Project synthetic profiles onto existing principal component axes generated using the reference 1KG profiles

The function projects the synthetic profiles onto existing principal component axes generated using the reference 1KG profiles. The reference profiles used to generate the synthetic profiles have previously been removed from the set of reference profiles.

computePCAMultiSynthetic(
  gdsProfile,
  listPCA,
  sampleRef,
  studyIDSyn,
  verbose = FALSE
)

Arguments

gdsProfile: an object of class gds.class (a GDS file), an opened Profile GDS file.
listPCA: a list containing the PCA object generated with the 1KG reference profiles (excluding the ones used to generate the synthetic data set) in an entry called "pca.unrel".
sampleRef: a vector of character strings representing the identifiers of the 1KG reference profiles that have been used to generate the synthetic profiles that are going to be analysed here. The sub-continental identifiers are used as names for the vector.
studyIDSyn: a character string corresponding to the study identifier. The study identifier must be present in the Profile GDS file.
verbose: a logical indicating if messages should be printed to show how the different steps in the function. Default: FALSE.

Value

a list containing 3 entries:

sample.id: a vector of character strings representing the identifiers of the synthetic profiles that have been projected onto the 1KG PCA.
eigenvector.ref: a matrix of numeric with the eigenvectors of the 1KG reference profiles used to generate the PCA.
eigenvector: a matrix of numeric with the eigenvectors of the synthetic profiles projected onto the 1KG PCA.

Author

Pascal Belleau, Astrid Deschênes and Alexander Krasnitz

Examples


## Required library
library(gdsfmt)

## Loading demo PCA on subset of 1KG reference dataset
data(demoPCA1KG)

## Path to the demo Profile GDS file is located in this package
dataDir <- system.file("extdata/demoKNNSynthetic", package="RAIDS")

# The name of the synthetic study
studyID <- "MYDATA.Synthetic"

samplesRM <- c("HG00246", "HG00325", "HG00611", "HG01173", "HG02165",
    "HG01112", "HG01615", "HG01968", "HG02658", "HG01850", "HG02013",
    "HG02465", "HG02974", "HG03814", "HG03445", "HG03689", "HG03789",
    "NA12751", "NA19107", "NA18548", "NA19075", "NA19475", "NA19712",
    "NA19731", "NA20528", "NA20908")
names(samplesRM) <- c("GBR", "FIN", "CHS","PUR", "CDX", "CLM", "IBS",
    "PEL", "PJL", "KHV", "ACB", "GWD", "ESN", "BEB", "MSL", "STU", "ITU",
    "CEU", "YRI", "CHB", "JPT", "LWK", "ASW", "MXL", "TSI", "GIH")

## Open the Profile GDS file
gdsProfile <- snpgdsOpen(file.path(dataDir, "ex1.gds"))

## Projects synthetic profiles on 1KG PCA
results <- computePCAMultiSynthetic(gdsProfile=gdsProfile,
    listPCA=demoPCA1KG,
    sampleRef=samplesRM, studyIDSyn=studyID, verbose=FALSE)

## The eigenvectors for the synthetic profiles
head(results$eigenvector)
#>                       [,1]         [,2]         [,3]         [,4]         [,5]
#> 1.ex1.HG00246.1 0.06469191 -0.004653002 -0.088967175 -0.060291452  0.031812132
#> 1.ex1.HG00325.1 0.09115431 -0.004743912 -0.071907454  0.044100229 -0.041522503
#> 1.ex1.HG00611.1 0.01381479 -0.017912275  0.062489822  0.003760931  0.061062765
#> 1.ex1.HG01173.1 0.02193600  0.016635981 -0.123902643 -0.104948054  0.021495661
#> 1.ex1.HG02165.1 0.15626481 -0.003083060 -0.004768404  0.100910618 -0.002478422
#> 1.ex1.HG01112.1 0.07699686 -0.015195235 -0.102489655 -0.088759431 -0.031143964
#>                         [,6]         [,7]        [,8]        [,9]        [,10]
#> 1.ex1.HG00246.1 -0.087084898 -0.002319659 -0.01327109 -0.06600164  0.011422042
#> 1.ex1.HG00325.1  0.092420817 -0.150333993  0.04064972  0.06185469  0.045882592
#> 1.ex1.HG00611.1  0.006946086  0.037328105  0.01327867 -0.03629313  0.015773551
#> 1.ex1.HG01173.1  0.026114397 -0.045510755 -0.02727912  0.12362088  0.005003337
#> 1.ex1.HG02165.1 -0.213193715 -0.205975416 -0.33167160  0.01689627  0.415307845
#> 1.ex1.HG01112.1  0.140457360 -0.129621812  0.18058981  0.09950699 -0.058262338
#>                         [,11]        [,12]       [,13]       [,14]       [,15]
#> 1.ex1.HG00246.1  0.1135730541  0.120776205  0.05104489  0.10009894  0.08226945
#> 1.ex1.HG00325.1 -0.0213545024  0.017612760 -0.12065696  0.11956275 -0.05519839
#> 1.ex1.HG00611.1  0.0002207075  0.008803511  0.06544166  0.02462076  0.00500031
#> 1.ex1.HG01173.1 -0.0877004088 -0.023906580 -0.11278874 -0.02636037 -0.09290133
#> 1.ex1.HG02165.1  0.1492485496 -0.094433444 -0.10994232  0.06307073  0.06593791
#> 1.ex1.HG01112.1 -0.1773609745 -0.105883583 -0.15020718  0.04382861 -0.04644355

## Close Profile GDS file (important)
closefn.gds(gdsProfile)