## ----style, echo = FALSE, results = 'asis'------------------------------------ BiocStyle::markdown() ## ----options, include = FALSE------------------------------------------------- knitr::opts_chunk$set( collapse = TRUE, comment = "#>" ) ## ----setup-------------------------------------------------------------------- library(tidyGenR) ## ----------------------------------------------------------------------------- # download test raw data (if not downloaded) raw <- system.file("extdata", "raw", package = "tidyGenR") freads <- list.files(raw, pattern = "1.fastq", full.names = TRUE) rreads <- list.files(raw, pattern = "2.fastq", full.names = TRUE) ## ----primers------------------------------------------------------------------ # data.frame with primers data("primers") head(primers, 3) ## ----demultiplex, results = "hide", message=FALSE----------------------------- p_sh_out <- tempfile(fileext = ".sh") # demultiplex reads by locus using 3 primer pairs demultiplex( freads = freads, rreads = rreads, primers = primers[1:3, ], sh_out = p_sh_out, run = FALSE ) ## ----cutadapt_script---------------------------------------------------------- readLines(p_sh_out) ## ----truncate_one_locus------------------------------------------------------- # Download per-locus demultiplexed FASTQ dem <- system.file("extdata", "demultiplexed", package = "tidyGenR") # truncate reads for one locus p_trun <- file.path(tempdir(), "truncated") one_locus <- trunc_amp( loci = "chrna9", mode_trun = "pe", in_dir = dem, fw_pattern = "1.fastq.gz", rv_pattern = "2.fastq.gz", trunc_fr = c(250, 180), max_ee = c(3, 3), outdir = p_trun ) ## ----trunc_fr----------------------------------------------------------------- # dataframe with locus-specific truncation lengths data("trunc_fr") head(trunc_fr, 3) ## ----truncate_all_loci, results="hide", message=FALSE------------------------- # truncate reads for all loci using locus-specific truncation lengths all_loci <- trunc_amp( mode_trun = "pe", in_dir = dem, fw_pattern = "1.fastq.gz", rv_pattern = "2.fastq.gz", trunc_fr = trunc_fr, max_ee = c(3, 3), outdir = p_trun ) ## ----truncated_fastq---------------------------------------------------------- head(list.files(p_trun)) ## ----trunc_in_out------------------------------------------------------------- head(all_loci, 3) ## ----variant_calling, message=FALSE, results="hide"--------------------------- variants <- variant_call(in_dir = p_trun) head(variants) ## ----head_variants------------------------------------------------------------ head(variants) ## ----genotype, message = FALSE------------------------------------------------ genotypes <- genotype(variants, ADt = 10, ploidy = 2) head(genotypes)