dist_mat: Calculate Distance Matrix

In dswatson/cc_testr: Rigorously test cluster stability

Description

This utility function calculates the distance matrix for a given dataset.

Usage

dist_mat(dat, dist)

Arguments

dat	Probe by sample omic data matrix.
dist	Distance metric for clustering. Supports all methods available in dist and vegdist, as well as those implemented in the bioDist package.

Details

Samplewise distance is calculated using one of the following methods:

• "euclidean", "maximum", "manhattan", "canberra", and "minkowski" are all documented in the dist function. M3C relies on a lower level implementation via wordspace::dist.matrix to speed up computations. This latter function also documents the "cosine" distance.

• "pearson", "kendall", and "spearman" correspond to various forms of correlation distance, generally defined as 1 - the correlation coefficient. See cor for more details.

• "bray", "kulczynski", "jaccard", "gower", "altGower", "morisita", "horn", "mountford", "raup", "binomial", "chao", "cao", and "mahalanobis" are all available and documented in the vegan::vegdist function. These are designed for use with ecological data, e.g. a matrix of microbial OTU counts.

• "MI" and "KLD" are information theoretic distance metrics based on the mutual information and Kullback-Leibler divergence between vectors, respectively. They are implemented in the bioDist package using the MIdist and KLdist.matrix functions.

Value

An object of class dist representing the pairwise distance between columns of dat.

Examples

mat <- matrix(rnorm(1000 * 12), nrow = 1000, ncol = 12)
dm <- dist_mat(mat, dist = "euclidean")

dswatson/cc_testr documentation built on May 23, 2019, 7:34 a.m.