KRIS (version 1.1.6)

cal.pc.linear: Calculate linear principal component analysis (PCA) from numeric data and Single-nucleotide polymorphism (SNP) dataset

Description

Available for two types of data; numeric data and Single-nucleotide polymorphism (SNP) dataset in additive coding (0, 1, and 2).

Usage

cal.pc.linear(X, PCscore = TRUE, no.pc = NA, data.type = "linear", XXT = TRUE)

Arguments

X

A data matrix which rows represent samples and columns represent features.

PCscore

To specify whether scaled PCs will be calculated or not. If FALSE, eigenvectors are returned instead. Default = TRUE.

no.pc

A number of PCs to be calculated. If no.pc is set, PCs are patially calculated. Otherwise all PCs are obtained after calculation. Default = NA.

data.type

To specify a type of data matrix X. It can be set to "linear" and "snp". Default = "linear".

XXT

To specify how pricipal components (PCs) are calculated. If TRUE, PCs are calculated from X.t(X), otherwise X is used directly. XXT is useful option especially an input matrix X contains many columns. Enabling this option, it helps to reduce computation complexity. Regardless the option XXT is enable or not, optained PCs are the same. Default = TRUE.

Value

The returned value is a list with 2 objects, $PC, $evalue:

• $PC is a PC matrix which rows represent samples and columns represent PCs.

• $evalue is a vector of eigen values.

See Also

cal.pc.projection

Examples

# NOT RUN {
#Load simulated dataset
data(example_SNP)

#Using default parameters
PCs <- cal.pc.linear(simsnp$snp)
summary(PCs)

#Preview $PC
print(PCs$PC[1:5,1:3])

#Preview $evalue
print(PCs$evalue[1:3])

plot3views(PCs$PC[,1:3], sample_labels)

#Calculate PCs without PC scores

PCs <- cal.pc.linear(simsnp$snp, PCscore = FALSE)
summary(PCs)

#Preview $PC
print(PCs$PC[1:5,1:3])

#Preview $evalue
print(PCs$evalue[1:3])

plot3views(PCs$PC[,1:3], sample_labels)

#Calculate the top 3 PCs
PCs <- cal.pc.linear(simsnp$snp, no.pc = 3)
summary(PCs)

#Preview $PC
print(PCs$PC[1:5,1:3])

#Preview $evalue
print(PCs$evalue[1:3])

plot3views(PCs$PC[,1:3], sample_labels)
# }