Linking Genotype to Phenotype: Further Exploration of Mutations in SARS-CoV-2 Associated with Mild or Severe Outcomes

Abstract

We previously interrogated the relationship between SARS-CoV-2 genetic mutations and associated patient outcomes using publicly available data downloaded from GISAID in October 2020 [1]. Using high-level patient data included in some GISAID submissions, we were able to aggregate patient status values and differentiate between severe and mild COVID-19 outcomes. In our previous publication, we utilized a logistic regression model with an L1 penalty (Lasso regularization) and found several statistically significant associations between genetic mutations and COVID-19 severity. In this work, we explore the applicability of our October 2020 findings to a more current phase of the COVID-19 pandemic. Here we first test our previous models on newer GISAID data downloaded in October 2021 to evaluate the classification ability of each model on expanded datasets. The October 2021 dataset (n=53,787 samples) is approximately 15 times larger than our October 2020 dataset (n=3,637 samples). We show limitations in using a supervised learning approach and a need for expansion of the feature sets based on progression of the COVID-19 pandemic, such as vaccination status. We then re-train on the newer GISAID data and compare the performance of our two logistic regression models. Based on accuracy and Area Under the Curve (AUC) metrics, we find that the AUC of the re-trained October 2021 model is modestly decreased as compared to the October 2020 model. These results are consistent with the increased emergence of multiple mutations, each with a potentially smaller impact on COVID-19 patient outcomes. Bioinformatics scripts used in this study are available at https://github.com/JPEO-CBRND/opendata-variant-analysis. As described in Voss et al. 2021, machine learning scripts are available at https://github.com/Digital-Biobank/covid_variant_severity.

SARS-CoV-2 Genetic Variants and Patient Factors Associated with Hospitalization Risk

“…Some studies have used methods to analyze one variant at a time, including chi-square or Fisher exact tests that do not account for genetic correlations (2, 3), multiple logistic regression with covariates to capture genetic background like in many human GWAS (4, 14, 15), and phylogeny-based association tests (6). Other studies have used analytical approaches to investigate multiple variant loci at a time, including multiple logistic regression with multiple variants as features (5, 17), neural network approaches (7, 8), random forests (16, 17), and XGBoost (7, 8).…”

Interpretable and Predictive Deep Neural Network Modeling of the SARS-CoV-2 Spike Protein Sequence to Predict COVID-19 Disease Severity

“…However, over time even well-performing classifiers began to perform worse than they did before in updated studies, in particular after Omicron began to emerge [ 36 ]. One approach did find a mutational signature using random forests based on mild/severe disease classifications, but the mutations it found like V1176F and L5F in the Spike gene have not been validated [ 37 ].…”