Figure 6

Calculation of agreement between original and noisy data clustering. OC indicates original data clustering of genes, and NC indicates noisy data clustering of genes. n(OC ∩ NC) is the number of genes assigned to the same clusters in both clusterings, and n(OC ∪ NC) is the number of genes assigned to one cluster at least for both clusterings. Here, the agreement computes the degree of agreement between the original and noisy datasets, where the noisy dataset was generated by adding a Gaussian random variable of mean 0, and standard deviation 1 to the original dataset.