consensus_spectral_clustering: Apply consensus clustering on affinity matrix.
In agapow/subtypr: Robust and Validated Patient Subtyping for Precision Medicine

Description Usage Arguments Details Value

Use spectral clustering as the clustering function of consensus clustering on the provided affinity matrix.

consensus_spectral_clustering(affinity_matrix, cluster_number_max = 5,
  reps = 10, pItem = 0.8, pFeature = 1,
  title = "Consensus spectral clustering", innerLinkage = "average",
  finalLinkage = "average", distance = "pearson", ml = NULL,
  tmyPal = NULL, seed = NULL, plot = NULL, writeTable = FALSE,
  weightsItem = NULL, weightsFeature = NULL, verbose = F,
  corUse = "everything")

`affinity_matrix`	affinity matrix (e.g. produced by snf or anf)
`cluster_number_max`	integer. The maximum cluster number to evaluate.
`reps`	Number of subsamples evaluated.
`pItem`	numeric, proportion of items to sample.
`pFeature`	numeric, proportion of features to sample.
`title`	character for output directory. Directory is created only if plot is not NULL or writeTable is TRUE. This title can be an abosulte or relative path.
`innerLinkage`	heirarchical linkage method for subsampling.
`finalLinkage`	heirarchical linkage method for consensus matrix.
`ml`	optional. prior result, if supplied then only do graphics and tables.
`tmyPal`	optional character vector of colors for consensus matrix
`seed`	optional numerical value. sets random seed for reproducible results.
`plot`	character value. NULL - print to screen, 'pdf', 'png', 'pngBMP' for bitmap png, helpful for large datasets.
`writeTable`	logical value. TRUE - write ouput and log to csv.
`weightsItem`	optional numerical vector. weights to be used for sampling items.
`weightsFeature`	optional numerical vector. weights to be used for sampling features.
`verbose`	boolean. If TRUE, print messages to the screen to indicate progress. This is useful for large datasets.
`corUse`	optional character value. specifies how to handle missing data in correlation distances 'everything','pairwise.complete.obs', 'complete.obs' see cor() for description.

It uses ConsensusClusterPlus. ConsensusClusterPlus implements the Consensus Clustering algorithm of Monti, et al (2003). The function will subsamples the affinity matrix according to pItem, pFeature, weightsItem, and weightsFeature, and clusters the data into 2 to maxK clusters using spectral clustering.

It will also compute the item consensus results using calcICL. For more informations, see the documentation of the original package!

results of ConsensusClusterPlus & calcICL.

agapow/subtypr documentation built on May 5, 2019, 1:33 a.m.