cytosee_DensityCut: The densityCut algorithm

In mingchen-lab/cytosee: automatic computation and evaluation of cytometry data

Description

densityCut first roughly estimates the densities of data points from a K-nearest neighbour graph and then refines the densities via a random walk. A cluster consists of points falling into the basin of attraction of an estimated mode of the underlining density function. A post-processing step merges clusters and generates a hierarchical cluster tree. The number of clusters is selected from the most stable clustering in the hierarchical cluster tree. Experimental results on ten synthetic benchmark datasets and two microarray gene expression datasets demonstrate that densityCut performs better than state-of-the-art algorithms for clustering biological datasets.

Usage

cytosee_DensityCut(object, K, knn.index, knn.dist, V, D, G, threshold,
  alpha = 0.9, adjust = TRUE, maxit = 50, eps = 1e-05, col = NULL,
  debug = FALSE, xlab = TRUE, text = NULL, ...)

Arguments

object	an object of cytosee class.
K	A integer to specify the number of neighbours in building the Knn graph. Default to K=\log_2(N), where N is the number of data points
knn.index	An N*K data matrix for the nearest neighbour indices
knn.dist	An N*K data matrix for the nearest neighbour distances
V	The initial density vector of length N
D	The dimensionality of data
G	A sparse Knn graph, reseaved for extension
threshold	A number between 0 and 1 specifying the saliency index to cut the tree. If not specified, it is selecting by stability analysis of the clustering tree
alpha	The damping factor between 0 and 1, default to 0.90
adjust	Lotical, whether to ajdust valley height or not
maxit	The maximum number of iteration allowed in density refinement, default to 50
eps	The threshold in density refinement, default to 1e-5
col	A vector of clours
debug	Logical, whether to print debug information
xlab	Logical, whether to show the xlab
text	subplot label
...	Reserved for extension
X	A data matrix (columns are features and rows are data points)
The	damping factor between 0 and 1, default to 0.90
nu	The saliency index in merging trees, default to seq(0.0, 1.0, by=0.05)
show.plot	Logical, whether to draw clustering results
show.tip.label	Logical, whether to draw the tip labels of trees

mingchen-lab/cytosee documentation built on May 6, 2019, 8:34 p.m.