Artificial intelligence (AI) can now be used to make a prediction to look for the patterns for viral infections including COVID-19, MERS, and SARS to name a few. In the study, the University of California San Diego School of Medicine made use of the gene expression data which work like a switch through an "on and off" scenario.
AI Could Tell How Your Immune System Responds to Viral Infections
In a study entitled "AI-guided discovery of the invariant host response to viral pandemics" posted in eBiomedicine on Friday, June 11, two different gene sets have shown different actions.
The first one, which includes 166 genes, showed the human immune system's response in combating viral infections in the body. On the other hand, the second set which covers 20 signature genes imposed a prediction on the severity of the disease among patients. The latter tackles if the patient needs immediate hospitalization or a ventilator.
For the validation of the algorithm, the researchers have collected lung tissues from patients who died from COVID-19. In comparison, they also gathered samples from animals that suffered from viral infection.
According to cellular and molecular medicine at UC San Diego School of Medicine, Dr. Pradipta Ghosh, the mentioned signatures have helped them to know the body's response against the existing viral infections, as well as their risks and severity.
Moreover, the study also sheds some light for them to create a map that would help the future studies linked to the recent one.
How the Body Acts Upon Interacting With Viral Infection
According to the latest report from Science Daily, the human body is known to release cytokines or small proteins into the blood at the time when the viral infection emerges. The function of these proteins is to help the immune cells to fight body infection.
However, there are times that overproduction of cytokines happens, and this results in a self-attack response of the immune system to some healthy tissues. This is called the cytokine storm which gives rise to viral infections in the body. Others experience flu and manage to survive, but some could not cope up with it.
Before the study was conducted, experts had no idea about further information about cytokine storms including the best way to treat a patient suffering from it.
"When the COVID-19 pandemic began, I wanted to use my computer science background to find something that all viral pandemics have in common -- some universal truth we could use as a guide as we try to make sense of a novel virus," Sahoo, who is a pathology professor at USC San Diego School of Medicine said.
Sahoo continued that they used the participants' gene signatures in the study to identify the coverage of the disease through an examination. It was also revealed where cytokine storms originated. Moreover, the results also showed the extent of the damage that they brought to the patient's lung and killer cells.
Soumite Das, one of the study's co-author said that the HUMANOID Center team is preparing to make a human lung modeling for the COVID-19 infection which includes the effects of the disease before and after the infection.
For the trial, the researchers made use of the rodent samples. They tested Molnupiravir's precursor version, which is used for the treatment of Sars-CoV-2 patients. The team concluded that the rodents yielded 20-gene expression and 166 pandemic-linked signatures.
This article is owned by Tech Times
Written by Joseph Henry