config.yml

# List of SRA run ids to analyse, and corresponding GSM ids.
sample_ids: ["SRR935090","SRR935091","SRR935092"]
sample_ids_geo: ["GSM1186459", "GSM1186460", "GSM1186461"]
series_id_geo: "GSE48896"

# URLs to gzipped fastq files for each sample in remote repository
samples:
  SRR935090: "https://figshare.scilifelab.se/ndownloader/files/39539767"
  SRR935091: "https://figshare.scilifelab.se/ndownloader/files/39539770"
  SRR935092: "https://figshare.scilifelab.se/ndownloader/files/39539773"

# Maximal number of reads to retrieve for each run. This is to reduce the time
# and space needed for this tutorial. The maximum number of reads is 100000
# which is the total number of reads available in the subsampled files we
# are using for this course
max_reads: 50000

# Genome id to align to. Should match with an entry in "genomes" below.
genome_id: ST398

# Dictionary with genomes that can be aligned against. Here we have added
# NCTC8325, which is the strain used in the study, and ST398, which is primarily
# associated with cattle but that can infect humans.
genomes:
  NCTC8325:
    fasta: ftp://ftp.ensemblgenomes.org/pub/bacteria/release-37/fasta/bacteria_18_collection/staphylococcus_aureus_subsp_aureus_nctc_8325/dna//Staphylococcus_aureus_subsp_aureus_nctc_8325.ASM1342v1.dna_rm.toplevel.fa.gz
    gff3: ftp://ftp.ensemblgenomes.org/pub/bacteria/release-37/gff3/bacteria_18_collection/staphylococcus_aureus_subsp_aureus_nctc_8325//Staphylococcus_aureus_subsp_aureus_nctc_8325.ASM1342v1.37.gff3.gz
  ST398:
    fasta: ftp://ftp.ensemblgenomes.org/pub/bacteria/release-37/fasta/bacteria_18_collection//staphylococcus_aureus_subsp_aureus_st398/dna/Staphylococcus_aureus_subsp_aureus_st398.ASM958v1.dna.toplevel.fa.gz
    gff3: ftp://ftp.ensemblgenomes.org/pub/bacteria/release-37/gff3/bacteria_18_collection/staphylococcus_aureus_subsp_aureus_st398//Staphylococcus_aureus_subsp_aureus_st398.ASM958v1.37.gff3.gz