sigminer (version 0.1.11)

sig_estimate: Estimate signature number

Description

Use NMF package to evaluate the optimal number of signatures. Users should library(NMF) firstly.

Usage

sig_estimate(nmf_matrix, range = 2:5, nrun = 10, what = "all",
  cores = 1, seed = 123456, use_random = TRUE, save_plots = FALSE,
  plot_basename = file.path(tempdir(), "nmf"), method = "brunet",
  pConstant = NULL, verbose = FALSE)

Arguments

nmf_matrix

a matrix used for NMF decomposition (with rownames and colnames), generate from sig_prepare function.

range

a numeric vector containing the ranks of factorization to try. Note that duplicates are removed and values are sorted in increasing order. The results are notably returned in this order.

nrun

a numeric giving the number of run to perform for each value in range, nrun set to 30~50 is enough to achieve robust result.

what

a character vector whose elements partially match one of the following item, which correspond to the measures computed by summary on each <U+2013> multi-run <U+2013> NMF result: <U+2018>all<U+2019>, <U+2018>cophenetic<U+2019>, <U+2018>rss<U+2019>, <U+2018>residuals<U+2019>, <U+2018>dispersion<U+2019>, <U+2018>evar<U+2019>, <U+2018>silhouette<U+2019> (and more specific *.coef, *.basis, *.consensus), <U+2018>sparseness<U+2019> (and more specific *.coef, *.basis). It specifies which measure must be plotted (what='all' plots all the measures).

cores

number of cpu cores to run NMF.

seed

specification of the starting point or seeding method, which will compute a starting point, usually using data from the target matrix in order to provide a good guess.

use_random

Should generate random data from input to test measurements. Default is TRUE.

save_plots

if TRUE, save plots to local machine.

plot_basename

when save plots, set custom basename for file path.

method

specification of the NMF algorithm. Use 'brunet' as default. Available methods for nmf decompositions are 'brunet', 'lee', 'ls-nmf', 'nsNMF', 'offset'.

pConstant

A small positive value to add to the matrix. Use it ONLY if the functions throws an non-conformable arrays error.

verbose

if TRUE, print extra message.

Value

a list contains information of NMF run and rank survey.

Details

The most common approach is to choose the smallest rank for which cophenetic correlation coefficient starts decreasing (Used by this function). Another approach is to choose the rank for which the plot of the residual sum of squares (RSS) between the input matrix and its estimate shows an inflection point. More custom features please directly use NMF::nmfEstimateRank.

References

Gaujoux, Renaud, and Cathal Seoighe. "A flexible R package for nonnegative matrix factorization." BMC bioinformatics 11.1 (2010): 367.

See Also

Other signature analysis series function: sig_assign_samples, sig_extract, sig_get_activity, sig_get_correlation, sig_get_similarity, sig_prepare, sig_summarize_subtypes

Examples

# NOT RUN {
# Load copy number prepare object
load(system.file("extdata", "toy_copynumber_prepare.RData",
  package = "sigminer", mustWork = TRUE
))
library(NMF)
cn_estimate <- sig_estimate(cn_prepare$nmf_matrix,
  cores = 1, nrun = 5,
  verbose = TRUE
)
# }