Identifying COVID-19 Severity-Related SARS-CoV-2 Mutation Using a Machine Learning Method

Prediction models for COVID-19 disease outcomes

SARS-CoV-2 has caused over 6.9 million deaths and continues to produce lasting health consequences. COVID-19 manifests broadly from no symptoms to death. In a retrospective cross-sectional study, we developed personalized risk assessment models that predict clinical outcomes for individuals with COVID-19 and inform targeted interventions. We sequenced viruses from SARS-CoV-2-positive nasopharyngeal swab samples between July 2020 and July 2022 from 4450 individuals in Missouri and retrieved associated disease courses, clinical history, and urban-rural classification. We integrated this data to develop machine learning-based predictive models to predict hospitalization, ICU admission, and long COVID.The mean age was 38.3 years (standard deviation = 21.4) with 55.2% (N = 2453) females and 44.8% (N = 1994) males (not reported, N = 4). Our analyses revealed a comprehensive set of predictors for each outcome, encompassing human, environment, and virus genome-wide genetic markers. Immunosuppression, cardiovascular disease, older age, cardiac, gastrointestinal, and constitutional symptoms, rural residence, and specific amino acid substitutions were associated with hospitalization. ICU admission was associated with acute respiratory distress syndrome, ventilation, bacterial co-infection, rural residence, and non-wild type SARS-CoV-2 variants. Finally, long COVID was associated with hospital admission, ventilation, and female sex.Overall, we developed risk assessment models that offer the capability to identify patients with COVID-19 necessitating enhanced monitoring or early interventions. Of importance, we demonstrate the value of including key elements of virus, host, and environmental factors to predict patient outcomes, serving as a valuable platform in the field of personalized medicine with the potential for adaptation to other infectious diseases.

Multivariate analyses and machine learning link sex and age with antibody responses to SARS-CoV-2 and vaccination

Prevention of negative COVID-19 infection outcomes is associated with the quality of antibody responses, whose variance by age and sex is poorly understood. Network approaches identified sex and age effects in antibody responses and neutralization potential of de novo infection and vaccination throughout the COVID-19 pandemic. Neutralization values followed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-specific receptor binding immunoglobulin G (RIgG), spike immunoglobulin G (SIgG) and spike and receptor immunoglobulin G (S, and RIgA) levels based on COVID-19 status. Serum immunoglobulin A (IgA) antibody titers correlated with neutralization only in females 40-60 years old (y.o.). Network analysis found males could improve IgA responses after vaccination dose 2. Complex correlation analyses found vaccination induced less antibody isotype switching and neutralization in older persons, especially in females. Sex-dependent antibody and neutralization decayed the fastest in older males. Shown sex and age characterization can direct studies integrating cell-mediated responses to define yet elusive correlates of protection and inform age and sex precision-focused vaccine design.

Identification of key gene expression associated with quality of life after recovery from COVID-19

Post-acute sequelae of COVID-19 (PASC) is a persistent complication of severe acute respiratory syndrome coronavirus 2 infection that includes symptoms, such as fatigue, cognitive impairment, and respiratory distress. These symptoms severely affect the quality of life of patients after their recovery from COVID-19. In this study, a group of machine learning algorithms analyzed the whole blood RNA-seq data from patients with different PASC levels. The purpose of this analysis was to identify the gene markers associated with PASC and the special expression patterns for different PASC levels. By comparing the quality of life of patients after the acute phase of COVID-19 and before the disease, samples in the dataset were divided into three groups, namely, "Better," "The Same," and "Worse." Each patient was represented by the expression levels of 58,929 genes. The machine learning-based workflow included six feature-ranking algorithms, incremental feature selection (IFS), and four classification algorithms. The feature ranking algorithms were in charge of assessing feature importance, whereas IFS with classification algorithms were used to extract essential genes and to construct efficient classifiers and classification rules. The expression of top genes in the results was associated with the immune response to viral infection, which is supported by the published literature. For example, patients with low CCDC18 expression and high CPED1 expression had good quality of life, whereas those with low CDC16 expression had poor quality of life.

An AI-based novel system for predicting respiratory support in COVID-19 patients through CT imaging analysis

The proposed AI-based diagnostic system aims to predict the respiratory support required for COVID-19 patients by analyzing the correlation between COVID-19 lesions and the level of respiratory support provided to the patients. Computed tomography (CT) imaging will be used to analyze the three levels of respiratory support received by the patient: Level 0 (minimum support), Level 1 (non-invasive support such as soft oxygen), and Level 2 (invasive support such as mechanical ventilation). The system will begin by segmenting the COVID-19 lesions from the CT images and creating an appearance model for each lesion using a 2D, rotation-invariant, Markov-Gibbs random field (MGRF) model. Three MGRF-based models will be created, one for each level of respiratory support. This suggests that the system will be able to differentiate between different levels of severity in COVID-19 patients. The system will decide for each patient using a neural network-based fusion system, which combines the estimates of the Gibbs energy from the three MGRF-based models. The proposed system were assessed using 307 COVID-19-infected patients, achieving an accuracy of [Formula: see text], a sensitivity of [Formula: see text], and a specificity of [Formula: see text], indicating a high level of prediction accuracy.

Epigenetic age acceleration in surviving versus deceased COVID-19 patients with acute respiratory distress syndrome following hospitalization

BACKGROUND

Aging has been reported as a major risk factor for severe symptoms and higher mortality rates in COVID-19 patients. Molecular hallmarks such as epigenetic alterations and telomere attenuation reflect the biological process of aging. Epigenetic clocks have been shown to be valuable tools for measuring biological age in various tissues and samples. As such, these epigenetic clocks can determine accelerated biological aging and time-to-mortality across various tissues. Previous reports have shown accelerated biological aging and telomere attrition acceleration following SARS-CoV-2 infection. However, the effect of accelerated epigenetic aging on outcome (death/recovery) in COVID-19 patients with acute respiratory distress syndrome (ARDS) has not been well investigated.

RESULTS

In this study, we measured DNA methylation age and telomere attrition in 87 severe COVID-19 cases with ARDS under mechanical ventilation. Furthermore, we compared dynamic changes in epigenetic aging across multiple time points until recovery or death. Epigenetic age was measured using the Horvath, Hannum, DNAm skin and blood, GrimAge, and PhenoAge clocks, whereas telomere length was calculated using the surrogate marker DNAmTL. Our analysis revealed significant accelerated epigenetic aging but no telomere attrition acceleration in severe COVID-19 cases. In addition, we observed epigenetic age deceleration at inclusion versus end of follow-up in recovered but not in deceased COVID-19 cases using certain clocks. When comparing dynamic changes in epigenetic age acceleration (EAA), we detected higher EAA using both the Horvath and PhenoAge clocks in deceased versus recovered patients. The DNAmTL measurements revealed telomere attrition acceleration in deceased COVID-19 patients between inclusion and end of follow-up and a significant change in dynamic telomere attrition acceleration when comparing patients who recovered versus those who died.

CONCLUSIONS

EAA and telomere attrition acceleration were associated with treatment outcomes in hospitalized COVID-19 patients with ARDS. A better understanding of the long-term effects of EAA in COVID-19 patients and how they might contribute to long COVID symptoms in recovered individuals is urgently needed.

XCNN-SC: Explainable CNN for SARS-CoV-2 variants classification and mutation detection

The COVID-19 pandemic spread rapidly all over the world in 2019, causing the deaths of millions of people. One of the main challenges in controlling the pandemic was the high rate of virus mutation, which evaded the immune system and reduced the vaccine's effectiveness. Due to the differences in symptoms, transmission and mortality rate, and effective prevention strategies of each variant, identifying and classifying different variants is a great necessity. In the present study, 82802 whole genomes of Alpha, Beta, Delta, Eta, Epsilon, Lota, and Omicron variants of SARS-CoV-2 were obtained from the NCBI database. The label encoding method was applied to convert the genomic sequences to numeric sequences. Then, a single-layer 1D-CNN model was used to classify seven variants of SARS-CoV-2 and achieved 99.78% accuracy, 97.98% precision, 97.66% sensitivity, 99.95% specificity, and 98.68% F1-score. The max pool layer feature maps of this network were investigated to discover the sequence discriminative regions in SARS-CoV-2 variants and their effect on biological functional differences. The feature map examination led to the detection of three mutations; one of them was a missense mutation, which has been reported previously. The rest of the detected mutations were silent mutations. In conclusion, the achieved results indicated that CNN models can extract effective features to discriminate several SARS-CoV-2 variants. Also, investigation of CNN feature maps led to an explainable CNN revealing the learned knowledge of the network from the training database. This knowledge helped us to detect mutations and their functional effects in different variants.

Sequence Analysis of Hot Spot Regions of Spike and RNA-dependent-RNA polymerase (RdRp) Genes of SARS-CoV-2 in Kerman, Iran

Background

Mutations in the SARS-CoV-2 genome might influence pathogenicity, transmission rate, and evasion of the host immune system. Therefore, the purpose of the present study was to investigate the genetic alteration as well as assess their effects on the receptor binding domain (RBD) of the spike and the putative RNA binding site of the RdRp genes of SARS-CoV-2 using bioinformatics tools.

Materials and Method

In this cross-sectional study, 45 confirmed COVID-19 patients using qRT-PCR were included and divided into mild, severe, and critical groups based on the severity of the disease. RNA was extracted from nasopharyngeal swab samples using a commercial kit. RT-PCR was performed to amplify the target sequences of the spike and RdRp genes and sequence them by the Sanger method. Clustal OMEGA, MEGA 11 software, I-mutant tools, SWISS-MODEL, and HDOCK web servers were used for bioinformatics analyses.

Results

The mean age of the patients was 50.68±2.73. The results showed that four of six mutations (L452R, T478K, N501Y, and D614G) in RBD and three of eight in the putative RNA binding site (P314L, E1084D, V1883T) were missense. In the putative RNA binding site, another deletion was discovered. Among missense mutations, N501Y and V1883T were responsible for increasing structural stability, while others were responsible for decreasing it. The various homology models designed showed that these homologies were like the Wuhan model. The molecular docking analysis revealed that the T478K mutation in RBD had the highest binding affinity. In addition, 35 RBD samples (89.7%) and 33 putative RNA binding site samples (84.6%) were similar to the Delta variant.

Conclusion

Our results indicated that double mutations (T478K and N501Y) in the S protein might increase the binding affinity of SARS-CoV-2 to human ACE2 compared to the wild-type (WT) strain. Moreover, variations in the spike and RdRp genes might influence the stability of encoded proteins.

Role of different types of RNA molecules in the severity prediction of SARS-CoV-2 patients

SARS-CoV-2 pandemic is the current threat of the world with enormous number of deceases. As most of the countries have constraints on resources, particularly for intensive care and oxygen, severity prediction with high accuracy is crucial. This prediction will help the medical society in the selection of patients with the need for these constrained resources. Literature shows that using clinical data in this study is the common trend and molecular data is rarely utilized in this prediction. As molecular data carry more disease related information, in this study, three different types of RNA molecules ( lncRNA, miRNA and mRNA) of SARS-COV-2 patients are used to predict the severity stage and treatment stage of those patients. Using seven different machine learning algorithms along with several feature selection techniques shows that in both phenotypes, feature importance selected features provides the best accuracy along with random forest classifier. Further to this, it shows that in the severity stage prediction miRNA and lncRNA give the best performance, and lncRNA data gives the best in treatment stage prediction. As most of the studies related to molecular data uses mRNA data, this is an interesting finding.

Rapid Detection of SARS-CoV-2 Variants of Concern by Genomic Surveillance Techniques

This chapter describes the application of genomic, transcriptomic, proteomic, and metabolomic methods in the study of SARS-CoV-2 variants of concern. We also describe the important role of machine learning tools to identify the most significant biomarker signatures and discuss the latest point-of-care devices that can be used to translate these findings to the physician's office or to bedside care. The main emphasis is placed on increasing our diagnostic capacity and predictability of disease outcomes to guide the most appropriate treatment strategies.

Identifying anal and cervical tumorigenesis-associated methylation signaling with machine learning methods

Cervical and anal carcinoma are neoplastic diseases with various intraepithelial neoplasia stages. The underlying mechanisms for cancer initiation and progression have not been fully revealed. DNA methylation has been shown to be aberrantly regulated during tumorigenesis in anal and cervical carcinoma, revealing the important roles of DNA methylation signaling as a biomarker to distinguish cancer stages in clinics. In this research, several machine learning methods were used to analyze the methylation profiles on anal and cervical carcinoma samples, which were divided into three classes representing various stages of tumor progression. Advanced feature selection methods, including Boruta, LASSO, LightGBM, and MCFS, were used to select methylation features that are highly correlated with cancer progression. Some methylation probes including cg01550828 and its corresponding gene RNF168 have been reported to be associated with human papilloma virus-related anal cancer. As for biomarkers for cervical carcinoma, cg27012396 and its functional gene HDAC4 were confirmed to regulate the glycolysis and survival of hypoxic tumor cells in cervical carcinoma. Furthermore, we developed effective classifiers for identifying various tumor stages and derived classification rules that reflect the quantitative impact of methylation on tumorigenesis. The current study identified methylation signals associated with the development of cervical and anal carcinoma at qualitative and quantitative levels using advanced machine learning methods.

Identification of uveitis-associated functions based on the feature selection analysis of gene ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment scores

Uveitis is a typical type of eye inflammation affecting the middle layer of eye (i.e., uvea layer) and can lead to blindness in middle-aged and young people. Therefore, a comprehensive study determining the disease susceptibility and the underlying mechanisms for uveitis initiation and progression is urgently needed for the development of effective treatments. In the present study, 108 uveitis-related genes are collected on the basis of literature mining, and 17,560 other human genes are collected from the Ensembl database, which are treated as non-uveitis genes. Uveitis- and non-uveitis-related genes are then encoded by gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment scores based on the genes and their neighbors in STRING, resulting in 20,681 GO term features and 297 KEGG pathway features. Subsequently, we identify functions and biological processes that can distinguish uveitis-related genes from other human genes by using an integrated feature selection method, which incorporate feature filtering method (Boruta) and four feature importance assessment methods (i.e., LASSO, LightGBM, MCFS, and mRMR). Some essential GO terms and KEGG pathways related to uveitis, such as GO:0001841 (neural tube formation), has04612 (antigen processing and presentation in human beings), and GO:0043379 (memory T cell differentiation), are identified. The plausibility of the association of mined functional features with uveitis is verified on the basis of the literature. Overall, several advanced machine learning methods are used in the current study to uncover specific functions of uveitis and provide a theoretical foundation for the clinical treatment of uveitis.