messina (version 1.8.2)

plot,MessinaSurvResult,missing-method: Plot the results of a Messina analysis on a survival problem.

Description

Plots diagnostic and performance information for fits in a MessinaSurvResult object, as returned by messinaSurv.

Usage

## S3 method for class 'MessinaSurvResult,missing':
plot(x, y, ...)

Arguments

x

the result of a Messina survival analysis, as returned by messinaSurv.

...

additional options to control the plot: [object Object],[object Object],[object Object],[object Object],[object Object],[object Object]

y

the y coordinates of points in the plot, optional if x is an appropriate structure.

Details

For each feature index given by indices, produces four plots: [object Object],[object Object],[object Object],[object Object]

The Kaplan-Meier plots may optionally display bootstrap bands, if bootstrap_type != "none". Note that the calculation of bootstrap bands is computationally-intensive, and this function will by default use multiprocessing to speed calculations if doMC is loaded and more than one core registered for use. For examples of the plots and their interpretation, see the vignette.

See Also

MessinaSurvResult-class

messinaSurv

Examples

## Load a subset of the TCGA renal clear cell carcinoma data
## as an example.
data(tcga_kirc_example)

## Run the messinaSurv analysis on these data.  Use a tau
## objective, with a minimum performance of 0.6.  Note that
## messinaSurv analyses are very computationally-intensive,
## so multicore use with doMC loaded and parallel = TRUE is
## strongly recommended.  In this example we use a single
## core by default.
fit = messinaSurv(kirc.exprs, kirc.surv, obj_func = "tau", obj_min = 0.6)

## Plot the three best features found by Messina
plot(fit, indices = 1:3)

## Plot the best feature found by Messina, with 90\% confidence bands.
## Note that the bootstrap iterations can be slow, so it is
## recommended that multiple cores are used, with doMC loaded
## and parallel = TRUE.
plot(fit, indices = 1, bootstrap_type = "ci", bootstrap_ci = 0.9)

## Plot the Messina fit of the 10th feature in the dataset, with
## +/- 1 standard deviation bands.
plot(fit, indices = 10, sort_features = FALSE, bootstrap_type = "stdev")