Fig. 6 | Scientific Reports

Fig. 6

From: Identification of potential biomarkers for 2022 Mpox virus infection: a transcriptomic network analysis and machine learning approach

Fig. 6

Candidate drugs and predicted biomarkers. (A) Top 10 potential therapeutic drugs for the 13 key genes expressed in 2022 MPXV infection. The y-axis represents drug names, while the horizontal bars on the x-axis represent the combined scores, with the circles indicating the -log(P-value) for each candidate. (B) Feature importance plot for the random forest model, focusing on the top 10 most important DEGs ranked by their importance coefficient. (C,D) t-SNE and PCA based on the top 10 genes’ expressions in the RNA-Seq data. Samples associated with the keratinocyte cell line show clear distinction from that associated with colon organoids as they have not shown any differential expression. (E) The ROC curve of ranked DEGs displays AUC values for each gene predicted by both LR and RF models. t-SNE: t-distributed Stochastic Neighbor Embedding; PC: Principal Component; AUC: Area Under the ROC Curve.

Back to article page