A Machine Learning Approach for Identifying HLA Variants Associated with Symptomatic and Asymptomatic COVID-19

COVID-19 disease severity and symptoms can vary considerably among infected patients. Even though most studies investigating COVID-19 have focused on patients with a severe form of the disease, investigations of asymptomatic infection have provided new insights into patient-specific immunological features that protect patients from COVID-19 symptoms. Recent studies have shown an association between common human leukocyte antigen (HLA) alleles such and asymptomatic COVID-19 infections. Here we utilize machine learning in conjunction with explainable AI (XAI) to identify alleles in five HLA loci that can be either “protective” or “atrisk” for symptomatic COVID-19. Data from the public online HLA-COVID database (composed of 3238 samples) was used for training and validation of multiple ML classification models to identify the top performing model. The model was then further processed with XAI via SHAP (SHapley Additive exPlanations) to identify the “protective” and “at-risk” HLA alleles. We determined that HLA-B *07:02, *40:01, and *15:01 are associated with asymptomatic disease, i.e., are protective and HLA-B* 44:01, 39:06, and 51:01 are associated with symptomatic disease i.e., place the individual at greater risk. This study provides a proof-of-concept study for utilizing machine learning to provide valuable insights for Covid-19 patients. These findings can be translated into algorithms that can help physicians personalize COVID-19 treatment and achieve better clinical outcomes.