Learning From Biological and Computational Machines: Importance of SARS-CoV-2 Genomic Surveillance, Mutations and Risk Stratification

Abstract

The global coronavirus disease 2019 (COVID-19) pandemic has demonstrated the range of disease severity and pathogen genomic diversity emanating from a singular virus (severe acute respiratory syndrome coronavirus 2, SARS-CoV-2). This diversity in disease manifestations and genomic mutations has challenged healthcare management and resource allocation during the pandemic, especially for countries such as India with a bigger population base. Here, we undertake a combinatorial approach toward scrutinizing the diagnostic and genomic diversity to extract meaningful information from the chaos of COVID-19 in the Indian context. Using methods of statistical correlation, machine learning (ML), and genomic sequencing on a clinically comprehensive patient dataset with corresponding with/without respiratory support samples, we highlight specific significant diagnostic parameters and ML models for assessing the risk of developing severe COVID-19. This information is further contextualized in the backdrop of SARS-CoV-2 genomic features in the cohort for pathogen genomic evolution monitoring. Analysis of the patient demographic features and symptoms revealed that age, breathlessness, and cough were significantly associated with severe disease; at the same time, we found no severe patient reporting absence of physical symptoms. Observing the trends in biochemical/biophysical diagnostic parameters, we noted that the respiratory rate, total leukocyte count (TLC), blood urea levels, and C-reactive protein (CRP) levels were directly correlated with the probability of developing severe disease. Out of five different ML algorithms tested to predict patient severity, the multi-layer perceptron-based model performed the best, with a receiver operating characteristic (ROC) score of 0.96 and an F1 score of 0.791. The SARS-CoV-2 genomic analysis highlighted a set of mutations with global frequency flips and future inculcation into variants of concern (VOCs) and variants of interest (VOIs), which can be further monitored and annotated for functional significance. In summary, our findings highlight the importance of SARS-CoV-2 genomic surveillance and statistical analysis of clinical data to develop a risk assessment ML model.

Contrasting Epidemiology and Population Genetics of COVID-19 Infections Defined by Multilocus Genotypes in SARS-CoV-2 Genomes Sampled Globally

“…Our data suggest that the S N501Y mutation emerged earlier, possibly May-June 2020, when Australia had its second wave of transmissions [43]. We investigated the epidemiology of infections with SARS-CoV-2 variants that carried mutant alleles at eight loci, orf1ab (265, 3606, and 4715), orf3a 57, orf8 84, N (203 and 204), and S 614, considered informative for clade/variant designation [16,17] (Figure 2). When compared to younger patients (<20 years), older patients (>20 years) had a higher We investigated the epidemiology of infections with SARS-CoV-2 variants that carried mutant alleles at eight loci, orf1ab (265, 3606, and 4715), orf3a 57, orf8 84, N (203 and 204), and S 614, considered informative for clade/variant designation [16,17] (Figure 2).…”

“…We investigated the epidemiology of infections with SARS-CoV-2 variants that carried mutant alleles at eight loci, orf1ab (265, 3606, and 4715), orf3a 57, orf8 84, N (203 and 204), and S 614, considered informative for clade/variant designation [16,17] (Figure 2). When compared to younger patients (<20 years), older patients (>20 years) had a higher We investigated the epidemiology of infections with SARS-CoV-2 variants that carried mutant alleles at eight loci, orf1ab (265, 3606, and 4715), orf3a 57, orf8 84, N (203 and 204), and S 614, considered informative for clade/variant designation [16,17] (Figure 2). When compared to younger patients (<20 years), older patients (>20 years) had a higher risk of being infected with variants carrying mutant alleles at four loci, orf8 84 (North America), N 203 and 204 (Asian), and orf3a 57 (Europe) (Figure 2).…”

“…These mutant alleles have been associated with infectivity, disease severity, and immune dysregulation [ 12 , 15 , 17 , 38 ] and have been detected in VOCs including the Delta variants [ 39 , 40 ]. In particular, four VOC-defining mutant alleles, orf1ab L 4715 , S G 614 , and N KR 203&204 [ 16 ], rose sharply in prevalence from <6% in February 2020 to >90% in August 2020 ( Figure 1 ). This rise coincided with the period when COVID-19 cases, associated with the Delta variant, peaked globally [ 41 ], suggesting that these mutant alleles confer a higher transmission advantage than wild-types [ 19 ].…”

“…In the United Kingdom, the B.1.1.7 lineage (Alpha variant) with the spike mutations of E484K, D614G, and N501Y was shown to spread more rapidly among children and young people (<20 years) than in adults [ 12 ]. In addition, several non-S mutations including orf1ab P4715L, orf3a G251V, orf8 L84S, N R203K, and N G204R have been implicated in high infectivity and replication [ 13 , 14 , 15 ] and have been designated for clade classifications of VOCs including 20I (Alpha), 21A (Delta), 21B (Kappa), and 20H (Beta) [ 16 ]. The epidemiological diversity and frequency of these mutations have been shown to vary spatiotemporally among different geographical regions [ 17 ], making the loci carrying these mutations “informative” for monitoring the viral transmission dynamics and evolution in different populations [ 10 , 15 , 18 , 19 ].…”

The Need for Modernization of Biosecurity in the Post-COVID World

“…Such machine learning could supplant the need for wet bench creation of altered pathogens, as shown in promising early analyses of influenza ( 27 ). Moreover, such models have been initiated to study the current pandemic’s propensity for mutations ( 28 ). Of course, this would not entirely mitigate risk; GOF research databases could be vulnerable to hacking and their information subject to nefarious use ( 29 ).…”