computeSumClustPEAR: computeSumClustPear

In magStra/nonparametricSummaryPSM: Nonparametric methods to find optimal weights to combine posterior similarity matrices

Description

Compute summary PSMs (posterior similarity matrices) from a set of multiple PSMs obtained for instance by means of subsampling. This implements the Dirichlet process and Pitman-Yor process based methods for combining PSMs proposed in Strauss et al. Unravelling shared pseudo-trajectories at single-cell resolution. Internal function

Usage

computeSumClustPEAR(PSM, maxCl = 10)

Arguments

PSM	posterior similarity matrix
maxCl	maximum number of clusters

Value

Summary clustering computed using the PEAR criterion (Fritsch and Ickstadt, 2009, using the mcclust package (Fritsch, 2012))

Author(s)

Magdalena Strauss

magStra/nonparametricSummaryPSM documentation built on July 15, 2019, 5:59 p.m.