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/harshitakadiyala/Documents/BIOSC 1540/MyPortfolio"
list.files(pattern = "vcf")
## [1] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf"
## [2] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf.gz"
## [3] "vcf_num_df.csv"
## [4] "vcf_num_df2.csv"
## [5] "vcf_num.csv"
my_vcf <- "8.37585180-37825180.ALL.chr8_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: 6771
## column count: 2513
##
Meta line 130 read in.
## All meta lines processed.
## gt matrix initialized.
## Character matrix gt created.
## Character matrix gt rows: 6771
## Character matrix gt cols: 2513
## skip: 0
## nrows: 6771
## row_num: 0
##
Processed variant 1000
Processed variant 2000
Processed variant 3000
Processed variant 4000
Processed variant 5000
Processed variant 6000
Processed variant: 6771
## 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)
list.files()
## [1] "1000genomes_people_info2-1 (1).csv"
## [2] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf"
## [3] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf.gz"
## [4] "final_report.html"
## [5] "final_report.Rmd"
## [6] "gwas_pheno_env.csv"
## [7] "my_portfolio.csv"
## [8] "MyPortfolio.Rproj"
## [9] "pheno.csv"
## [10] "rsconnect"
## [11] "vcf_num_df.csv"
## [12] "vcf_num_df2.csv"
## [13] "vcf_num.csv"
## [14] "Workflow.html"
## [15] "Workflow.Rmd"
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/harshitakadiyala/Documents/BIOSC 1540/MyPortfolio"
write.csv(vcf_num_df,
file = "vcf_num_df.csv",
row.names = F)
list.files()
## [1] "1000genomes_people_info2-1 (1).csv"
## [2] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf"
## [3] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf.gz"
## [4] "final_report.html"
## [5] "final_report.Rmd"
## [6] "gwas_pheno_env.csv"
## [7] "my_portfolio.csv"
## [8] "MyPortfolio.Rproj"
## [9] "pheno.csv"
## [10] "rsconnect"
## [11] "vcf_num_df.csv"
## [12] "vcf_num_df2.csv"
## [13] "vcf_num.csv"
## [14] "Workflow.html"
## [15] "Workflow.Rmd"
pop_meta <- read.csv(file = "1000genomes_people_info2-1 (1).csv")
names(pop_meta)
## [1] "pop" "super_pop" "sample" "sex" "lat" "lng"
vcf_num_df2 <- merge(pop_meta,
vcf_num_df,
by = "sample")
nrow(vcf_num_df) == nrow(vcf_num_df2)
## [1] TRUE
names(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/harshitakadiyala/Documents/BIOSC 1540/MyPortfolio"
write.csv(vcf_num_df2, file = "vcf_num_df2.csv", row.names = F)
list.files()
## [1] "1000genomes_people_info2-1 (1).csv"
## [2] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf"
## [3] "8.37585180-37825180.ALL.chr8_GRCh38.genotypes.20170504.vcf.gz"
## [4] "final_report.html"
## [5] "final_report.Rmd"
## [6] "gwas_pheno_env.csv"
## [7] "my_portfolio.csv"
## [8] "MyPortfolio.Rproj"
## [9] "pheno.csv"
## [10] "rsconnect"
## [11] "vcf_num_df.csv"
## [12] "vcf_num_df2.csv"
## [13] "vcf_num.csv"
## [14] "Workflow.html"
## [15] "Workflow.Rmd"
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 6771 processed...
## 1770 columns removed
my_meta_N_invar_cols <- 1770
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)
N_rows <- nrow(vcf_num_t)
N_NA <- rep(x = 0, times = N_rows)
N_SNPs <- ncol(vcf_num_t)
for(i in 1:N_rows){
i_NA <- find_NAs(vcf_num_t[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] 0.002748519
my_meta_N_meanNA_rows <- mean(percent_NA)
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" "X2" "X3" "X4"
vcf_noNA <- vcf_noinvar
vcf_noNA[, -c(1:6)] <- mean_imputation(vcf_noinvar[, -c(1:6)])
vcf_scaled <- vcf_noNA
vcf_scaled[, -c(1:6)] <- scale(vcf_noNA[, -c(1:6)])
write.csv(vcf_noNA, file = "my_portfolio.csv",
row.names = F)
list.files(pattern = ".csv")
## [1] "1000genomes_people_info2-1 (1).csv" "gwas_pheno_env.csv"
## [3] "my_portfolio.csv" "pheno.csv"
## [5] "vcf_num_df.csv" "vcf_num_df2.csv"
## [7] "vcf_num.csv"