Identifying MicroRNA Markers That Predict COVID-19 Severity Using Machine Learning Methods

Identification of gene and protein signatures associated with long-term effects of COVID-19 on the immune system after patient recovery by analyzing single-cell multi-omics data using a machine learning approach

Viral infections significantly impact the immune system, and impact will persist until recovery. However, the influence of severe acute respiratory syndrome coronavirus 2 infection on the homeostatic immune status and secondary immune response in recovered patients remains unclear. To investigate these persistent alterations, we employed five feature-ranking algorithms (LASSO, MCFS, RF, CATBoost, and XGBoost), incremental feature selection, synthetic minority oversampling technique and two classification algorithms (decision tree and k-nearest neighbors) to analyze multi-omics data (surface proteins and transcriptome) from coronavirus disease 2019 (COVID-19) recovered patients and healthy controls post-influenza vaccination. The single-cell multi-omics dataset was divided into five subsets corresponding to five immune cell subtypes: B cells, CD4+ T cells, CD8+ T cells, Monocytes, and Natural Killer cells. Each cell was represented by 28,402 scRNA-seq (RNA) features, 3 Hash Tag Oligo (HTO) features, 138 Cellular indexing of transcriptomes and epitopes by sequencing (CITE) features and 23,569 Single Cell Transform (SCT) features. Some multi-omics markers were identified and effective classifiers were constructed. Our findings indicate a distinct immune status in COVID-19 recovered patients, characterized by low expression of ribosomal protein (RPS26) and high expression of immune cell surface proteins (CD33, CD48). Notably, TMEM176B, a membrane protein, was highly expressed in monocytes of COVID-19 convalescent patients. These observations aid in discerning molecular differences among immune cell subtypes and contribute to understanding the prolonged effects of COVID-19 on the immune system, which is valuable for treating infectious diseases like COVID-19.

Alteration of circulating ACE2-network related microRNAs in patients with COVID-19

Angiotensin converting enzyme 2 (ACE2) serves as the primary receptor for the SARS-CoV-2 virus and has implications for the functioning of the cardiovascular system. Based on our previously published bioinformatic analysis, in this study we aimed to analyze the diagnostic and predictive utility of miRNAs (miR-10b-5p, miR-124-3p, miR-200b-3p, miR-26b-5p, miR-302c-5p) identified as top regulators of ACE2 network with potential to affect cardiomyocytes and cardiovascular system in patients with COVID-19. The expression of miRNAs was determined through qRT-PCR in a cohort of 79 hospitalized COVID-19 patients as well as 32 healthy volunteers. Blood samples and clinical data of COVID-19 patients were collected at admission, 7-days and 21-days after admission. We also performed SHAP analysis of clinical data and miRNAs target predictions and advanced enrichment analyses. Low expression of miR-200b-3p at the seventh day of admission is indicative of predictive value in determining the length of hospital stay and/or the likelihood of mortality, as shown in ROC curve analysis with an AUC of 0.730 and a p-value of 0.002. MiR-26b-5p expression levels in COVID-19 patients were lower at the baseline, 7 and 21-days of admission compared to the healthy controls (P < 0.0001). Similarly, miR-10b-5p expression levels were lower at the baseline and 21-days post admission (P = 0.001). The opposite situation was observed in miR-124-3p and miR-302c-5p. Enrichment analysis showed influence of analyzed miRNAs on IL-2 signaling pathway and multiple cardiovascular diseases through COVID-19-related targets. Moreover, the COVID-19-related genes regulated by miR-200b-3p were linked to T cell protein tyrosine phosphatase and the HIF-1 transcriptional activity in hypoxia. Analysis focused on COVID-19 associated genes showed that all analyzed miRNAs are strongly affecting disease pathways related to CVDs which could be explained by their strong interaction with the ACE2 network.

SARS-CoV-2 remodels the landscape of small non-coding RNAs with infection time and symptom severity

The COVID-19 pandemic caused by the coronavirus SARS-CoV-2 has significantly impacted global health, stressing the necessity of basic understanding of the host response to this viral infection. In this study, we investigated how SARS-CoV-2 remodels the landscape of small non-coding RNAs (sncRNA) from a large collection of nasopharyngeal swab samples taken at various time points from patients with distinct symptom severity. High-throughput RNA sequencing analysis revealed a global alteration of the sncRNA landscape, with abundance peaks related to species of 21-23 and 32-33 nucleotides. Host-derived sncRNAs, including microRNAs (miRNAs), transfer RNA-derived small RNAs (tsRNAs), and small nucleolar RNA-derived small RNAs (sdRNAs) exhibited significant differential expression in infected patients compared to controls. Importantly, miRNA expression was predominantly down-regulated in response to SARS-CoV-2 infection, especially in patients with severe symptoms. Furthermore, we identified specific tsRNAs derived from Glu- and Gly-tRNAs as major altered elements upon infection, with 5' tRNA halves being the most abundant species and suggesting their potential as biomarkers for viral presence and disease severity prediction. Additionally, down-regulation of C/D-box sdRNAs and altered expression of tinyRNAs (tyRNAs) were observed in infected patients. These findings provide valuable insights into the host sncRNA response to SARS-CoV-2 infection and may contribute to the development of further diagnostic and therapeutic strategies in the clinic.

Systems biology approaches to identify driver genes and drug combinations for treating COVID-19

Corona virus 19 (Covid-19) has caused many problems in public health, economic, and even cultural and social fields since the beginning of the epidemic. However, in order to provide therapeutic solutions, many researches have been conducted and various omics data have been published. But there is still no early diagnosis method and comprehensive treatment solution. In this manuscript, by collecting important genes related to COVID-19 and using centrality and controllability analysis in PPI networks and signaling pathways related to the disease; hub and driver genes have been identified in the formation and progression of the disease. Next, by analyzing the expression data, the obtained genes have been evaluated. The results show that in addition to the significant difference in the expression of most of these genes, their expression correlation pattern is also different in the two groups of COVID-19 and control. Finally, based on the drug-gene interaction, drugs affecting the identified genes are presented in the form of a bipartite graph, which can be used as the potential drug combinations.

Bioinformatics and system biology analysis revealed the crosstalk between COVID-19 and osteoarthritis

BACKGROUND

The global coronavirus disease 2019 (COVID-19) outbreak has significantly impacted public health. Moreover, there has been an association between the incidence and severity of osteoarthritis (OA) and the onset of COVID-19. However, the optimal diagnosis and treatment strategies for patients with both diseases remain uncertain. Bioinformatics is a novel approach that may help find the common pathology between COVID-19 and OA.

METHODS

Differentially expressed genes (DEGs) were screened by R package "limma." Functional enrichment analyses were performed to find key biological functions. Protein-protein interaction (PPI) network was constructed by STRING database and then Cytoscape was used to select hub genes. External data sets and OA mouse model validated and identified the hub genes in both mRNA and protein levels. Related transcriptional factors (TF) and microRNAs (miRNAs) were predicted with miRTarBase and JASPR database. Candidate drugs were obtained from Drug Signatures database. The immune infiltration levels of COVID-19 and OA were evaluated by CIBERSORT and scRNA-seq.

RESULTS

A total of 74 common DEGs were identified between COVID-19 and OA. Receiver operating characteristic curves validated the effective diagnostic values (area under curve > 0.7) of four hub genes (matrix metalloproteinases 9, ATF3, CCL4, and RELA) in both the training and validation data sets of COVID-19 and OA. Quantitative polymerase chain reaction and Western Blot showed significantly higher hub gene expression in OA mice than in healthy controls. A total of 84 miRNAs and 28 TFs were identified to regulate the process of hub gene expression. The top 10 potential drugs were screened including "Simvastatin," "Hydrocortisone," and "Troglitazone" which have been proven by Food and Drug Administration. Correlated with hub gene expression, Macrophage M0 was highly expressed while Natural killer cells and Mast cells were low in both COVID-19 and OA.

CONCLUSION

Four hub genes, disease-related miRNAs, TFs, drugs, and immune infiltration help to understand the pathogenesis and perform further studies, providing a potential therapy target for COVID-19 and OA.

MicroRNAs as powerful tool against COVID-19: Computational perspective

Severe acute respiratory syndrome coronavirus 2 is the virus that is responsible for the current pandemic, COVID-19 (SARS-CoV-2). MiRNAs, a component of RNAi technology, belong to the family of short, noncoding ssRNAs, and may be crucial in the battle against this global threat since they are involved in regulating complex biochemical pathways and may prevent viral proliferation, translation, and host expression. The complicated metabolic pathways are modulated by the activity of many proteins, mRNAs, and miRNAs working together in miRNA-mediated genetic control. The amount of omics data has increased dramatically in recent years. This massive, linked, yet complex metabolic regulatory network data offers a wealth of opportunity for iterative analysis; hence, extensive, in-depth, but time-efficient screening is necessary to acquire fresh discoveries; this is readily performed with the use of bioinformatics. We have reviewed the literature on microRNAs, bioinformatics, and COVID-19 infection to summarize (1) the function of miRNAs in combating COVID-19, and (2) the use of computational methods in combating COVID-19 in certain noteworthy studies, and (3) computational tools used by these studies against COVID-19 in several purposes. This article is categorized under: Infectious Diseases > Computational Models.

Changes and Clinical Value of Serum miR-24 and miR-223 Levels in Patients with Severe Pneumonia

Introduction

Severe pneumonia progresses rapidly, so early assessment of the severity and prognosis is crucial for reducing mortality rates.

Objective

We explore the role of serum microRNA-24 (miR-24) and microRNA-223 (miR-223) in the prognosis of severe pneumonia.

Methods

There were a total of 96 patients with general pneumonia, 94 patients with severe pneumonia, and 93 healthy people, who were enrolled in this study. The levels of serum miR-24 and miR-223 were detected by real-time fluorescent quantitative PCR in all groups.

Results

The serum miR-223 level in the severe group was higher than that in the common group and the control group, and the miR-24 level was lower than that in the common group and the control group (P<0.05). The serum miR-223 levels and APACHEII scores in the death group were higher than those in the survival group on the first, third, and seventh day after admission, while the miR-24 levels were lower than those in the survival group (P<0.05). The proportion of patients with mechanical ventilation in the death group was higher than that in the survival group (P<0.05). The level of serum miR-24 was negatively correlated with APACHEII score and mechanical ventilation in patients who died of severe pneumonia (P<0.05), and miR-223 was positively correlated with APACHEII score and mechanical ventilation (P<0.05). The AUC predicted by serum miR-24, miR-223, and APACHEII scores alone and jointly were 0.867, 0.839, 0.791, and 0.952, respectively. MiR-24 and miR-223 are protective and independent risk factors for mortality in severe pneumonia patients, respectively (P<0.05). MiR-24 was a protective factor affecting the death of patients with severe pneumonia, and miR-223 was an independent risk factor affecting the death of patients with severe pneumonia (P<0.05).

Conclusion

The combination of serum miR-24 and miR-223 levels on the first day after admission and APACHEII score can effectively predict prognosis.

Using Machine Learning Methods to Study Colorectal Cancer Tumor Micro-Environment and Its Biomarkers

Colorectal cancer (CRC) is a leading cause of cancer deaths worldwide, and the identification of biomarkers can improve early detection and personalized treatment. In this study, RNA-seq data and gene chip data from TCGA and GEO were used to explore potential biomarkers for CRC. The SMOTE method was used to address class imbalance, and four feature selection algorithms (MCFS, Borota, mRMR, and LightGBM) were used to select genes from the gene expression matrix. Four machine learning algorithms (SVM, XGBoost, RF, and kNN) were then employed to obtain the optimal number of genes for model construction. Through interpretable machine learning (IML), co-predictive networks were generated to identify rules and uncover underlying relationships among the selected genes. Survival analysis revealed that INHBA, FNBP1, PDE9A, HIST1H2BG, and CADM3 were significantly correlated with prognosis in CRC patients. In addition, the CIBERSORT algorithm was used to investigate the proportion of immune cells in CRC tissues, and gene mutation rates for the five selected biomarkers were explored. The biomarkers identified in this study have significant implications for the development of personalized therapies and could ultimately lead to improved clinical outcomes for CRC patients.

Investigation of shared genes and regulatory mechanisms associated with coronavirus disease 2019 and ischemic stroke

Objective

Clinical associations between coronavirus disease (COVID-19) and ischemic stroke (IS) have been reported. This study aimed to investigate the shared genes between COVID-19 and IS and explore their regulatory mechanisms.

Methods

Published datasets for COVID-19 and IS were downloaded. Common differentially expressed genes (DEGs) in the two diseases were identified, followed by protein–protein interaction (PPI) network analysis. Moreover, overlapping module genes associated with the two diseases were investigated using weighted correlation network analysis (WGCNA). Through intersection analysis of PPI cluster genes and overlapping module genes, hub-shared genes associated with the two diseases were obtained, followed by functional enrichment analysis and external dataset validation. Moreover, the upstream miRNAs and transcription factors (TFs) of the hub-shared genes were predicted.

Results

A total of 91 common DEGs were identified from the clusters of the PPI network, and 129 overlapping module genes were screened using WGCNA. Based on further intersection analysis, four hub-shared genes in IS and COVID-19 were identified, including PDE5A, ITGB3, CEACAM8, and BPI. These hub-shared genes were remarkably enriched in pathways such as ECM-receptor interaction and focal adhesion pathways. Moreover, ITGB3, PDE5A, and CEACAM8 were targeted by 53, 32, and 3 miRNAs, respectively, and these miRNAs were also enriched in the aforementioned pathways. Furthermore, TFs, such as lactoferrin, demonstrated a stronger predicted correlation with the hub-shared genes.

Conclusion

The four identified hub-shared genes may participate in crucial mechanisms underlying both COVID-19 and IS and may exhibit the potential to be biomarkers or therapeutic targets for the two diseases.