final_data

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)

list.files(pattern = "vcf")

## [1] "16.26712210-26952210.ALL.chr16_GRCh38.genotypes.20170504.vcf.gz"
## [2] "7.26000-266000.ALL.chr7_GRCh38.genotypes.20170504.vcf.gz"       
## [3] "vcf_num_df2.csv"                                                
## [4] "vcf_scaled.csv"

vcf_data <- vcfR::read.vcfR("16.26712210-26952210.ALL.chr16_GRCh38.genotypes.20170504.vcf.gz", convertNA = T)

## Scanning file to determine attributes.
## File attributes:
##   meta lines: 130
##   header_line: 131
##   variant count: 7941
##   column count: 2513
## 
Meta line 130 read in.
## All meta lines processed.
## gt matrix initialized.
## Character matrix gt created.
##   Character matrix gt rows: 7941
##   Character matrix gt cols: 2513
##   skip: 0
##   nrows: 7941
##   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: 7941
## All variants processed

vcf_data_genotype <- vcfR::extract.gt(vcf_data, 
           element = "GT",
           IDtoRowNames  = F,
           as.numeric = T,
           convertNA = T,
           )

vcf_data_genotype_t <- t(vcf_data_genotype)

vcf_data_genotype_df <- data.frame(vcf_data_genotype_t)

sample <- row.names(vcf_data_genotype_df)

vcf_data_genotype_df <- data.frame(sample, vcf_data_genotype_df)

Clean Data

meta_data <- read.csv(file = "1000genomes_people_info2-1.csv")

vcf_data_genotype_df_2 <- merge(meta_data, vcf_data_genotype_df, by = "sample")

invar

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)                      
}


vcf_data_no_invar <- data.frame(vcf_data_genotype_df_2[,c(1:6)],
                            invar_omit(vcf_data_genotype_df_2[,-c(1:6)]),
                            row.names = NULL)

## 1953 columns removed

find NA’s

find_NAs <- function(x){
  NAs_TF <- is.na(x)
  i_NA <- which(NAs_TF == TRUE)
  N_NA <- length(i_NA)
  # cat("Results:",N_NA, "NAs present\n.")
  return(i_NA)
}

N_rows <- nrow(vcf_data_no_invar)

N_NA <- rep(x = 0, times = N_rows)

N_SNPs <- ncol(vcf_data_no_invar)

for (i in 1:N_rows) {
  
  i_NA <- find_NAs(vcf_data_no_invar[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

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 = T)
    
    NAs_i <- which(is.na(column_i))
    
    N_NAs <- length(NAs_i)
    
    column_i[NAs_i] <- mean_i
    
    df[,i] <- column_i
  }
  return(df)
}

vcf_data_no_NA <- data.frame(vcf_data_no_invar[,c(1:6)],
                         mean_imputation(vcf_data_no_invar[,-c(1:6)]),
                         row.names = NULL)

vcf_scaled <- vcf_data_no_NA
vcf_scaled[,-c(1:6)] <-scale(vcf_data_no_NA[,-c(1:6)])

dim(vcf_scaled)

## [1] 2504 5994

write.csv(vcf_scaled, file = "Kodavali_cleaned.csv",
          row.names = F)