Clinical and genomic signatures of rising SARS-CoV-2 Delta breakthrough infections in New York

Feature selection for effective prediction of SARS-COV-2 using machine learning

BACKGROUND

With rise in variants of SARS-CoV-2, it is necessary to classify the emerging SARS-CoV-2 for early detection and thereby reduce human transmission. Genomic and proteomic information have less frequently been used for classifying in a machine learning (ML) approach for detection of SARS-CoV-2.

OBJECTIVE

With this aim we used nucleoprotein and viral proteomic evolutionary information of SARS-CoV-2 along with the charge and basicity distribution of amino acids from various strains of SARS-CoV-2 to generate a disease severity model based on ML.

METHODS

All sequence and clinical data were obtained from GISAID. Proteomic level calculations were added to comprise the dataset. The training set was used for feature selection. Select K- Best feature selection method was employed which was cross validated with testing set and performance evaluated. Delong's test was also done. We also employed BIRCH clustering on SARS-CoV-2 for clustering the strains.

RESULTS

Out of six ML models four were successful in training and testing. Extra Trees algorithm generated a micro-averaged F1-score of 74.2% and a weighted averaged area under the receiver operating characteristic curve (AUC-ROC) score of 73.7% with multi-class option. The feature selection set to 5, enhanced the ROC AUC from 73.7 to 76.4%. Accuracy of the selected model of 86.9% was achieved.

CONCLUSION

The unique features identified in the ML approach was able to classify disease severity into classes and had potential for predicting risk in newer variants.

Clinical and experimental evidence suggest omicron variant of SARS-CoV-2 is inherently less pathogenic than delta variant independent of previous immunity

OBJECTIVES

To study clinical disease outcomes in both human and animal models to understand the pathogenicity of omicron compared to the delta variant.

METHODS

In this cross-sectional observational study, clinical outcomes of adults who tested positive at 2 testing centres in Delhi National Capital Region between January 2022 and March 2022 (omicron-infected; N = 2998) were compared to a similar geographical cohort (delta-infected; N = 3292). In addition, disease course and outcomes were studied in SARS-CoV-2-infected golden Syrian hamsters and K-18 humanized ACE2 transgenic mice.

RESULTS

Omicron variant infection was associated with a milder clinical course [83% (95% CI 61, 94) reduced risk of severity compared against delta] adjusting for vaccination, age, sex, prior infection and occupational risk. This correlated with lower disease index and vir comparing omicron with other variants in animal models.

CONCLUSIONS

Infections caused by the omicron variant were milder compared to those caused by the delta variant independent of previous immunity.

Delta-Omicron recombinant escapes therapeutic antibody neutralization

Background

The emergence of recombinant viruses is a threat to public health. Recombination of viral variants may combine variant-specific features that together catalyze viral escape from treatment or immunity. The selective advantages of recombinant SARS-CoV-2 isolates over their parental lineages remain unknown.

Methods

Multi-method amplicon and metagenomic sequencing of a clinical swab and the in vitro grown virus allowed for high-confidence detection of a novel recombinant variant. Mutational, phylogeographic, and structural analyses determined features of the recombinant genome and spike protein. Neutralization assays using infectious as well as pseudotyped viruses and point mutants thereof defined the recombinant's sensitivity to a panel of monoclonal antibodies and sera from vaccinated and/or convalescent individuals.

Results

A novel Delta-Omicron SARS-CoV-2 recombinant was identified in an unvaccinated, immunosuppressed kidney transplant recipient treated with monoclonal antibody Sotrovimab. The recombination breakpoint is located in the spike N-terminal domain, adjacent to the Sotrovimab quaternary binding site, and results in a 5'-Delta AY.45 and a 3'-Omicron BA.1 mosaic spike protein. Delta and BA.1 are sensitive to Sotrovimab neutralization, whereas the Delta-Omicron recombinant is highly resistant to Sotrovimab, both with and without the RBD resistance mutation E340D.

Conclusions

Recombination between circulating SARS-CoV-2 variants can functionally contribute to immune escape. It is critical to validate phenotypes of mosaic viruses and monitor immunosuppressed COVID-19 patients treated with monoclonal antibodies for the selection of recombinant and immune escape variants. (Funded by NYU, the National Institutes of Health, and others).