The example is split into 2 Parts:
Part 1 must be completed first to create a file,
SNPs_cleaned.csv, that has been completely prepared for
analysis.
Now in Part 2, you will analyze the data with PCA. The steps here will be:
scale())prcomp())screeplot())vegan::scores())In the code below all code is provided. Your tasks will be to do 4 things:
Load the vcfR package with library()
library(vcfR) # KEY
##
## ***** *** vcfR *** *****
## This is vcfR 1.13.0
## browseVignettes('vcfR') # Documentation
## citation('vcfR') # Citation
## ***** ***** ***** *****
library(vegan)
## Loading required package: permute
## Loading required package: lattice
## This is vegan 2.6-4
library(ggplot2)
library(ggpubr)
Set the working directory
Load the data
SNPs_cleaned <- read.csv(file = "SNPs_cleaned.csv")
warning("If this didn't work, its may be because you didn't set your working directory.")
## Warning: If this didn't work, its may be because you didn't set your working
## directory.
TODO: Scale data using scale() function
SNPs_scaled <- scale(SNPs_cleaned)
TODO: Perform PCA analysis o scaled data using prcomp() function
pca_scaled <- prcomp(SNPs_scaled)
TODO: Put PCA data into a scree plot to see variance against number of principle components
TODO: UPDATE PLOT WITH TITLE
screeplot(pca_scaled,
ylab = "Relative importance",
main = "PCA variance")
TODO: PCA Diagnostics
TODO: Get summary of PCA data to explain variation
summary_out_scaled <- summary(pca_scaled)
PCA_variation <- function(pca_summary, PCs = 2){
var_explained <- pca_summary$importance[2,1:PCs]*100
var_explained <- round(var_explained,1)
return(var_explained)
}
var_out <- PCA_variation(summary_out_scaled,PCs = 10)
N_columns <- ncol(SNPs_scaled)
barplot(var_out,
main = "Percent variation Scree plot",
ylab = "Percent variation explained")
abline(h = 1/N_columns*100, col = 2, lwd = 2)
TODO: INTERPRET VARIANCE EXPLAINED
TODO: Make biplot to interpret the relationship between the features
biplot(pca_scaled)
TODO: This is a bad idea because it will make a very messy plot that is hard to read and understand
TODO: Get the scores
pca_scores <- vegan::scores(pca_scaled)
TODO: Create a vector with the Population ID
pop_id <- c("Nel","Nel","Nel","Nel","Nel","Nel","Nel","Nel",
"Nel", "Nel", "Nel", "Nel", "Nel", "Nel", "Nel", "Alt",
"Alt", "Alt", "Alt", "Alt", "Alt", "Alt", "Alt", "Alt",
"Alt", "Alt", "Alt", "Alt", "Alt", "Alt", "Sub", "Sub",
"Sub", "Sub", "Sub", "Sub", "Sub", "Sub", "Sub", "Sub",
"Sub", "Cau", "Cau", "Cau", "Cau", "Cau", "Cau", "Cau",
"Cau", "Cau", "Cau", "Cau", "Cau", "Div", "Div", "Div",
"Div", "Div", "Div", "Div", "Div", "Div", "Div", "Div",
"Div", "Div", "Div", "Div")
TODO: Combine scores and ID info into a dataframe
pca_scores2 <- data.frame(pop_id,
pca_scores)
TODO: Plot the scores with color coding
TODO: UPDATE PLOT WITH TITLE TODO: UPDATE X and Y AXES WITH AMOUNT OF VARIATION EXPLAINED
ggpubr::ggscatter(data = pca_scores2,
y = "PC2",
x = "PC1",
color = "pop_id",
shape = "pop_id",
xlab = "PC1 (20% variation)",
ylab = "PC2 (3% variation)",
main = "PCA Scatterplot")
TODO: INTERPRET PLOT