biodata.yaml

---
# Configuration file defining biological data to retrieve and install.
# These are stored in an Amazon S3 bucket:
# https://s3.amazonaws.com/biodata
# and retrieved using the data_fabfile Fabric script.

# ## Genome data -- Next generation sequencing and Galaxy

# Details about the genomes you want to include.
#  Required genome fields (corresponding to Galaxy's tool_data_table_conf.xml columns):
#    dbkey   - globally unique identifier for the genome (e.g., hg19)
#    name    - descriptive name for the given genome (to be displayed in Galaxy, e.g., Hsapiens)
#  Optional genome fields (corresponding to Galaxy's tool_data_table_conf.xml columns):
#    formats, species, dbkey1, dbkey2, value, path, index
#  Additional genome fields specific to data deployment:
#    genome_indexes - list of tool indexes specific to the associated genome (overrides global 'genome_indexes')
genomes:
  - dbkey: phix
    name: phiX174
  - dbkey: hg19
    name: Human (hg19)
    dbsnp: true
    rnaseq: true
  - dbkey: GRCh37
    name: Human (GRCh37)
    dbsnp: true
  - dbkey: dm3
    name: D melangogaster (dm3)
  - dbkey: mm10
    name: Mouse (mm10)
    dbsnp: true
    rnaseq: true
  - dbkey: mm9
    name: Mouse (mm9)
    rnaseq: true
  - dbkey: araTha_tair9
    name: Arabidopsis thaliana (TAIR9)
  # - dbkey: xenTro2
  #   name: X tropicalis (frog)
  - dbkey: sacCer2
    name: S cerevisiae (yeast)
  # - dbkey: WS210
  #   name: C elegans (WS210)
  # Build these
  # - dbkey: danRer6
  #   name: Zebrafish (Danio rerio)
  # - dbkey: apiMel3
  #   name: Honey bee (A mellifera)

# Global set of indexes to include for each genome.
# Available choices are in GENOMES_INDEXES_SUPPORTED in data_fabfile.py
genome_indexes:
  - bowtie
  # For the time being, bowtie2 has only mm10, hg19 & GRCh37 genomes
  # - bowtie2
  - bwa
  - novoalign
  - ucsc

# Additional data targets
install_liftover: false
install_uniref: false