Skip to main content


Figure 9 | BMC Bioinformatics

Figure 9

From: Learning smoothing models of copy number profiles using breakpoint annotations

Figure 9

The n/t -fold cross-validation protocol was used to estimate error, false positive (fp), and false negative (fn) rates in the detailed annotations of the n = 575 profiles. Squares show the same colors as in the figures, and are absent for default models that have no smoothness parameters. The smoothness parameter was chosen using annotations from approximately t=10 profiles, and mean and standard deviation (sd) of test error over n/t=57 folds are shown as percents. The Timings column shows the median number of seconds to fit the sequence of smoothing models for a single profile.

Back to article page