library(vcfR)
##
## ***** *** 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)
getwd()
## [1] "/Users/omchauhan/Documents/my snps"
list.files()
## [1] "1000genomes_people_info2-1.csv"
## [2] "2.136483646-136733646.ALL.chr2_GRCh38.genotypes.20170504.vcf.gz"
## [3] "9.36073098-36313098.ALL.chr9_GRCh38.genotypes.20170504.vcf"
## [4] "9.36073098-36313098.ALL.chr9_GRCh38.genotypes.20170504.vcf.gz"
## [5] "Final Project.Rmd"
## [6] "final_report_template.html"
## [7] "final_report_template.rmd"
## [8] "final-practice-soln-flat-4 (1).pdf"
## [9] "final-practice-soln-flat-4.pdf"
## [10] "Final-Project.html"
## [11] "Final-Project.Rmd"
## [12] "fst_exploration_in_class.html"
## [13] "fst_exploration_in_class.rmd"
## [14] "my snps.Rproj"
## [15] "rsconnect"
## [16] "RSVP_Breakfast_for_Dinner_Flyer.pdf"
## [17] "vcf_num_df.csv"
## [18] "vcf_num_df2.csv"
## [19] "vcf_num.csv"
## [20] "vcf_scaled.csv"
list.files(pattern = "vcf")
## [1] "2.136483646-136733646.ALL.chr2_GRCh38.genotypes.20170504.vcf.gz"
## [2] "9.36073098-36313098.ALL.chr9_GRCh38.genotypes.20170504.vcf"
## [3] "9.36073098-36313098.ALL.chr9_GRCh38.genotypes.20170504.vcf.gz"
## [4] "vcf_num_df.csv"
## [5] "vcf_num_df2.csv"
## [6] "vcf_num.csv"
## [7] "vcf_scaled.csv"
my_vcf <- "9.36073098-36313098.ALL.chr9_GRCh38.genotypes.20170504.vcf.gz"
vcf <- vcfR::read.vcfR(my_vcf, convertNA = T)
## Scanning file to determine attributes.
## File attributes:
## meta lines: 130
## header_line: 131
## variant count: 6984
## column count: 2513
##
Meta line 130 read in.
## All meta lines processed.
## gt matrix initialized.
## Character matrix gt created.
## Character matrix gt rows: 6984
## Character matrix gt cols: 2513
## skip: 0
## nrows: 6984
## row_num: 0
##
Processed variant 1000
Processed variant 2000
Processed variant 3000
Processed variant 4000
Processed variant 5000
Processed variant 6000
Processed variant: 6984
## All variants processed
vcf_num <- vcfR::extract.gt(vcf,
element = "GT",
IDtoRowNames = F,
as.numeric = T,
convertNA = T)
write.csv(vcf_num, file = "vcf_num.csv", row.names = F)
vcf_num_t <- t(vcf_num)
vcf_num_df <- data.frame(vcf_num_t)
sample <- row.names(vcf_num_df)
vcf_num_df <- data.frame(sample, vcf_num_df)
getwd()
## [1] "/Users/omchauhan/Documents/my snps"
write.csv(vcf_num_df,
file = "vcf_num_df.csv",
row.names = F)
pop_meta <- read.csv(file = "1000genomes_people_info2-1.csv")
names(pop_meta)
## [1] "pop" "super_pop" "sample" "sex" "lat" "lng"
names(vcf_num_df)[1:10]
## [1] "sample" "X1" "X2" "X3" "X4" "X5" "X6" "X7"
## [9] "X8" "X9"
vcf_num_df2 <- merge(pop_meta,
vcf_num_df,
by = "sample")
nrow(vcf_num_df) == nrow(vcf_num_df2)
## [1] TRUE
names(vcf_num_df)[1:15]
## [1] "sample" "X1" "X2" "X3" "X4" "X5" "X6" "X7"
## [9] "X8" "X9" "X10" "X11" "X12" "X13" "X14"
getwd()
## [1] "/Users/omchauhan/Documents/my snps"
write.csv(vcf_num_df2, file = "vcf_num_df2.csv", row.names = F)
invar_omit <- function(x){
cat("Dataframe of dim", dim(x), "processed ...\n")
sds <- apply(x, 2, sd, na.rm = TRUE)
i_var0 <- which(sds == 0)
cat(length(i_var0), "columns removed\n")
if(length(i_var0) > 0){
x <- x[, -i_var0]
}
return(x)
}
names(vcf_num_df2)[1:10]
## [1] "sample" "pop" "super_pop" "sex" "lat" "lng"
## [7] "X1" "X2" "X3" "X4"
vcf_noinvar <- vcf_num_df2
vcf_noinvar[, -c(1:6)] <- invar_omit(vcf_noinvar[, -c(1:6)])
## Dataframe of dim 2504 6984 processed ...
## 1655 columns removed
my_meta_N_invar_cols <- 306
find_NAs <- function(x){
NAs_TF <- is.na(x)
i_NA <- which(NAs_TF == TRUE)
N_NA <- length(i_NA)
return(i_NA)
}
N_rows <- nrow(vcf_noinvar)
N_NA <- rep(x = 0, times = N_rows)
N_SNPs <- ncol(vcf_noinvar)
cat("This may take a minute..")
## This may take a minute..
for(i in 1:N_rows){
i_NA <- find_NAs(vcf_noinvar[i,])
N_NA_i <- length(i_NA)
N_NA[i] <- N_NA_i
}
cutoff50 <- N_SNPs*0.5
percent_NA <- N_NA/N_SNPs*100
any(percent_NA > 50)
## [1] FALSE
mean(percent_NA)
## [1] 0
my_meta_N_meanNA_rows <- mean(percent_NA)
mean_imputation <- function(df){
cat("This may take some time...")
n_cols <- ncol(df)
for(i in 1:n_cols){
column_i <- df[,i]
mean_i <- mean(column_i, na.rm = TRUE)
NAs_i <- which(is.na(column_i))
N_NAs <- length(NAs_i)
column_i[NAs_i] <- mean_i
df[,i] <- column_i
}
return(df)
}
names(vcf_noinvar)[1:10]
## [1] "sample" "pop" "super_pop" "sex" "lat" "lng"
## [7] "X1" "X2" "X3" "X4"
vcf_noNA <- vcf_noinvar
vcf_noNA[,-c(1:6)] <- mean_imputation(vcf_noinvar[,-c(1:6)])
## This may take some time...
vcf_scaled <- vcf_noNA
vcf_scaled[,-c(1:6)] <- scale(vcf_noNA[,-c(1:6)])
write.csv(vcf_scaled, file = "vcf_scaled.csv", row.names = F)
vcf_pca <- prcomp(vcf_scaled[,-c(1:6)])
screeplot(vcf_pca)
PCA_variation <- function(pca_summary, PCs = 2){
var_explained <- pca_summary$importance[2,1:PCs]*100
var_explained <- round(var_explained,3)
return(var_explained)
}
vcf_pca_summary <- summary(vcf_pca)
var_out <- PCA_variation(vcf_pca_summary,
PCs = 500)
N_columns <- ncol(vcf_scaled)
cut_off <- 1/N_columns*100
i_cut_off <- which(var_out < cut_off)
i_cut_off <- min(i_cut_off)
## Warning in min(i_cut_off): no non-missing arguments to min; returning Inf
my_meta_N_meanNA_rowsPCs <- i_cut_off
my_meta_var_PC123 <- var_out[c(1,2,3)]
barplot(var_out,
main = "Percent variation (%) Scree plot",
ylab = "Percent variation (%) explained",
names.arg = 1:length(var_out))
abline(h = cut_off, col = 2, lwd = 2)
abline(v = i_cut_off)
legend("topright",
col = c(2,1),
lty = c(1,1),
legend = c("Vertical line: cutoff",
"Horizontal line: 1st value below cut off"))
cumulative_variation <- cumsum(var_out)
plot(cumulative_variation, type = "l")
vcf_pca_scores <- vegan::scores(vcf_pca)
vcf_pca_scores2 <- data.frame(super_pop = vcf_noNA$super_pop,
vcf_pca_scores)
my_meta_var_PC123[1]
## PC1
## 3.672
my_meta_var_PC123[2]
## PC2
## 2.23
ggpubr::ggscatter(data = vcf_pca_scores2,
y = "PC2",
x = "PC1",
color = "super_pop",
shape = "super_pop",
main = "PCA Scatterplot",
xlab = "PC1 (1.5% of variation)",
ylab = "PC2 (1.1% of variation)")
ggpubr::ggscatter(data = vcf_pca_scores2,
y = "PC3",
x = "PC2",
color = "super_pop",
shape = "super_pop",
main = "PCA Scatterplot",
xlab = "PC2 (1.1% of variation)",
ylab = "PC3 (1.05% of variation")
ggpubr::ggscatter(data = vcf_pca_scores2,
y = "PC3",
x = "PC1",
color = "super_pop",
shape = "super_pop",
main = "PCA Scatterplot",
xlab = "PC1 (1.5% of variation)",
ylab = "PC3 (1.05% of variation")
