Dataset Information

Deep learning identifies antigenic determinants of severe SARS-CoV-2 infection within T-cell repertoires.

ABSTRACT: SARS-CoV-2 infection is characterized by a highly variable clinical course with patients experiencing asymptomatic infection all the way to requiring critical care support. This variation in clinical course has led physicians and scientists to study factors that may predispose certain individuals to more severe clinical presentations in hopes of either identifying these individuals early in their illness or improving their medical management. We sought to understand immunogenomic differences that may result in varied clinical outcomes through analysis of T-cell receptor sequencing (TCR-Seq) data in the open access ImmuneCODE database. We identified two cohorts within the database that had clinical outcomes data reflecting severity of illness and utilized DeepTCR, a multiple-instance deep learning repertoire classifier, to predict patients with severe SARS-CoV-2 infection from their repertoire sequencing. We demonstrate that patients with severe infection have repertoires with higher T-cell responses associated with SARS-CoV-2 epitopes and identify the epitopes that result in these responses. Our results provide evidence that the highly variable clinical course seen in SARS-CoV-2 infection is associated to certain antigen-specific responses.

SUBMITTER: Sidhom JW

PROVIDER: S-EPMC8275616 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The spike protein of coronavirus is key target for drug development and other pharmacological interventions. In current study, we performed an integrative approach to predict antigenic sites in SARS-CoV-2 spike receptor binding domain and found nine potential antigenic sites. The predicted antigenic sites were then assessed for possible molecular similarity with other known antigens in different organisms. Out of nine sites, seven sites showed molecular similarity with 54 antigenic determinants found in twelve pathogenic bacterial species (Mycobacterium tuberculosis, Mycobacterium leprae, Bacillus anthracis, Borrelia burgdorferi, Clostridium perfringens, Clostridium tetani, Helicobacter Pylori, Listeria monocytogenes, Staphylococcus aureus, Streptococcus pyogenes, Vibrio cholera and Yersinia pestis), two malarial parasites (Plasmodium falciparum and Plasmodium knowlesi) and influenza virus A. Most of the bacterial antigens that displayed molecular similarity with antigenic sites in SARS-CoV-2 RBD (receptor binding domain) were toxins and virulent factors. Antigens from Mycobacterium that showed similarity were mainly involved in modulating host cell immune response and ensuring persistence and survival of pathogen in host cells. Presence of a large number of antigenic determinants, similar to those in highly pathogenic microorganisms, not merely accounts for complex etiology of the disease but also provides an explanation for observed pathophysiological complications, such as deregulated immune response, unleashed or dysregulated cytokine secretion (cytokine storm), multiple organ failure etc., that are more evident in aged and immune-compromised patients. Over-representation of antigenic determinants from Plasmodium and Mycobacterium in all antigenic sites suggests that anti-malarial and anti-TB drugs can prove to be clinical beneficial for COVID-19 treatment. Besides this, anti-leprosy, anti-lyme, anti-plague, anti-anthrax drugs/vaccine etc. are also expected to be beneficial in COVID-19 treatment. Moreover, individuals previously immunized/vaccinated or had previous history of malaria, tuberculosis or other disease caused by fifteen microorganisms are expected to display a considerable degree of resistance against SARS-CoV-2 infection. Out of the seven antigenic sites predicted in SARS-CoV-2, a part of two antigenic sites were also predicted as potent T-cell epitopes (KVGGNYNYL444-452 and SVLYNSASF366-374) against MHC class I and three (KRISNCVADYSVLYN356-370, DLCFTNVYADSFVI389-402, and YRVVVLSFELLHA508-520) against MHC class II. All epitopes possessed significantly lower predicted IC50 value which is a prerequisite for a preferred vaccine candidate for COVID-19.

Dataset Information

Deep learning identifies antigenic determinants of severe SARS-CoV-2 infection within T-cell repertoires.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets