Skip to main content
Fig. 4 | Genome Biology

Fig. 4

From: Identifying tumor cells at the single-cell level using machine learning

Fig. 4

Properties of the tumor gene signature. A Tumor gene signature co-expression analysis in tumor cells. Co-expression is measured as Pearson correlation between all pairs of genes from the gene list. B Tumor gene signature shows little overlap with known cancer-associated gene sets. The tumor gene signature was compared to the CancerSEA database. Out of the 162 genes, 134 showed no overlap with any of the gene lists. 9 genes overlapped with the cell cycle gene list. Only intersections of size 3 and more are shown. C Results of the gene co-expression analysis using SEEK. Top 150 co-expressed genes identified by SEEK were used as an input for GO enrichment analysis. D Tumor gene signature shows limited overlap with most of the gene sets from MsigDB. The most enriched gene set corresponds to the cell cycle

Back to article page