selectCommonComps: Select common components in two data blocks

In llrs/STATegRa: Classes and methods for multi-omics data integration

Description

This function applies a Simultaneous Component Analysis (SCA). The idea is that the scores for both blocks should have a similar behaviour if the components are in the common mode. Evaluation is by the ratios between the explained variances (SSQ) of each block and the estimator. The highest component count with 0.8 < ratio < 1.5 is selected.

Usage

selectCommonComps(X, Y, Rmax)

Arguments

X	Matrix of omics data
Y	Matrix of omics data
Rmax	Maximum number of common components to find

Value

A list with components:

common

Optimal number of common components

ssqs

Matrix of SSQ for each block and estimator

pssq

ggplot object showing SSQ for each block and estimator

pratios

ggplot object showing SSQ ratios between each block and estimator

Author(s)

Patricia Sebastian-Leon

Examples

data(STATegRa_S3)
cc <- selectCommonComps(X=Block1.PCA, Y=Block2.PCA, Rmax=3)
cc$common
cc$pssq
cc$pratios

llrs/STATegRa documentation built on May 29, 2019, 3:42 a.m.