Final Project_workflow
Samantha Epstein
2022-11-29
Load necessary R packages
library(vcfR) ## Warning: package 'vcfR' was built under R version 4.2.2##
## ***** *** 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 2.6-2library(ggplot2)
library(ggpubr)
library(scatterplot3d)Confirm working directory and location of vcf file
getwd()## [1] "C:/Users/saman/Desktop/Comp Bio/Final Project"list.files()## [1] "1000genomes_people_info2-1.csv"
## [2] "5.17947992-18187992.ALL.chr5_GRCh38.genotypes.20170504.vcf.gz"
## [3] "Final Project.Rmd"
## [4] "Final Project.Rproj"
## [5] "Final_Project_Final_Report.Rmd"
## [6] "Final_Project_Workflow.Rmd"
## [7] "final_report_Epstein.Rmd"
## [8] "SNPs_cleaned.csv"
## [9] "vcf_num.csv"
## [10] "vcf_num_df.csv"
## [11] "vcf_num_df2.csv"
## [12] "vcf_scaled.csv"list.files(pattern = "vcf")## [1] "5.17947992-18187992.ALL.chr5_GRCh38.genotypes.20170504.vcf.gz"
## [2] "vcf_num.csv"
## [3] "vcf_num_df.csv"
## [4] "vcf_num_df2.csv"
## [5] "vcf_scaled.csv"Load vcf file
vcf <- vcfR::read.vcfR("5.17947992-18187992.ALL.chr5_GRCh38.genotypes.20170504.vcf.gz", convertNA = TRUE)## Scanning file to determine attributes.
## File attributes:
## meta lines: 130
## header_line: 131
## variant count: 7085
## column count: 2513
##
Meta line 130 read in.
## All meta lines processed.
## gt matrix initialized.
## Character matrix gt created.
## Character matrix gt rows: 7085
## Character matrix gt cols: 2513
## skip: 0
## nrows: 7085
## row_num: 0
##
Processed variant 1000
Processed variant 2000
Processed variant 3000
Processed variant 4000
Processed variant 5000
Processed variant 6000
Processed variant 7000
Processed variant: 7085
## All variants processedConvert vcf data to genotype scores
vcf_num <- vcfR::extract.gt(vcf,
element = "GT",
IDtoRowNames = F,
as.numeric = T,
convertNA = T,
return.alleles = F)Save this information into a csv file
write.csv(vcf_num, file = "vcf_num.csv", row.names = F)list.files## function (path = ".", pattern = NULL, all.files = FALSE, full.names = FALSE,
## recursive = FALSE, ignore.case = FALSE, include.dirs = FALSE,
## no.. = FALSE)
## .Internal(list.files(path, pattern, all.files, full.names, recursive,
## ignore.case, include.dirs, no..))
## <bytecode: 0x000001d46c41e9a8>
## <environment: namespace:base>Transpose data
vcf_num_t <- t(vcf_num)Convert into a dataframe
vcf_num_df <- data.frame(vcf_num_t)Get sample names
sample <- row.names(vcf_num_df)Add sample names to data frame
vcf_num_df <- data.frame(sample, vcf_num_df)Save to a csv file
getwd()## [1] "C:/Users/saman/Desktop/Comp Bio/Final Project"write.csv(vcf_num_df, file = "vcf_num_df.csv", row.names = F)list.files()## [1] "1000genomes_people_info2-1.csv"
## [2] "5.17947992-18187992.ALL.chr5_GRCh38.genotypes.20170504.vcf.gz"
## [3] "Final Project.Rmd"
## [4] "Final Project.Rproj"
## [5] "Final_Project_Final_Report.Rmd"
## [6] "Final_Project_Workflow.Rmd"
## [7] "final_report_Epstein.Rmd"
## [8] "SNPs_cleaned.csv"
## [9] "vcf_num.csv"
## [10] "vcf_num_df.csv"
## [11] "vcf_num_df2.csv"
## [12] "vcf_scaled.csv"Clean data
Merge data with population data
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"Save to a csv fle
getwd()## [1] "C:/Users/saman/Desktop/Comp Bio/Final Project"write.csv(vcf_num_df2, file = "vcf_num_df2.csv", row.names = F)Remove invariant features
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[, -c(1:6)]
vcf_noinvar <- invar_omit(vcf_noinvar)## Dataframe of dim 2504 7085 processed...
## 1745 columns removedvcf_noinvar <- data.frame(vcf_num_df2[, c(1:6)],
vcf_noinvar)
dim(vcf_noinvar)## [1] 2504 5346my_meta_N_invar_cols <- 1745Remove NAs
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)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] FALSEmean(percent_NA)## [1] 0my_meta_N_meanNA_rows <- mean(percent_NA)Mean imputation of NAs
mean_imputation <- function(df){
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" "X3" "X4" "X5"vcf_noNA <- vcf_noinvar[, -c(1:6)]
vcf_noNA <- mean_imputation(vcf_noNA)
vcf_noNA <- data.frame(vcf_noinvar[, c(1:6)],
vcf_noNA)
dim(vcf_noNA)## [1] 2504 5346Scale data
vcf_scaled <- vcf_noNA
vcf_scaled[ ,-c(1:6)] <- scale(vcf_scaled[, -c(1:6)])Save to a csv file
write.csv(vcf_scaled, file = "vcf_scaled.csv", row.names = F)Run PCA
vcf_pca <- prcomp(vcf_scaled[, -c(1:6)])View data with a scree plot
screeplot(vcf_pca)
Calculate explained variation
PCA_variation <- function(pca_summary, PCs = 2){
var_explained <- pca_summary$importance[2, 1:PCs]*100
var_explained <- round(var_explained, 3)
return(var_explained)
}vcf_pca_summary <- summary(vcf_pca)var_out <- PCA_variation(vcf_pca_summary, PCs = 500)Find PCs that exceed the cut off
N_columns <- ncol(vcf_scaled)
cut_off <- 1/N_columns*100i_cut_off <- which(var_out < cut_off)
i_cut_off <- min(i_cut_off)## Warning in min(i_cut_off): no non-missing arguments to min; returning Infmy_meta_N_meanNA_rowPCs <- i_cut_off
my_meta_var_PC123 <- var_out[c(1,2,3)]Plot percentages with a bar plot
barplot(var_out,
main = "Percent variation (%) Scree plot",
ylab = "Percent variation (%) explained",
names.arg = 1:length(var_out)
)
abline(h = cut_off, col = 2, lwd = 2)
abline(v = i_cut_off)
legend("topright",
col = c(2,1),
lty = c(1,1),
legend = c("Vertical line: cutoff",
"Horizontal line: 1st value below cut off")
)
Plot cumulative percentages
cumulative_variation <- cumsum(var_out)
plot(cumulative_variation, type = "l")
Calculate PCA scores
vcf_pca_scores <- vegan::scores(vcf_pca)
vcf_pca_scores2 <- data.frame(super_pop = vcf_noNA$super_pop, vcf_pca_scores)my_meta_var_PC123[1]## PC1
## 3.105my_meta_var_PC123[2]## PC2
## 1.67my_meta_var_PC123[3]## PC3
## 1.594Create scatter plots of scores
ggpubr::ggscatter(data = vcf_pca_scores2,
y = "PC2",
x = "PC1",
color = "super_pop",
shape = "super_pop",
main = "PCA Scatterplot",
xlab = "PC1 (3.105% of variation)",
ylab = "PC2 (1.67% of variation)"
)
ggpubr:: ggscatter(data = vcf_pca_scores2,
y = "PC3",
x = "PC2",
color = "super_pop",
shape = "super_pop",
main = "PCA Scatterplot",
xlab = "PC2 (1.67% of variation)",
ylab = "PC3 (1.594% of variation)"
)
ggpubr:: ggscatter(data = vcf_pca_scores2,
y = "PC3",
x = "PC1",
color = "super_pop",
shape = "super_pop",
main = "PCA Scatterplot",
xlab = "PC1 (3.105% of variation)",
ylab = "PC3 (1.594% of variation)"
)