def __init__(self,
sampledata,
refdata,
job_params,
outdir,
libdir,
umi,
maxcores=1,
scratch="/scratch/tmp/tmp",
**kwargs):
ClinseqPipeline.__init__(self, sampledata, refdata, job_params, outdir,
libdir, umi, maxcores, scratch, **kwargs)
# Set the min alt frac value:
self.default_job_params["vardict-min-alt-frac"] = 0.01
self.default_job_params["vardict-min-num-reads"] = None
self.default_job_params[
"vep-additional-options"] = " --pick --filter_common "
# Remove clinseq barcodes for which data is not available:
self.check_sampledata()
if umi:
# Configure the umi processes from fastq to bam file:
self.configure_umi_processing()
else:
# Configure alignment and merging of fastq data for all clinseq barcodes:
self.configure_align_and_merge()
# Configure all panel analyses:
self.configure_panel_analyses()
# Configure liqbio-specific panel analyses:
self.configure_panel_analyses_liqbio(umi)
# Configure additional msings analysis:
self.configure_panel_msings_analyses()
# Configure QC of all panel data:
self.configure_all_panel_qcs()
# Configure fastq QCs:
self.configure_fastq_qcs()
# Configure the low-pass whole genome analysis:
self.configure_lowpass_analyses()
# Configure low-pass whole genome data QC:
self.configure_all_lowpass_qcs()
# Configure MultiQC:
self.configure_multi_qc()
def __init__(self,
sampledata,
refdata,
job_params,
outdir,
libdir,
maxcores=1,
scratch="/scratch/tmp/tmp/",
referral_db_conf="tests/referrals/referral-db-config.json",
addresses="tests/referrals/addresses.csv",
**kwargs):
ClinseqPipeline.__init__(self, sampledata, refdata, job_params, outdir,
libdir, maxcores, scratch, **kwargs)
self.referral_db_conf = referral_db_conf
self.addresses = addresses
self.default_job_params["vardict-min-num-reads"] = 6
self.default_job_params["create_alascca_report"] = True
# Check to ensure that the sample data is valid for an ALASCCA analysis:
self.validate_sample_data_for_alascca()
# Remove sample capture items for which data is not available:
self.check_sampledata()
# Configure alignment and merging of fastq data for all clinseq barcodes:
self.configure_align_and_merge()
# Configure all panel analyses:
self.configure_panel_analyses()
# Configure QC of all panel data:
self.configure_all_panel_qcs()
# Configure ALASCCA report generation:
self.configure_alascca_specific_analysis()
# Configure fastq QCs:
self.configure_fastq_qcs()
# Configure MultiQC:
self.configure_multi_qc()
def __init__(self, sampledata, refdata, job_params, outdir, libdir, umi, maxcores=1, scratch="/scratch/tmp/tmp",
**kwargs):
ClinseqPipeline.__init__(self, sampledata, refdata, job_params, outdir, libdir, umi,
maxcores, scratch, **kwargs)
# Set the min alt frac value:
self.default_job_params["vardict-min-alt-frac"] = 0.01
self.default_job_params["vardict-min-num-reads"] = None
self.default_job_params["vep-additional-options"] = " --pick --filter_common "
#Set initial data
self.sampledata = sampledata
self.refdata = refdata
self.job_params = job_params
self.outdir = outdir
self.libdir = libdir
self.umi = umi
self.maxcores = maxcores
self.scratch = scratch
self.kwargs = kwargs
self.somatic_merge_vcf = defaultdict(dict)
#Below dictionary will set the steps to run aws batch job with docker image (key: docker image name , value: function to add job).
self.step_to_run = {
"qc": self.qc_step, #docker: base
"alignment": self.alignment_step, #docker: aligner
"cnvkit": self.cnvkit_step, #docker: variants
"germline_variant": self.germline_variant_step, #docker: variants
"somatic_vardict": self.somatic_variant_vardict_step, #docker: variants # tested working
"somatic_strelka": self.somatic_variant_strelka_step, #docker: variants #tested working
"somatic_mutect2": self.somatic_variant_mutect2_step, #docker: variants #tested working
"somatic_varscan": self.somatic_variant_varscan_step, #docker: variants #tested working
"somatic_variant_merge": self.somatic_variant_merge_step, #docker: somaticseq #tested working
"vep": self.vep_step, #docker : vep #tested
"msi" : self.msi_sensor_step
}