RESUMO
IntroductionNumerous studies demonstrate frequent mutations in the genome of SARS-CoV-2. Our goal was to statistically link mutations to severe disease outcome. MethodsWe used an automated machine learning approach where 1,594 viral genomes with available clinical follow-up data were used as the training set (797 "severe" and 797 "mild"). The best algorithm, based on random forest classification combined with the LASSO feature selection algorithm was employed to the training set to link mutation signatures and outcome. The performance of the final model was estimated by repeated, stratified, 10-fold cross validation (CV), then adjusted for multiple testing with Bootstrap Bias Corrected CV. ResultsWe identified 26 protein and UTR mutations significantly linked to severe outcome. The best classification algorithm uses a mutation signature of 22 mutations as well as the patients age as the input and shows high classification efficiency with an AUC of 0.94 (CI: [0.912, 0.962]) and a prediction accuracy of 87% (CI: [0.830, 0.903]). Finally, we established an online platform (https://covidoutcome.com/) which is capable to use a viral sequence and the patients age as the input and provides a percentage estimation of disease severity. DiscussionWe demonstrate a statistical association between mutation signatures of SARS-CoV-2 and severe outcome of COVID-19. The established analysis platform enables a real-time analysis of new viral genomes. KEY MESSAGESO_LIA statistical link between SARS-Cov-2 mutation status and severe COVID outcome was established using automated machine learning techniques based on random forest and logistic regression combined with feature selection algorithms. C_LIO_LIA mutation signature based on 3,779 protein coding and 36 UTR mutations capable to identify severe outcome cases was established. C_LIO_LIThe trained model showed high classification performance (AUC=0.94 (CI: [0.912, 0.962]), accuracy=0.87 (CI: [0.830, 0.903])). C_LIO_LIA registration-free web-server for automated classification of new samples was set up and is accessible at http://www.covidoutcome.com. C_LIO_LIThe established pipeline provides a quick assessment of future patients warranting a prospective clinical validation. C_LI
RESUMO
IntroductionGenomic alterations in a viral genome can lead to either better or worse outcome and identifying these mutations is of utmost importance. Here, we correlated protein-level mutations in the SARS-CoV-2 virus to clinical outcome. MethodsMutations in viral sequences from the GISAID virus repository were evaluated by using "hCoV-19/Wuhan/WIV04/2019" as the reference. Patient outcomes were classified as mild disease, hospitalization and severe disease (death or documented treatment in an intensive-care unit). Chi-square test was applied to examine the association between each mutation and patient outcome. False discovery rate was computed to correct for multiple hypothesis testing and results passing a FDR cutoff of 5% were accepted as significant. ResultMutations were mapped to amino acid changes for 2,120 non-silent mutations. Mutations correlated to mild outcome were located in the ORF8, NSP6, ORF3a, NSP4, and in the nucleocapsid phosphoprotein N. Mutations associated with inferior outcome were located in the surface (S) glycoprotein, in the RNA dependent RNA polymerase, in the 3-to5 exonuclease, in ORF3a, NSP2 and N. Mutations leading to severe outcome with low prevalence were found in the surface (S) glycoprotein and in NSP7. Five out of 17 of the most significant mutations mapped onto a 10 amino acid long phosphorylated stretch of N indicating that in spite of obvious sampling restrictions the approach can find functionally relevant sites in the viral genome. ConclusionsWe demonstrate that mutations in the viral genes may have a direct correlation to clinical outcome. Our results help to quickly identify SARS-CoV-2 infections harboring mutations related to severe outcome.
