Skip to main content
Fig. 5 | Genome Biology

Fig. 5

From: MUFFINN: cancer gene discovery via network analysis of somatic mutation data

Fig. 5

MUFFINN effectively predicts cancer genes with only 10 % of TCGA samples. Comparison of MUFFINN predictions for cancer genes annotated by a CGC and b the 20/20 rule between using all cancer samples and using only 10 % of the cancer samples. AUC scores for 18 cancer types when using all samples and when using 10 % of samples are represented as box plots. Performance comparisons were also conducted based on the number of retrieved cancer genes annotated by c CGC and d the 20/20 rule in the top 100, 500, and 1000 candidates. Notice that the scores for the 10 % of samples are all based on the average of 100 random samples. In general, MUFFINN shows only a marginal decrease in performance when using 10 % of samples compared with all samples

Back to article page