## S6 Text

# Set seed for reproducing the data
set.seed(12345)

# Simulating artificial SNPs with their genotypes (independent variables) 1400 SNPs, and 460 subjects
df_SNPs <- data.frame(replicate(1400, sample(1:3, 460, rep=TRUE))) 

# Simulating response variable (phenotype); normally distributed.
yres_phen <- rnorm(460)

# Combining the response variable and SNPs, i.e, adding a new column to the above created data frame of SNPs (df_SNPs)
df_SNPs["phenotype"] <- yres_phen
df_SNPs_yres_phen <- df_SNPs[, 1:ncol(df_SNPs)]

# Viewing the few first rows and columns of the created data frame
head(df_SNPs_yres_phen[,c(1:4,1401)])