inst/doc/mergingbd5files.R

In BinaryDosage: Creates, Merges, and Reads Binary Dosage Files

## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

## ----setup, echo = FALSE------------------------------------------------------
library(BinaryDosage)

## ----setup_files, message = FALSE, warning = FALSE----------------------------
bdose_full <- file.path(tempdir(), "full.bdose")

if (requireNamespace("vcfppR", quietly = TRUE)) {
  vcftobd(vcffile    = system.file("extdata", "set1a.vcf.gz", package = "BinaryDosage"),
          bdose_file = bdose_full)
} else {
  updatebd(bdfiles    = system.file("extdata", "vcf1a.bdose", package = "BinaryDosage"),
           bdose_file = bdose_full)
}
bd_full <- getbdinfo(bdose_full)

cat("Subjects:", nrow(bd_full$samples), "\n")
cat("SNPs:    ", nrow(bd_full$snps),    "\n")

## ----subject_merge, message = FALSE, warning = FALSE--------------------------
bdose_a   <- file.path(tempdir(), "set_a.bdose")
bdose_b   <- file.path(tempdir(), "set_b.bdose")
bdose_out <- file.path(tempdir(), "merged_subjects.bdose")

sids <- bd_full$samples$sid

subsetbd(bdfiles    = bdose_full,
         bdose_file = bdose_a,
         subjectids = sids[1:30])

subsetbd(bdfiles    = bdose_full,
         bdose_file = bdose_b,
         subjectids = sids[31:60])

mergebd(bdose_files = c(bdose_a, bdose_b),
        bdose_file  = bdose_out)

bd_a   <- getbdinfo(bdose_a)
bd_b   <- getbdinfo(bdose_b)
bd_out <- getbdinfo(bdose_out)

cat("File A subjects:", nrow(bd_a$samples),   "\n")
cat("File B subjects:", nrow(bd_b$samples),   "\n")
cat("Merged subjects:", nrow(bd_out$samples), "\n")
cat("Merged SNPs:    ", nrow(bd_out$snps),    "\n")

## ----subject_order------------------------------------------------------------
knitr::kable(bd_out$samples, caption = "Subjects in merged file")

## ----snp_merge, message = FALSE, warning = FALSE------------------------------
bdose_snp_a   <- file.path(tempdir(), "snp_a.bdose")
bdose_snp_b   <- file.path(tempdir(), "snp_b.bdose")
bdose_snp_out <- file.path(tempdir(), "merged_snps.bdose")

locs <- bd_full$snps$location

subsetbd(bdfiles    = bdose_full,
         bdose_file = bdose_snp_a,
         locations  = locs[1:5])

subsetbd(bdfiles    = bdose_full,
         bdose_file = bdose_snp_b,
         locations  = locs[6:10])

mergebd(bdose_files = c(bdose_snp_a, bdose_snp_b),
        bdose_file  = bdose_snp_out)

bd_snp_a   <- getbdinfo(bdose_snp_a)
bd_snp_b   <- getbdinfo(bdose_snp_b)
bd_snp_out <- getbdinfo(bdose_snp_out)

cat("File A SNPs:    ", nrow(bd_snp_a$snps),   "\n")
cat("File B SNPs:    ", nrow(bd_snp_b$snps),   "\n")
cat("Merged SNPs:    ", nrow(bd_snp_out$snps),  "\n")
cat("Merged subjects:", nrow(bd_snp_out$samples), "\n")

## ----snp_order----------------------------------------------------------------
knitr::kable(bd_snp_out$snps, caption = "SNPs in merged file")

## ----cleanup, include = FALSE-------------------------------------------------
unlink(c(bdose_full,    paste0(bdose_full,    ".bdi"),
         bdose_a,       paste0(bdose_a,       ".bdi"),
         bdose_b,       paste0(bdose_b,       ".bdi"),
         bdose_out,     paste0(bdose_out,     ".bdi"),
         bdose_snp_a,   paste0(bdose_snp_a,   ".bdi"),
         bdose_snp_b,   paste0(bdose_snp_b,   ".bdi"),
         bdose_snp_out, paste0(bdose_snp_out, ".bdi")))