workflow
2022-12-17
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
install.packages("vcfR",
repos = "https://cloud.r-project.org")##
## The downloaded binary packages are in
## /var/folders/hn/6wgsl4wd7pv6vl38d9t06tnr0000gn/T//RtmpVM5WVZ/downloaded_packageslibrary(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 2.6-4library(ggplot2)
library(ggpubr)getwd()## [1] "/Users/adetayoadenekan/Downloads"list.files(pattern="vcf")## [1] "1.159051856-159301856.ALL.chr1_GRCh38.genotypes.20170504.vcf.gz"
## [2] "11.47816134-48056134.ALL.chr11_GRCh38.genotypes.20170504.vcf.gz"
## [3] "2.136483646-136733646.ALL.chr2_GRCh38.genotypes.20170504.vcf.gz"
## [4] "all_loci-1.vcf"
## [5] "all_loci.vcf"
## [6] "code_checkpoint_vcfR.html"
## [7] "code_checkpoint_vcfR.Rmd"
## [8] "my_final_genomes.vcf.gz"
## [9] "vcf_num_df.csv"
## [10] "vcf_num_df2.csv"
## [11] "vcf_num.csv"
## [12] "vcf_scaled.csv"
## [13] "vcf-num_df.csv"
## [14] "vcfR_test.vcf"
## [15] "vcfR_test.vcf.gz"my_vcf<-"my_final_genomes.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: 6238
## column count: 2513
##
Meta line 130 read in.
## All meta lines processed.
## gt matrix initialized.
## Character matrix gt created.
## Character matrix gt rows: 6238
## Character matrix gt cols: 2513
## skip: 0
## nrows: 6238
## row_num: 0
##
Processed variant 1000
Processed variant 2000
Processed variant 3000
Processed variant 4000
Processed variant 5000
Processed variant 6000
Processed variant: 6238
## All variants processedvcf_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)list.files(pattern="vcf_num")## [1] "vcf_num_df.csv" "vcf_num_df2.csv" "vcf_num.csv"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/adetayoadenekan/Downloads"write.csv(vcf_num_df, file="vcf_num_df.csv", row.names=F)list.files(pattern="vcf_num_df.csv")## [1] "vcf_num_df.csv"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] TRUEnames(vcf_num_df2)[1:15]## [1] "sample" "pop" "super_pop" "sex" "lat" "lng"
## [7] "X1" "X2" "X3" "X4" "X5" "X6"
## [13] "X7" "X8" "X9"getwd()## [1] "/Users/adetayoadenekan/Downloads"write.csv(vcf_num_df2, file="vcf_num_df2.csv", row.names=F)
list.files(pattern= "vcf_num_df2.csv")## [1] "vcf_num_df2.csv"invar_omit<-function(x){
cat("Dataframe of dim", dim(x), "processed...\n")
sds<-apply(x,2,sd,na.rm=T)
i_var0<- which(sds==0)
}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]
}
## add return() with x in it
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 6238 processed...
## 1719 columns removedmy_meta_N_invar_cols <- 1719find_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)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] FALSEmy_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",
col.names = F)## Warning in write.csv(vcf_scaled, file = "vcf_scaled.csv", col.names = F):
## attempt to set 'col.names' ignoredvcf_pca <- prcomp(vcf_scaled[,-c(1:6)])
screeplot(vcf_pca)
PCA_variation <- function(pca_summary, PCs = 2){
var_explained <- pca_summary$importance[2,1:PCs]*100
var_explained <- round(var_explained, 3)
return(var_explained)
}PCA_variation <- function(pca_summary, PCs = 2){
var_explained <- pca_summary$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 Infmy_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)
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
## 2.891my_meta_var_PC123[2]## PC2
## 2.659ggpubr::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")
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)")