comment