PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

1 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

if (!requireNamespace('BiocManager', quietly = TRUE))

install.packages('BiocManager')

BiocManager::install('PCAtools')

if (!requireNamespace('devtools', quietly = TRUE))

install.packages('devtools')

devtools::install_github('kevinblighe/PCAtools')

library(PCAtools)

2 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

library(Biobase)
library(GEOquery)

# load series and platform data from GEO

gset <- getGEO('GSE2990', GSEMatrix = TRUE, getGPL = FALSE)
mat <- exprs(gset[[1]])

# remove Affymetrix control probes

mat <- mat[-grep('^AFFX', rownames(mat)),]

# extract information of interest from the phenotype data (pdata)

idx <- which(colnames(pData(gset[[1]])) %in%
c('relation', 'age:ch1', 'distant rfs:ch1', 'er:ch1',
'ggi:ch1', 'grade:ch1', 'size:ch1',
'time rfs:ch1'))
metadata <- data.frame(pData(gset[[1]])[,idx],
row.names = rownames(pData(gset[[1]])))

# tidy column names

colnames(metadata) <- c('Study', 'Age', 'Distant.RFS', 'ER', 'GGI', 'Grade',
'Size', 'Time.RFS')

# prepare certain phenotypes of interest

metadata$Study <- gsub('Reanalyzed by: ', '', as.character(metadata$Study))
metadata$Age <- as.numeric(gsub('^KJ', NA, as.character(metadata$Age)))
metadata$Distant.RFS <- factor(metadata$Distant.RFS,
levels = c(0,1))
metadata$ER <- factor(gsub('\\?', NA, as.character(metadata$ER)),
levels = c(0,1))
metadata$ER <- factor(ifelse(metadata$ER == 1, 'ER+', 'ER-'),
levels = c('ER-', 'ER+'))
metadata$GGI <- as.numeric(as.character(metadata$GGI))
metadata$Grade <- factor(gsub('\\?', NA, as.character(metadata$Grade)),
levels = c(1,2,3))
metadata$Grade <- gsub(1, 'Grade 1', gsub(2, 'Grade 2', gsub(3, 'Grade 3', metada
ta$Grade)))
metadata$Grade <- factor(metadata$Grade, levels = c('Grade 1', 'Grade 2', 'Grade
3'))
metadata$Size <- as.numeric(as.character(metadata$Size))
metadata$Time.RFS <- as.numeric(gsub('^KJX|^KJ', NA, metadata$Time.RFS))

# remove samples from the pdata that have any NA value

discard <- apply(metadata, 1, function(x) any(is.na(x)))
metadata <- metadata[!discard,]

# filter the expression data to match the samples in our pdata

mat <- mat[,which(colnames(mat) %in% rownames(metadata))]

# check that sample names match exactly between pdata and expression data
all(colnames(mat) == rownames(metadata))

3 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

## [1] TRUE

p <- pca(mat, metadata = metadata, removeVar = 0.1)

## -- removing the lower 10% of variables based on variance

screeplot(p, axisLabSize = 18, titleLabSize = 22)

biplot(p)

biplot(p, showLoadings = TRUE, lab = NULL)

4 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

pairsplot(p)

5 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

plotloadings(p, labSize = 3)

## -- variables retained:

6 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

## 215281_x_at, 214464_at, 211122_s_at, 210163_at, 204533_at, 205225_at, 209351_at, 2

05044_at, 202037_s_at, 204540_at, 215176_x_at, 214768_x_at, 212671_s_at, 219415_at, 3
7892_at, 208650_s_at, 206754_s_at, 205358_at, 205380_at, 205825_at

eigencorplot(p,
metavars = c('Study','Age','Distant.RFS','ER',
'GGI','Grade','Size','Time.RFS'))

7 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

p$rotated[1:5,1:5]

## PC1 PC2 PC3 PC4 PC5

## GSM65752 -30.24272 43.826310 3.781677 -39.536149 18.612835
## GSM65753 -37.73436 -15.464421 -4.913100 -5.877623 9.060108
## GSM65755 -29.95155 7.788280 -22.980076 -15.222649 23.123766
## GSM65757 -33.73509 1.261410 -22.834375 2.494554 13.629207
## GSM65758 -40.95958 -8.588458 4.995440 14.340150 0.417101

p$loadings[1:5,1:5]

## PC1 PC2 PC3 PC4 PC5

## 206378_at -0.0024336244 -0.05312797 -0.004809456 0.04045087 0.0096616577
## 205916_at -0.0051057533 0.00122765 -0.010593760 0.04023264 0.0285972617
## 206799_at 0.0005723191 -0.05048096 -0.009992964 0.02568142 0.0024626261
## 205242_at 0.0129147329 0.02867789 0.007220832 0.04424070 -0.0006138609
## 206509_at 0.0019058729 -0.05447596 -0.004979062 0.01510060 -0.0026213610

8 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

suppressMessages(require(hgu133a.db))
newnames <- mapIds(hgu133a.db,
keys = rownames(p$loadings),
column = c('SYMBOL'),
keytype = 'PROBEID')

## 'select()' returned 1:many mapping between keys and columns

# tidy up for NULL mappings and duplicated gene symbols

newnames <- ifelse(is.na(newnames) | duplicated(newnames),
names(newnames), newnames)
rownames(p$loadings) <- newnames

horn <- parallelPCA(mat)

horn$n

## [1] 11

elbow <- findElbowPoint(p$variance)

elbow

## PC8
## 8

9 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

library(ggplot2)

screeplot(p,
components = getComponents(p, 1:20),
vline = c(horn$n, elbow)) +

geom_label(aes(x = horn$n + 1, y = 50,

label = 'Horn\'s', vjust = -1, size = 8)) +
geom_label(aes(x = elbow + 1, y = 50,
label = 'Elbow method', vjust = -1, size = 8))

which(cumsum(p$variance) > 80)[1]

10 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

## PC27
## 27

biplot(p,
lab = paste0(p$metadata$Age, ' años'),
colby = 'ER',
hline = 0, vline = 0,
legendPosition = 'right')

11 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

biplot(p,
colby = 'ER', colkey = c('ER+' = 'forestgreen', 'ER-' = 'purple'),
colLegendTitle = 'ER-\nstatus',
# encircle config
encircle = TRUE,
encircleFill = TRUE,
hline = 0, vline = c(-25, 0, 25),
legendPosition = 'top', legendLabSize = 16, legendIconSize = 8.0)

12 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

biplot(p,
colby = 'ER', colkey = c('ER+' = 'forestgreen', 'ER-' = 'purple'),
colLegendTitle = 'ER-\nstatus',
# encircle config
encircle = TRUE, encircleFill = FALSE,
encircleAlpha = 1, encircleLineSize = 5,
hline = 0, vline = c(-25, 0, 25),
legendPosition = 'top', legendLabSize = 16, legendIconSize = 8.0)

13 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

14 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

biplot(p,
colby = 'ER', colkey = c('ER+' = 'forestgreen', 'ER-' = 'purple'),
# ellipse config
ellipse = TRUE,
ellipseConf = 0.95,
ellipseFill = TRUE,
ellipseAlpha = 1/4,
ellipseLineSize = 1.0,
xlim = c(-125,125), ylim = c(-50, 80),
hline = 0, vline = c(-25, 0, 25),
legendPosition = 'top', legendLabSize = 16, legendIconSize = 8.0)

15 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

biplot(p,
colby = 'ER', colkey = c('ER+' = 'forestgreen', 'ER-' = 'purple'),
# ellipse config
ellipse = TRUE,
ellipseConf = 0.95,
ellipseFill = TRUE,
ellipseAlpha = 1/4,
ellipseLineSize = 0,
ellipseFillKey = c('ER+' = 'yellow', 'ER-' = 'pink'),
xlim = c(-125,125), ylim = c(-50, 80),
hline = 0, vline = c(-25, 0, 25),
legendPosition = 'top', legendLabSize = 16, legendIconSize = 8.0)

16 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

17 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

biplot(p,
colby = 'ER', colkey = c('ER+' = 'forestgreen', 'ER-' = 'purple'),
hline = c(-25, 0, 25), vline = c(-25, 0, 25),
legendPosition = 'top', legendLabSize = 13, legendIconSize = 8.0,
shape = 'Grade', shapekey = c('Grade 1' = 15, 'Grade 2' = 17, 'Grade 3' = 8),
drawConnectors = FALSE,
title = 'PCA bi-plot',
subtitle = 'PC1 versus PC2',
caption = '27 PCs ≈ 80%')

biplot(p,
lab = NULL,
colby = 'ER', colkey = c('ER+'='royalblue', 'ER-'='red3'),
hline = c(-25, 0, 25), vline = c(-25, 0, 25),
vlineType = c('dotdash', 'solid', 'dashed'),
gridlines.major = FALSE, gridlines.minor = FALSE,
pointSize = 5,
legendPosition = 'left', legendLabSize = 14, legendIconSize = 8.0,
shape = 'Grade', shapekey = c('Grade 1'=15, 'Grade 2'=17, 'Grade 3'=8),
drawConnectors = FALSE,
title = 'PCA bi-plot',
subtitle = 'PC1 versus PC2',
caption = '27 PCs ≈ 80%')

biplot(p,
# loadings parameters
showLoadings = TRUE,
lengthLoadingsArrowsFactor = 1.5,
sizeLoadingsNames = 4,
colLoadingsNames = 'red4',
# other parameters
lab = NULL,
colby = 'ER', colkey = c('ER+'='royalblue', 'ER-'='red3'),
hline = 0, vline = c(-25, 0, 25),
vlineType = c('dotdash', 'solid', 'dashed'),
gridlines.major = FALSE, gridlines.minor = FALSE,
pointSize = 5,
legendPosition = 'left', legendLabSize = 14, legendIconSize = 8.0,
shape = 'Grade', shapekey = c('Grade 1'=15, 'Grade 2'=17, 'Grade 3'=8),
drawConnectors = FALSE,
title = 'PCA bi-plot',
subtitle = 'PC1 versus PC2',
caption = '27 PCs ≈ 80%')

18 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

# add ESR1 gene expression to the metadata

p$metadata$ESR1 <- mat['205225_at',]

biplot(p,
x = 'PC2', y = 'PC3',
lab = NULL,
colby = 'ESR1',
shape = 'ER',
hline = 0, vline = 0,
legendPosition = 'right') +

scale_colour_gradient(low = 'gold', high = 'red2')

19 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

biplot(p, x = 'PC10', y = 'PC50',

lab = NULL,
colby = 'Age',
hline = 0, vline = 0,
hlineWidth = 1.0, vlineWidth = 1.0,
gridlines.major = FALSE, gridlines.minor = TRUE,
pointSize = 5,
legendPosition = 'left', legendLabSize = 16, legendIconSize = 8.0,
shape = 'Grade', shapekey = c('Grade 1'=15, 'Grade 2'=17, 'Grade 3'=8),
drawConnectors = FALSE,
title = 'PCA bi-plot',
subtitle = 'PC10 versus PC50',
caption = '27 PCs ≈ 80%')

20 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

pairsplot(p,
components = getComponents(p, c(1:10)),
triangle = TRUE, trianglelabSize = 12,
hline = 0, vline = 0,
pointSize = 0.4,
gridlines.major = FALSE, gridlines.minor = FALSE,
colby = 'Grade',
title = 'Pairs plot', plotaxes = FALSE,
margingaps = unit(c(-0.01, -0.01, -0.01, -0.01), 'cm'))

21 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

22 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

pairsplot(p,
components = getComponents(p, c(4,33,11,1)),
triangle = FALSE,
hline = 0, vline = 0,
pointSize = 0.8,
gridlines.major = FALSE, gridlines.minor = FALSE,
colby = 'ER',
title = 'Pairs plot', titleLabSize = 22,
axisLabSize = 14, plotaxes = TRUE,
margingaps = unit(c(0.1, 0.1, 0.1, 0.1), 'cm'))

23 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

plotloadings(p,
rangeRetain = 0.01,
labSize = 4.0,
title = 'Loadings plot',
subtitle = 'PC1, PC2, PC3, PC4, PC5',
caption = 'Top 1% variables',
shape = 24,
col = c('limegreen', 'black', 'red3'),
drawConnectors = TRUE)

## -- variables retained:

## POGZ, CDC42BPA, CXCL11, ESR1, SFRP1, EEF1A2, IGKC, GABRP, CD24, PDZK1

24 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

plotloadings(p,
components = getComponents(p, c(4,33,11,1)),
rangeRetain = 0.1,
labSize = 4.0,
absolute = FALSE,
title = 'Loadings plot',
subtitle = 'Misc PCs',
caption = 'Top 10% variables',
shape = 23, shapeSizeRange = c(1, 16),
col = c('white', 'pink'),
drawConnectors = FALSE)

## -- variables retained:

## CXCL11, IGKC, CXCL9, 210163_at, 214768_x_at, 211645_x_at, 211644_x_at, IGHA1, 2164

91_x_at, 214777_at, 216576_x_at, 212671_s_at, IL23A, PLAAT4, 212588_at, 212998_x_at,
KRT14, GABRP, SOX10, PTX3, TTYH1, CPB1, KRT15, MYBPC1, DST, CXADR, GALNT3, CDH3, TCI
M, DHRS2, MMP1, CRABP1, CST1, MAGEA3, ACOX2, PRKAR2B, PLCB1, HDGFL3, CYP2B6, ORM1, 20
5040_at, HSPB8, SCGB2A2, JCHAIN, POGZ, 213872_at, DYNC2LI1, CDC42BPA

25 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

26 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

eigencorplot(p,
components = getComponents(p, 1:27),
metavars = c('Study','Age','Distant.RFS','ER',
'GGI','Grade','Size','Time.RFS'),
col = c('darkblue', 'blue2', 'black', 'red2', 'darkred'),
cexCorval = 0.7,
colCorval = 'white',
fontCorval = 2,
posLab = 'bottomleft',
rotLabX = 45,
posColKey = 'top',
cexLabColKey = 1.5,
scale = TRUE,
main = 'PC1-27 clinical correlations',
colFrame = 'white',
plotRsquared = FALSE)

27 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

eigencorplot(p,
components = getComponents(p, 1:horn$n),
metavars = c('Study','Age','Distant.RFS','ER','GGI',
'Grade','Size','Time.RFS'),
col = c('white', 'cornsilk1', 'gold', 'forestgreen', 'darkgreen'),
cexCorval = 1.2,
fontCorval = 2,
posLab = 'all',
rotLabX = 45,
scale = TRUE,
main = bquote(Principal ~ component ~ Pearson ~ r^2 ~ clinical ~ correlates),
plotRsquared = TRUE,
corFUN = 'pearson',
corUSE = 'pairwise.complete.obs',
corMultipleTestCorrection = 'BH',
signifSymbols = c('****', '***', '**', '*', ''),
signifCutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, 1))

28 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

pscree <- screeplot(p, components = getComponents(p, 1:30),

hline = 80, vline = 27, axisLabSize = 14, titleLabSize = 20,
returnPlot = FALSE) +
geom_label(aes(20, 80, label = '80% explained variation', vjust = -1, size = 8))

ppairs <- pairsplot(p, components = getComponents(p, c(1:3)),

triangle = TRUE, trianglelabSize = 12,
hline = 0, vline = 0,
pointSize = 0.8, gridlines.major = FALSE, gridlines.minor = FALSE,
colby = 'Grade',
title = '', plotaxes = FALSE,
margingaps = unit(c(0.01, 0.01, 0.01, 0.01), 'cm'),
returnPlot = FALSE)

pbiplot <- biplot(p,

# loadings parameters
showLoadings = TRUE,
lengthLoadingsArrowsFactor = 1.5,
sizeLoadingsNames = 4,
colLoadingsNames = 'red4',
# other parameters
lab = NULL,
colby = 'ER', colkey = c('ER+'='royalblue', 'ER-'='red3'),
hline = 0, vline = c(-25, 0, 25),
vlineType = c('dotdash', 'solid', 'dashed'),
gridlines.major = FALSE, gridlines.minor = FALSE,
pointSize = 5,
legendPosition = 'none', legendLabSize = 16, legendIconSize = 8.0,
shape = 'Grade', shapekey = c('Grade 1'=15, 'Grade 2'=17, 'Grade 3'=8),
drawConnectors = FALSE,
title = 'PCA bi-plot',
subtitle = 'PC1 versus PC2',
caption = '27 PCs ≈ 80%',
returnPlot = FALSE)

ploadings <- plotloadings(p, rangeRetain = 0.01, labSize = 4,

title = 'Loadings plot', axisLabSize = 12,
subtitle = 'PC1, PC2, PC3, PC4, PC5',
caption = 'Top 1% variables',
shape = 24, shapeSizeRange = c(4, 8),
col = c('limegreen', 'black', 'red3'),
legendPosition = 'none',
drawConnectors = FALSE,
returnPlot = FALSE)

peigencor <- eigencorplot(p,

components = getComponents(p, 1:10),
metavars = c('Study','Age','Distant.RFS','ER',
'GGI','Grade','Size','Time.RFS'),
cexCorval = 1.0,

29 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

fontCorval = 2,
posLab = 'all',
rotLabX = 45,
scale = TRUE,
main = "PC clinical correlates",
cexMain = 1.5,
plotRsquared = FALSE,
corFUN = 'pearson',
corUSE = 'pairwise.complete.obs',
signifSymbols = c('****', '***', '**', '*', ''),
signifCutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, 1),
returnPlot = FALSE)

library(cowplot)
library(ggplotify)

top_row <- plot_grid(pscree, ppairs, pbiplot,

ncol = 3,
labels = c('A', 'B Pairs plot', 'C'),
label_fontfamily = 'serif',
label_fontface = 'bold',
label_size = 22,
align = 'h',
rel_widths = c(1.10, 0.80, 1.10))

bottom_row <- plot_grid(ploadings,

as.grob(peigencor),
ncol = 2,
labels = c('D', 'E'),
label_fontfamily = 'serif',
label_fontface = 'bold',
label_size = 22,
align = 'h',
rel_widths = c(0.8, 1.2))

plot_grid(top_row, bottom_row, ncol = 1,

rel_heights = c(1.1, 0.9))

30 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

p <- pca(mat, metadata = metadata, removeVar = 0.1)

## -- removing the lower 10% of variables based on variance

31 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

p.prcomp <- list(sdev = p$sdev,

rotation = data.matrix(p$loadings),
x = data.matrix(p$rotated),
center = TRUE, scale = TRUE)

class(p.prcomp) <- 'prcomp'

# for this simple example, just use a chunk of

# the original data for the prediction
newdata <- t(mat[,seq(1,20)])
predict(p.prcomp, newdata = newdata)[,1:5]

## PC1 PC2 PC3 PC4 PC5

## GSM65752 11.683293 71.0152986 10.677205 -75.97644152 29.7537169
## GSM65753 -10.542633 -31.9953531 -2.753783 -19.59178967 14.9924713
## GSM65755 6.585509 13.4975310 -40.370389 -29.38990525 47.7142845
## GSM65757 1.498398 -0.1294115 -37.336278 0.08078156 22.3448232
## GSM65758 -18.049833 -14.9445805 14.890320 16.57567005 3.4010033
## GSM65760 8.073473 47.5491189 -18.016340 -9.73629569 -51.7330414
## GSM65761 -3.689814 7.7199606 -35.476666 -35.31465087 -40.1455143
## GSM65762 3.949911 -24.9428080 4.710631 2.71721065 43.2182093
## GSM65763 -20.757238 -33.3085383 22.639443 7.41053224 -9.9339918
## GSM65764 -12.287305 -12.7566718 13.813429 33.75583684 17.7938583
## GSM65767 -4.209505 -13.9349129 -17.814569 -14.87200276 -82.4754172
## GSM65768 3.547044 39.6095431 -28.424912 40.26444836 45.6591355
## GSM65769 3.754370 30.0201461 12.415498 45.74502641 37.9905308
## GSM65770 2.538593 -36.6517740 54.887990 5.94021104 -0.9545218
## GSM65771 -7.382089 -8.5963702 27.749060 -21.50981794 -71.4524526
## GSM65772 3.735223 43.2576570 26.995375 21.01817312 -68.8193200
## GSM65773 15.775812 -19.4523339 4.419158 -6.47899302 -25.2479186
## GSM65774 17.589719 -28.5666333 -52.875007 -16.82207768 37.8455365
## GSM65775 -3.375783 -5.2950960 27.071957 49.10111537 55.0410908
## GSM65776 1.562855 -22.0947718 12.797877 7.08296875 -4.9924828

32 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

sessionInfo()

33 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

## R version 4.0.3 (2020-10-10)

## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.5 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.12-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.12-bioc/R/lib/libRlapack.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=C
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] stats4 parallel stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] ggplotify_0.0.5 cowplot_1.1.0 hgu133a.db_3.2.3
## [4] org.Hs.eg.db_3.12.0 AnnotationDbi_1.52.0 IRanges_2.24.0
## [7] S4Vectors_0.28.0 GEOquery_2.58.0 Biobase_2.50.0
## [10] BiocGenerics_0.36.0 PCAtools_2.2.0 ggrepel_0.8.2
## [13] ggplot2_3.3.2
##
## loaded via a namespace (and not attached):
## [1] matrixStats_0.57.0 bit64_4.0.5
## [3] ash_1.0-15 RColorBrewer_1.1-2
## [5] tools_4.0.3 R6_2.4.1
## [7] irlba_2.3.3 KernSmooth_2.23-17
## [9] DBI_1.1.0 colorspace_1.4-1
## [11] withr_2.3.0 tidyselect_1.1.0
## [13] ggalt_0.4.0 bit_4.0.4
## [15] curl_4.3 compiler_4.0.3
## [17] extrafontdb_1.0 cli_2.1.0
## [19] xml2_1.3.2 DelayedArray_0.16.0
## [21] labeling_0.4.2 scales_1.1.1
## [23] proj4_1.0-10 readr_1.4.0
## [25] stringr_1.4.0 digest_0.6.27
## [27] rmarkdown_2.5 pkgconfig_2.0.3
## [29] htmltools_0.5.0 extrafont_0.17
## [31] sparseMatrixStats_1.2.0 MatrixGenerics_1.2.0
## [33] limma_3.46.0 highr_0.8
## [35] maps_3.3.0 rlang_0.4.8
## [37] rstudioapi_0.11 RSQLite_2.2.1
## [39] DelayedMatrixStats_1.12.0 gridGraphics_0.5-0
## [41] farver_2.0.3 generics_0.0.2
## [43] BiocParallel_1.24.0 dplyr_1.0.2

34 of 35 21-01-2021, 02:19 pm
PCAtools: everything Principal Component Analysis https://bioconductor.org/packages/release/bioc/vignettes/PCAtools/inst/d...

## [45] magrittr_1.5 BiocSingular_1.6.0

## [47] Matrix_1.2-18 Rcpp_1.0.5
## [49] munsell_0.5.0 fansi_0.4.1
## [51] lifecycle_0.2.0 stringi_1.5.3
## [53] yaml_2.2.1 MASS_7.3-53
## [55] plyr_1.8.6 grid_4.0.3
## [57] blob_1.2.1 dqrng_0.2.1
## [59] crayon_1.3.4 lattice_0.20-41
## [61] beachmat_2.6.0 hms_0.5.3
## [63] knitr_1.30 ps_1.4.0
## [65] pillar_1.4.6 reshape2_1.4.4
## [67] glue_1.4.2 evaluate_0.14
## [69] BiocManager_1.30.10 vctrs_0.3.4
## [71] Rttf2pt1_1.3.8 gtable_0.3.0
## [73] purrr_0.3.4 tidyr_1.1.2
## [75] assertthat_0.2.1 xfun_0.18
## [77] rsvd_1.0.3 tibble_3.0.4
## [79] rvcheck_0.1.8 memoise_1.1.0
## [81] ellipsis_0.3.1

35 of 35 21-01-2021, 02:19 pm