These exercises follow the material in the GitHub section of Reproducible R.

  1. Lets setup an environment to do some basic counting for RNAseq. We will follow the example in the salmon guide, but we will modify it for S. cerevisiae to make it quicker as the genomes smaller.
library(Herper)
install_CondaTools(tools = "salmon", env = "rnaseq")

download.file("http://ftp.ensemblgenomes.org/pub/fungi/release-56/fasta/saccharomyces_cerevisiae/cdna/Saccharomyces_cerevisiae.R64-1-1.cdna.all.fa.gz", "~/Desktop/Saccharomyces_cerevisiae.R64.fa.gz")

with_CondaEnv(new = "rnaseq", code = system2("salmon", c("index", 
                                                         "-t", "~/Desktop/Saccharomyces_cerevisiae.R64.fa.gz",
                                                         "-i", "~/Desktop/Saccharomyces_cerevisiae.R64_index")))

download.file("ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR180/065/SRR18072865/SRR18072865_1.fastq.gz", "~/Desktop/yeast_fastq.fastq.qz")

with_CondaEnv(new = "rnaseq", code = system2("salmon", c("quant",
                                                         "-i", "~/Desktop/Saccharomyces_cerevisiae.R64_index",
                                                         "-l", "A",
                                                         "-r", "~/Desktop/yeast_fastq.fastq.qz",
                                                         "-p", "8",
                                                         "--validateMappings",
                                                         "-o", "~/Desktop/yeast_quant")))

export_CondaEnv("rnaseq", "~/Desktop/my_yeast_salmon_conda_envrionment.yml")