2.1 Create data matrices for CpG-SNP analysis

To illustrate this type of analysis we produce the following artificial files.

• CpG_locations.* – filematrix with the location of the SNP-CpGs.
  It has two columns with integer values – chromosome number and location (chr and position).
• CpG_chromosome_names.txt – file with chromosome names (factor levels) for the integer column chr in the location filematrix.
• Coverage.* – filematrix with the data for all samples and all locations.
  Each row has data for a single sample. Row names are sample names.
  Each column has data for a single location. Columns match rows of the location filematrix.
• SNPs.* – filematrix with genotype data, matching the coverage matrix.

First, we load the package and set up a working directory. The project directory dr can be set to a more convenient location when running the code.

library(ramwas)

# work in a temporary directory
dr = paste0(tempdir(), "/simulated_matrix_data")
dir.create(dr, showWarnings = FALSE)
cat(dr,"\n")

## /tmp/RtmpGaPsUu/simulated_matrix_data

Let the sample data matrix have 200 samples and 100,000 variables.

nsamples = 200
nvariables = 100000

For these 200 samples we generate a data frame with age and sex phenotypes and a batch effect covariate.

covariates = data.frame(
    sample = paste0("Sample_",seq_len(nsamples)),
    sex = seq_len(nsamples) %% 2,
    age = runif(nsamples, min = 20, max = 80),
    batch = paste0("batch",(seq_len(nsamples) %% 3))
)
pander(head(covariates))

Next, we create the genomic locations for 100,000 variables.

temp = cumsum(sample(20e7 / nvariables, nvariables, replace = TRUE) + 0)
chr      = as.integer(temp %/% 1e7) + 1L
position = as.integer(temp %% 1e7)

locmat = cbind(chr = chr, position = position)
chrnames = paste0("chr", 1:10)
pander(head(locmat))

Now we save locations in a filematrix and create a text file with chromosome names.

fmloc = fm.create.from.matrix(
            filenamebase = paste0(dr, "/CpG_locations"),
            mat = locmat)
close(fmloc)
writeLines(con = paste0(dr, "/CpG_chromosome_names.txt"), text = chrnames)

Finally, we create methylation and SNP matrices and populate them.

fmm = fm.create(paste0(dr,"/Coverage"), nrow = nsamples, ncol = nvariables)
fms = fm.create(paste0(dr,"/SNPs"), nrow = nsamples, ncol = nvariables,
                size = 1, type = "integer")

# Row names of the matrices are set to sample names
rownames(fmm) = as.character(covariates$sample)
rownames(fms) = as.character(covariates$sample)

# The matrices are filled, 2000 variables at a time
byrows = 2000
for( i in seq_len(nvariables/byrows) ){ # i=1
    ind = (1:byrows) + byrows*(i-1)

    snps = rbinom(n = byrows * nsamples, size = 2, prob = 0.2)
    dim(snps) = c(nsamples, byrows)
    fms[,ind] = snps

    slice = double(nsamples*byrows)
    dim(slice) = c(nsamples, byrows)
    slice[,  1:225] = slice[,  1:225] + covariates$sex / 50 / sd(covariates$sex)
    slice[,101:116] = slice[,101:116] + covariates$age / 16 / sd(covariates$age)
    slice = slice +
                ((as.integer(factor(covariates$batch))+i) %% 3) / 200 +
                snps / 1.5 +
                runif(nsamples*byrows) / 2
    fmm[,ind] = slice
}
close(fms)
close(fmm)