Fig. 5
From: N-of-one differential gene expression without control samples using a deep generative model
Differential expression and enrichment analysis for cancer driver genes across TCGA. A single sample was randomly selected from each TCGA-tumor type to calculate the differentially expressed genes with our model. This process was repeated 20 times. The left panel shows boxplots of the enrichment scores for every TCGA-tumor. Dots indicate the experiment replicates. The middle plot shows the number of cancer driver genes present in CancerDBv3 for each cancer. The right panel shows a violin plot of the number of differentially expressed genes in every replicate of our experiments