Bioinformatics and machine learning approach identifies potential drug targets and pathways in COVID-19

Abstract

Current coronavirus disease-2019 (COVID-19) pandemic has caused massive loss of lives. Clinical trials of vaccines and drugs are currently being conducted around the world; however, till now no effective drug is available for COVID-19. Identification of key genes and perturbed pathways in COVID-19 may uncover potential drug targets and biomarkers. We aimed to identify key gene modules and hub targets involved in COVID-19. We have analyzed SARS-CoV-2 infected peripheral blood mononuclear cell (PBMC) transcriptomic data through gene coexpression analysis. We identified 1520 and 1733 differentially expressed genes (DEGs) from the GSE152418 and CRA002390 PBMC datasets, respectively (FDR < 0.05). We found four key gene modules and hub gene signature based on module membership (MMhub) statistics and protein-protein interaction (PPI) networks (PPIhub). Functional annotation by enrichment analysis of the genes of these modules demonstrated immune and inflammatory response biological processes enriched by the DEGs. The pathway analysis revealed the hub genes were enriched with the IL-17 signaling pathway, cytokine-cytokine receptor interaction pathways. Then, we demonstrated the classification performance of hub genes (PLK1, AURKB, AURKA, CDK1, CDC20, KIF11, CCNB1, KIF2C, DTL and CDC6) with accuracy >0.90 suggesting the biomarker potential of the hub genes. The regulatory network analysis showed transcription factors and microRNAs that target these hub genes. Finally, drug-gene interactions analysis suggests amsacrine, BRD-K68548958, naproxol, palbociclib and teniposide as the top-scored repurposed drugs. The identified biomarkers and pathways might be therapeutic targets to the COVID-19.

Keywords: COVID-19; differentially expressed genes; gene coexpression network; machine learning; protein–protein interaction; systems biology.

Figure 1

Flowchart of this study.

Figure 2

Construction of WGCNA coexpression modules and hub modules selection. (A) The cluster dendrogram of COVID-19 infected samples. (B) Analysis of the scale-free fit index (left) and the mean connectivity (right) for various soft-thresholding powers. (C) Heatmap plot of all genes. (D) Dendrogram of all differentially expressed genes clustered based on a dissimilarity measure (1-TOM). (E) Module eigengene dendrogram and eigengene network heatmap summarize the modules yielded in the clustering analysis. (F) The median rank of the modules; the rank value close to zero indicates a high degree of module preservation. (G) The Z summary statistics plot over each module; the blue and green dashed lines indicate the thresholds Z = 2 and Z = 10, indicate moderate and strong preservation thresholds, respectively.

Figure 3

GO and KEGG enrichment analysis for four key modules. (A) biological process, (B) molecular function, (C) cellular components and (D) KEGG enrichment analysis.

Figure 4

Receiver operating curve (ROC) plot of the five classifier performance based on (A) accuracies, (B) AUC.

Figure 5

Hub gene expression profiles. (A) Venn diagram of common hub genes identified among the hub genes of GSE152418 identified via MM scores and PPI and the DEGs of CRA002390 data. (B) Heatmap of hub genes of GSE152418 dataset. (C) Bar chart of the log expression values of 52 common hub-genes in the GSE152418 dataset.

Figure 6

Network construction. (A) PPI network of the 52 common hub genes of COVID-19 data, (B) TFs-Gene interaction network of the 52 common hub genes, (C) gene-miRNAs interaction for the common hub genes of COVID-19.