def build_pooled_normal_sample_by_file(pooled_normal, run_ids,
preservation_types, bait_set,
sample_name):
specimen_type = "Pooled Normal"
sample = dict()
sample["id"] = pooled_normal.file.id
sample["path"] = pooled_normal.file.path
sample["file_name"] = pooled_normal.file.file_name
metadata = init_metadata()
metadata["sampleId"] = sample_name
metadata["sampleName"] = sample_name
metadata["cmoSampleName"] = sample_name
metadata["requestId"] = sample_name
metadata["sequencingCenter"] = "MSKCC"
metadata["platform"] = "Illumina"
metadata["baitSet"] = bait_set
metadata["recipe"] = bait_set
metadata["runId"] = run_ids
metadata["preservation"] = preservation_types
metadata["libraryId"] = sample_name + "_1"
# because rgid depends on flowCellId and barcodeIndex, we will
# spoof barcodeIndex so that pairing can work properly; see
# build_sample in runner.operator.argos_operator.bin
metadata["R"] = get_r_orientation(pooled_normal.file.file_name)
metadata["barcodeIndex"] = spoof_barcode(sample["file_name"],
metadata["R"])
metadata["flowCellId"] = "PN_FCID"
metadata["tumorOrNormal"] = "Normal"
metadata["patientId"] = "PN_PATIENT_ID"
metadata["specimenType"] = specimen_type
metadata["runMode"] = ""
metadata["sampleClass"] = ""
sample["metadata"] = metadata
return sample
def build_pooled_normal_sample_by_file(pooled_normal, run_ids, preservation_types, bait_set, sample_name):
specimen_type = 'Pooled Normal'
sample = dict()
sample['id'] = pooled_normal.file.id
sample['path'] = pooled_normal.file.path
sample['file_name'] = pooled_normal.file.file_name
metadata = init_metadata()
metadata['sampleId'] = sample_name
metadata['sampleName'] = sample_name
metadata['cmoSampleName'] = sample_name
metadata['requestId'] = sample_name
metadata['sequencingCenter'] = "MSKCC"
metadata['platform'] = "Illumina"
metadata['baitSet'] = bait_set
metadata['recipe'] = bait_set
metadata['runId'] = run_ids
metadata['preservation'] = preservation_types
metadata['libraryId'] = sample_name + "_1"
# because rgid depends on flowCellId and barcodeIndex, we will
# spoof barcodeIndex so that pairing can work properly; see
# build_sample in runner.operator.argos_operator.bin
metadata['R'] = get_r_orientation(pooled_normal.file.file_name)
metadata['barcodeIndex'] = spoof_barcode(sample['file_name'], metadata['R'])
metadata['flowCellId'] = 'PN_FCID'
metadata['tumorOrNormal'] = 'Normal'
metadata['patientId'] = 'PN_PATIENT_ID'
metadata['specimenType'] = specimen_type
metadata['runMode'] = ""
metadata['sampleClass'] = ""
sample['metadata'] = metadata
return sample
def build_dmp_sample(dmp_bam, patient_id, bait_set, tumor_type):
dmp_metadata = dmp_bam.metadata
specimen_type = "DMP"
sample_name = dmp_metadata["external_id"]
sequencingCenter = "MSKCC"
platform = "Illumina"
sample = dict()
sample["id"] = dmp_bam.file.id
sample["path"] = dmp_bam.file.path
sample["file_name"] = dmp_bam.file.file_name
sample["file_type"] = dmp_bam.file.file_type
metadata = init_metadata()
metadata["sampleId"] = sample_name
metadata["sampleName"] = format_sample_name(sample_name, specimen_type)
metadata["cmoSampleName"] = metadata["sampleName"]
metadata["requestId"] = sample_name
metadata["sequencingCenter"] = sequencingCenter
metadata["platform"] = platform
metadata["baitSet"] = bait_set
metadata["recipe"] = bait_set
metadata["run_id"] = ""
metadata["preservation"] = ""
metadata["libraryId"] = sample_name + "_1"
metadata["R"] = "Not applicable"
# because rgid depends on flowCellId and barcodeIndex, we will
# spoof barcodeIndex so that pairing can work properly; see
# build_sample in runner.operator.argos_operator.bin
metadata["barcodeIndex"] = "DMP_BARCODEIDX"
metadata["flowCellId"] = "DMP_FCID"
metadata["tumorOrNormal"] = tumor_type
metadata["patientId"] = patient_id
metadata["specimenType"] = specimen_type
metadata["runMode"] = ""
metadata["sampleClass"] = ""
sample["metadata"] = metadata
return sample
def build_dmp_sample(dmp_bam, patient_id, bait_set, tumor_type):
dmp_metadata = dmp_bam.metadata
specimen_type = "DMP"
sample_name = dmp_metadata['external_id']
sequencingCenter = "MSKCC"
platform = "Illumina"
sample = dict()
sample['id'] = dmp_bam.file.id
sample['path'] = dmp_bam.file.path
sample['file_name'] = dmp_bam.file.file_name
sample['file_type'] = dmp_bam.file.file_type
metadata = init_metadata()
metadata['sampleId'] = sample_name
metadata['sampleName'] = format_sample_name(sample_name, specimen_type)
metadata['cmoSampleName'] = metadata['sampleName']
metadata['requestId'] = sample_name
metadata['sequencingCenter'] = sequencingCenter
metadata['platform'] = platform
metadata['baitSet'] = bait_set
metadata['recipe'] = bait_set
metadata['run_id'] = ""
metadata['preservation'] = ""
metadata['libraryId'] = sample_name + "_1"
metadata['R'] = 'Not applicable'
# because rgid depends on flowCellId and barcodeIndex, we will
# spoof barcodeIndex so that pairing can work properly; see
# build_sample in runner.operator.argos_operator.bin
metadata['barcodeIndex'] = 'DMP_BARCODEIDX'
metadata['flowCellId'] = 'DMP_FCID'
metadata['tumorOrNormal'] = tumor_type
metadata['patientId'] = patient_id
metadata['specimenType'] = specimen_type
metadata['runMode'] = ""
metadata['sampleClass'] = ""
sample['metadata'] = metadata
return sample