Figure 3
From: FunPat: function-based pattern analysis on RNA-seq time series data
Example of C-precision and C-recall. Toy example illustrating how C-precision are C-recall are calculated. Each simulated dataset, like the toy example shown in this figure, consists of 120 differentially expressed genes separated in 6 clusters characterized by different temporal patterns and 9880 not differentially expressed profiles. C-precision is calculated as true positives divided by the number of genes identified in the cluster; C-recall as true positives divided by the number of genes in the simulated cluster. As an example, since all the genes belonging to the identified profile 3 also belong to the same simulated pattern 3, the C-precision associated to the identified profile is 1 (4/4). On the other hand, the pattern 3 is also associated to other 16 genes which do not belong to this profile, thus the corresponding C-recall is 0.2 (4/20).