Long non-coding RNAs in biomarking COVID-19: a machine learning-based approach

Abstract

Abstract Background The coronavirus pandemic that started in 2019 has caused the highest mortality and morbidity rates worldwide. Data on the role of long non-coding RNAs (lncRNAs) in coronavirus disease 2019 (COVID-19) is scarce. We aimed to elucidate the relationship of three important lncRNAs in the inflammatory states, H19, taurine upregulated gene 1 (TUG1), and colorectal neoplasia differentially expressed (CRNDE) with key factors in inflammation and fibrosis induction including signal transducer and activator of transcription3 (STAT3), alpha smooth muscle actin (α-SMA), tumor necrosis factor-alpha (TNF-α), and interleukin-6 (IL-6) in COVID-19 patients with moderate to severe symptoms. Methods Peripheral blood mononuclear cells from 28 COVID-19 patients and 17 healthy controls were collected. The real-time quantitative polymerase chain reaction (RT-qPCR) was performed to evaluate the expression of RNAs and lncRNAs. Western blotting analysis was also performed to determine the expression levels of STAT3 and α-SMA proteins. Machine learning and receiver operating characteristic (ROC) curve analysis were carried out to evaluate the distinguishing ability of lncRNAs. Results The expression levels of H19, TUG1, and CRNDE were significantly overexpressed in COVID-19 patients compared to healthy controls. Moreover, STAT3 and α-SMA expression levels were remarkedly increased at both transcript and protein levels in patients with COVID-19 compared to healthy subjects and were correlated with Three lncRNAs. Likewise, IL-6 and TNF-α were considerably upregulated in COVID-19 patients. Machine learning and ROC curve analysis showed that CRNDE-H19 panel has the proper ability to distinguish COVID-19 patients from healthy individuals (area under the curve (AUC) = 0.86). Conclusion The overexpression of three lncRNAs in COVID-19 patients observed in this study may align with significant manifestations of COVID-19. Furthermore, their co-expression with STAT3 and α-SMA, two critical factors implicated in inflammation and fibrosis induction, underscores their potential involvement in exacerbating cardiovascular, pulmonary and common symptoms and complications associated with COVID-19. The combination of CRNDE and H19 lncRNAs seems to be an impressive host-based biomarker panel for screening and diagnosis of COVID-19 patients from healthy controls. Research into lncRNAs can provide a robust platform to find new viral infection-related mediators and propose novel therapeutic strategies for viral infections and immune disorders.

Keywords

• COVID-19
• Long non-coding RNA
• Peripheral blood mononuclear cell
• Diagnosis
• Machine learning