get_NMF: Implement transcriptome subtyping by NMF method

In AllenSpike/CPDR: Cancer Drug Personalized Recommendation (CDPR)

Implement transcriptome subtyping by NMF method

Description

Implement transcriptome subtyping by NMF method

Usage

get_NMF(
  mat,
  method = "MAD",
  value = 1500,
  clusterNum = NULL,
  rank = 2:6,
  nrun = 30,
  seed = NULL,
  doPlot = TRUE
)

Arguments

mat	Profiles of selected TCGA data set.
method	Method for feature selection, optional 'MAD', 'VAR' and 'PCA' ('MAD' by default).
value	A numeric value for biological feature selection. If method='MAD' or 'VAR', the top number of value features are selected. If method='PCA', the value of principal component is selected.
clusterNum	Number of subtypes for the data set.
rank	A numeric vector for the estimation of clusterNum. It will be overrided if clusterNum is not NULL.
nrun	Number of runs to perform NMF. A default of 30 runs are performed, allowing the computation of a consensus matrix that is used in selecting the best result for cancer subtypes identification as Consensus Clustering method.
seed	A numeric value is used to seed the random number generator before generating a random starting point.
doPlot	A logical value. If true, draw the heatmap for the distance matrix with samples ordered to form clusters.

Value

The NMF subtyping result.

AllenSpike/CPDR documentation built on April 18, 2022, 4:38 p.m.