config.automator.yaml

###############################################################################
# Len Taing 2019 (TGBTG)
###############################################################################
# Automator configuration file
###############################################################################

# Give the new instance a unique name, e.g. the wes run name
# NOTE: "wes-auto" will automatically be prepended to this string
instance_name: "test1"

# Define the number of cores for the wes instance
# Options- 32 (default), 64, 96 
cores: 32

# Define the disk size to use in GB, default 500
# the name of the persistent disk will be: "wes_auto_{instance_name}_disk"
disk_size: 500

# Path to sentieon binary
# Uncomment and define the sentieon path to use--otherwise 
# sentieon-genomics-202010.01 is used by default
#sentieon_path: "/home/taing/sentieon/sentieon-genomics-202010.01/bin/"

#DEFINE the path to the google bucket path for the run
google_bucket_path: gs://mybucket/

# Uncomment the following and define the specific wes commit string to use
# wes_commit: "develop"

#Uncomment the following and define the specific wes GCP image to use
#NOTE: IF a specific GCP image is not set via config['image'], then
#the default behavior is to get the latest wes image
image: wes-ver2-26a

#Define the wes reference snapshot to use, default wes-ref-ver1-0
wes_ref_snapshot: 'wes-human-ref-ver1-6a'

# SOMATIC CALLER to use, options are {tnsnv, tnhaplotyper2, tnscope}
# tnscope is the default EVEN if the somatic_caller param is NOT defined
somatic_caller: tnscope

# CIMAC center: choices are {'mocha', 'mda', 'broad' (default)}
cimac_center: 'broad'

# Trim soft clip reads when calling somatic variants? False (default)
# NOT available for tnsnv
trim_soft_clip: False

# tumor_only - IF the normal sample is NOT available, then set this flag to
# be True by uncommenting the line below.
# Also make sure that the normal samples in the metasheet are empty.
#
# Default: tumor_only: False
tumor_only: False

# DEFINE the samples- each sample should have a name, e.g. SAMPLE1
# and a Google bucket path to the input file, 
# e.g. gs://mybucket/data/sample1.fastq.gz
# VALID INPUTS: fastq, fastq.gz
# NOTE: for PAIRED-END fastq/fastq.gz, give both pairs to the sample:
# SAMPLE_1_PE:
#   - gs://mybucket/data/sample1_pair1.fastq
#   - gs://mybucket/data/sample1_pair2.fastq
samples:
  mocha2-Run1-pt1-Normal:
    - gs://mybucket/data/R1-1-N_HHTFLDSXX_R1.fastq.gz
    - gs://mybucket/data/R1-1-N_HHTFLDSXX_R2.fastq.gz
  mocha2-Run1-pt1-FF-Tumor:
    - gs://mybucket/data/R1-1-F_HHTFLDSXX_R1.fastq.gz
    - gs://mybucket/data/R1-1-F_HHTFLDSXX_R2.fastq.gz
  mocha2-Run1-pt1-FFPE-Tumor:
    - gs://mybucket/data/R1-1-FP_HHTFLDSXX_R1.fastq.gz
    - gs://mybucket/data/R1-1-FP_HHTFLDSXX_R2.fastq.gz

# metahseet- Group the samples into Tumor/Normal "runs"
# each run should have a name, e.g. run_1:
# then under each run, define a tumor and a normal sample
# EXAMPLE:
# metasheet:
#  run_1:
#    tumor: SAMPLE_Tumor
#    normal: SAMPLE_normal
metasheet:
  mocha2-Run1-pt1-FF_run:
    normal: mocha2-Run1-pt1-Normal
    tumor: mocha2-Run1-pt1-FF-Tumor
  mocha2-Run1-pt1-FFPE_run:
    normal: mocha2-Run1-pt1-Normal
    tumor: mocha2-Run1-pt1-FFPE-Tumor

# (Optional) Define any RNA-seq expression data associated with the TUMOR
# samples only.  Currently, only expression results from Salmon are supported.
# The sample names in this section must match the same names used in the
# previous section.
# BOTH bam and expression files are required
#rna:
#  mocha2-Run1-pt1-FF-Tumor:
#    bam_file: gs://mybucket/data/mocha2-Run1-pt1-FF-Tumor.sorted.bam
#    expression_file: gs://mybucket/data/mocha2-Run1-pt1-FF-Tumor.quant.sf
#  mocha2-Run1-pt1-FFPE-Tumor:
#    bam_file: gs://mybucket/data/mocha2-Run1-pt1-FFPE-Tumor.sorted.bam
#    expression_file: gs://mybucket/data/mocha2-Run1-pt1-FFPE-Tumor.quant.sf