Machine Learning Model Uncovers Genetic Predisposition to Severe COVID-19
By HospiMedica International staff writers Posted on 24 Feb 2021 |
Image: The risk score suggested by the researchers (vertical axis) is considerably higher in the group of patients suffering severe COVID-19 (sample of patients from Moscow) (Photo courtesy of HSE University)
Researchers at HSE University (Moscow, Russia) have become the first in the world to discover genetic predisposition to severe COVID-19 using a machine learning model.
T-cell immunity is one of the key mechanisms used by the human body to fight virus infections. The staging ground for cell immunity development is the presentation of virus peptides on the surface of infected cells. This is followed by activation of T lymphocytes, which start to kill the infected cells.
The ability to successfully present virus peptides is largely determined by genetics. In human cells, human leukocyte antigen class I (HLA-I) molecules are responsible for this presentation. The set of six such molecules is unique in every human and is inherited from an individual's parents. In simple terms, if the set of alleles detects the virus well, then the immune cells will detect and destroy the infected cells fast; if a person has a set that is bad at such detection, a more severe case of disease is more likely to be observed.
The researchers studied the interconnection between HLA-I genotype and the severity of COVID-19. Using machine learning, they built a model that provides an integral assessment of the possible power of T-cell immune response to COVID-19: if the set of HLA-I alleles allows for effective presentation of the SARS-CoV-2 virus peptides, those individuals received low risk score, while people with lower presentation capability received higher risk scores (in the range from 0 to 100). To validate the model, genotypes of over 100 patients who had suffered from COVID-19 and over 400 healthy people (the control group) were analyzed. It turned out that the modeled risk score is highly effective in predicting the severity of COVID-19.
In addition to analyzing the Moscow population, the researchers used their model on a sample of patients from Madrid, Spain. The high precision of prediction was confirmed on this independent sample as well: the risk score of patients suffering severe COVID-19 was significantly higher than in patients with moderate and mild cases of the disease.
“In addition to the discovered correlations between the genotype and COVID-19 severity, the suggested approach also helps to evaluate how a certain COVID-19 mutation can affect the development of T-cell immunity to the virus. For example, we will be able to detect groups of patients for whom infection with new strains of SARS-CoV-2 can lead to more severe forms of the disease,” said Alexander Tonevitsky, a researcher from the HSE Faculty of Biology and Biotechnology.
Related Links:
HSE University
T-cell immunity is one of the key mechanisms used by the human body to fight virus infections. The staging ground for cell immunity development is the presentation of virus peptides on the surface of infected cells. This is followed by activation of T lymphocytes, which start to kill the infected cells.
The ability to successfully present virus peptides is largely determined by genetics. In human cells, human leukocyte antigen class I (HLA-I) molecules are responsible for this presentation. The set of six such molecules is unique in every human and is inherited from an individual's parents. In simple terms, if the set of alleles detects the virus well, then the immune cells will detect and destroy the infected cells fast; if a person has a set that is bad at such detection, a more severe case of disease is more likely to be observed.
The researchers studied the interconnection between HLA-I genotype and the severity of COVID-19. Using machine learning, they built a model that provides an integral assessment of the possible power of T-cell immune response to COVID-19: if the set of HLA-I alleles allows for effective presentation of the SARS-CoV-2 virus peptides, those individuals received low risk score, while people with lower presentation capability received higher risk scores (in the range from 0 to 100). To validate the model, genotypes of over 100 patients who had suffered from COVID-19 and over 400 healthy people (the control group) were analyzed. It turned out that the modeled risk score is highly effective in predicting the severity of COVID-19.
In addition to analyzing the Moscow population, the researchers used their model on a sample of patients from Madrid, Spain. The high precision of prediction was confirmed on this independent sample as well: the risk score of patients suffering severe COVID-19 was significantly higher than in patients with moderate and mild cases of the disease.
“In addition to the discovered correlations between the genotype and COVID-19 severity, the suggested approach also helps to evaluate how a certain COVID-19 mutation can affect the development of T-cell immunity to the virus. For example, we will be able to detect groups of patients for whom infection with new strains of SARS-CoV-2 can lead to more severe forms of the disease,” said Alexander Tonevitsky, a researcher from the HSE Faculty of Biology and Biotechnology.
Related Links:
HSE University
Latest COVID-19 News
- Low-Cost System Detects SARS-CoV-2 Virus in Hospital Air Using High-Tech Bubbles
- World's First Inhalable COVID-19 Vaccine Approved in China
- COVID-19 Vaccine Patch Fights SARS-CoV-2 Variants Better than Needles
- Blood Viscosity Testing Can Predict Risk of Death in Hospitalized COVID-19 Patients
- ‘Covid Computer’ Uses AI to Detect COVID-19 from Chest CT Scans
- MRI Lung-Imaging Technique Shows Cause of Long-COVID Symptoms
- Chest CT Scans of COVID-19 Patients Could Help Distinguish Between SARS-CoV-2 Variants
- Specialized MRI Detects Lung Abnormalities in Non-Hospitalized Long COVID Patients
- AI Algorithm Identifies Hospitalized Patients at Highest Risk of Dying From COVID-19
- Sweat Sensor Detects Key Biomarkers That Provide Early Warning of COVID-19 and Flu
- Study Assesses Impact of COVID-19 on Ventilation/Perfusion Scintigraphy
- CT Imaging Study Finds Vaccination Reduces Risk of COVID-19 Associated Pulmonary Embolism
- Third Day in Hospital a ‘Tipping Point’ in Severity of COVID-19 Pneumonia
- Longer Interval Between COVID-19 Vaccines Generates Up to Nine Times as Many Antibodies
- AI Model for Monitoring COVID-19 Predicts Mortality Within First 30 Days of Admission
- AI Predicts COVID Prognosis at Near-Expert Level Based Off CT Scans