Researchers at the University of California, San Diego School of Medicine used an artificial intelligence (AI) algorithm to sift terabytes of gene expression data (which genes are “turned on” or “turned off” during infection) to look for shared patterns in patients with past pandemic viral infections, including SARS, MERS, and swine flu.
Two revealing firms emerged from the study, published on June 11, 2021 BC eBiomedicine. One, a set of 166 people, reveals how the human immune system answer a viral infections. A second set of 20 signature genes predicts the severity of a patient’s disease. For example, the need to hospitalize or use a mechanical ventilator. The usefulness of the algorithm was validated by lung tissues collected in autopsies of patients killed with COVID-19 and animal models of the infection.
“These signatures associated with a viral pandemic tell us how a person’s immune system responds to a viral infection and how severe it can be, and that provides us with a map for that and future pandemics,” Pradipta Ghosh said. , MD, professor of molecular medicine at the UC San Diego School of Medicine and Moores Cancer Center.
Ghosh co-led the study with Debashis Sahoo, Ph.D., assistant professor of pediatrics at UC San Diego School of Medicine and computer science and engineering at the Jacobs School of Engineering, and Soumita Das, Ph.D., associate professor of pathology at UC San Diego School of Medicine.
During a viral infection, the immune system releases small proteins called cytokines into the blood. These proteins guide immune cells at the site of the infection to help you eliminate the infection. Sometimes, however, the body releases too much cytokines, creating a fugitive immune system that attacks its own healthy tissue. This setback, known as the cytokine storm, is believed to be one of the reasons why some virus-infected patients, including some with common flu, succumb to the infection while others do not.
But the nature, extent and source of deadly cytokine storms, which is most at risk and how it can be best treated, have long been unclear.
“When the COVID-19 pandemic began, I wanted to use my computer training to find something that all viral pandemics had in common: some universal truth that we could use as a guide as we try to make sense of a new virus,” Sahoo . dit. “This coronavirus may be new to us, but there are only so many ways our body can respond to an infection.”
The data used to test and train the algorithm came from public sources of patient gene expression data, all RNA transcribed from patients ’genes and detected in tissue or blood samples. Each time a new data set of patients with COVID-19 was available, the team tested them on their model. They saw the same signature gene expression patterns every time.
“In other words, this was what we call a prospective study, in which participants were enrolled in the study while developing the disease and used the gene signatures we found to navigate the unknown territory of a completely new disease,” he said. dir Sahoo.
By examining the origin and function of these genes in the first set of signature genes, the study also revealed the source of cytokine storms: the cells that line the pulmonary airways and white blood cells known as macrophages and T cells. In addition, the results illuminated the consequences of the storm: damage to the cells of the lungs themselves and natural killer cells, a specialized immune cell. which kills virus-infected cells.
“We could see and show the world that the alveolar cells of our lungs that are normally designed to allow the exchange of gases and oxygenation of our blood, are one of the main sources of the cytokine storm and, for both serve as a storm cytokine eye, ”Das said. “Next, our team at the HUMANOID center is modeling human lungs in the context of COVID-19 infection in order to examine the acute and post-COVID-19 effects.”
The researchers think the information may also help target treatment approaches for patients experiencing a cytokine storm by providing cellular targets and benchmarks to measure improvement.
To test their theory, the team previously treated rodents with a precursor version of Molnupiravir, a drug currently being tested in clinical trials for the treatment of patients with COVID-19 or SARS-CoV-2 neutralizing antibodies. . After exposure to SARS-CoV-2, the lung cells of controlled-treated rodents showed pandemic-related gene expression signatures of 166 and 20 genes. The treated rodents did not, suggesting that the treatments were effective in the blunt cytokine storm.
“It’s not a question of whether, but when the next pandemic will arise,” said Ghosh, who is also director of the Institute of Network Medicine and executive director of the HUMANOID Center for Research Excellence at UC San Diego School. “We are building tools that are relevant not only to the current pandemic, but to the next one around the corner.”
Debashis Sahoo et al, AI-guided discovery of the host invariant response to viral pandemics, eBiomedicine (2021). DOI: 10.1016 / j.ebiom.2021.103390
University of California – San Diego
Citation: AI predicts what patients with viral infections will look like, including COVID-19 (2021, June 11), retrieved June 11, 2021 at https://medicalxpress.com/news/2021-06-ai- patients-viral-infections-covid -.html
This document is subject to copyright. Apart from any fair treatment for the purposes of private study or research, no part may be reproduced without written permission. Content is provided for informational purposes only.