Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: Model selection and robust inference of mutational signatures using Negative Binomial non-negative matrix factorization

Fig. 2

Method comparison using simulated data. Each method is applied on the data sets from Fig. 1b and, for each data set, the value of the estimated number of signatures is kept. We test values for the number of signatures from two to eight for Poisson noise and Negative Binomial noise with \(\alpha = \{10, 200 \}\), and a patient specific dispersion parameter \(\alpha \sim U(10,500)\)

Back to article page