AI predicts how patients with viral infections, including COVID-19, will be destined-ScienceDaily

A survey published on June 11, 2021 revealed two clear signatures. eBiomedicine.. One is a set of 166 genes that reveal how the human immune system responds to viral infections. The second set of 20 signature genes predicts the severity of a patient’s illness. For example, the need to be hospitalized or use a ventilator. The usefulness of the algorithm was validated using lung tissue collected at necropsy from animal models of COVID-19 mortality and infection.

“These viral pandemic-related features tell us how the human immune system responds to viral infections and how severe they become, which provides a map of current and future pandemics. “, Says Ph.D., Ph.D., Ph.D., Ph.D., Ph.D., Ph.D. Medicine at the University of California, San Diego School of Medicine and the Moors Cancer Center.

Gauche collaborated with Dr. Devasis Sahu, an assistant professor of pediatrics at the University of California, San Diego School of Medicine, an assistant professor of computer science and engineering at the Jacobs Institute of Technology, and Dr. Sumita Das, an associate professor of pathology at the University of California, San Diego. Led. Of medicine.

During a viral infection, the immune system releases small proteins called cytokines into the blood. These proteins guide immune cells to the site of infection and help clear the infection. However, sometimes the body releases too many cytokines, creating a runaway immune system that attacks its own healthy tissues. Known as a cytokine storm, this accident is believed to be one of the reasons why some virus-infected patients, including those with the common flu, succumb to the infection while others do not.

However, the nature, extent, causes, and best treatment for the deadly cytokine storms at greatest risk have long been unclear.

“When the COVID-19 pandemic began, I wanted to use my computer science background to find something common to all virus pandemics. As a guide when trying to understand new viruses. There are some universal truths available, “said Sahu. “This coronavirus may be new to us, but there are numerous ways our bodies can react to infections.”

The data used to test and train the algorithm was taken from public sources of patient gene expression data. All RNA was transcribed from the patient’s genes and detected in tissues or blood samples. Each time a new dataset from a patient with COVID-19 became available, the team tested it on the model. They saw the same signature gene expression pattern every time.

“In other words, this is what we call a prospective study, where participants are enrolled in the study when they develop the disease and use the genetic signatures we find to find a whole new disease unknown. We navigated the area of, “said Sahoo.

The study also revealed the sources of cytokine storms by examining the sources and functions of these genes in the first signature gene set. The cells that line the pulmonary airways and the white blood cells known as macrophages and T cells. In addition, the results revealed the results of a storm: damage to those same lung airway cells and natural killer cells, special immune cells that kill virus-infected cells.

“We see in the world that lung alveolar cells, which are usually designed to allow gas exchange and oxygenation of blood, are one of the major causes of cytokine storms and therefore function as the eye of cytokines. I was able to show it. Storm. ” “Next, our Humanoid Center team is modeling the human lung in the context of COVID-19 infection to investigate both acute and post-COVID-19 effects.”

Researchers believe that this information may also help guide therapeutic approaches for patients experiencing cytokine storms by providing cell targets and benchmarks to measure improvement.

To test their theory, the team teamed rodents with a precursor version of molnupiravir, a drug currently being tested in clinical trials for the treatment of COVID-19 patients, or SARS-CoV-2 neutralizing antibodies. Preprocessed with either. After exposure to SARS-CoV-2, control-treated rodent lung cells showed signs of expression of the pandemic-related 166 and 20 genes. Treated rodents did not, suggesting that treatment was effective in blunting cytokine storms.

“It doesn’t matter, but it doesn’t matter when the next pandemic occurs,” said Gauche, director of the Institute for Network Medicine and secretary-general of the Center for Humanoid Research at the University of California, San Diego School of Medicine. It was. “We are building tools that are relevant not only for today’s pandemics, but for the next pandemic around the corner.”

Co-authors of this study include Gajanan D. Katkar, Soni Khandelwal, Mahdi Behroozikhah, Amanraj Claire, Vanessa Castillo, Courtney Tindle, MacKenzie Fuller, Sahar Taheri, Stephen A. Rawlings, Victor Pretorius, David M. Smith, Jason Duran, University of California, San Diego; Thomas F. Rogers, Scripps Research, University of California, San Diego. Nathan Beutler, Dennis R. Burton, Scripps Research; Sydney I. Ramirez, La Hora Immunology Institute; Laura E. Crotti Alexander, VA San Diego Healthcare System and UC San Diego; Shane Crotti, Jennifer M. Dan, La Hora Institute of Immunology, University of California, San Diego.