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 _set_R(self, file_list):
"""
From the file list, retrieve R1 and R2 fastq files
Sets PU and bids, as well
Uses _get_fastq_from_list() to find R2 pair.
"""
r1s = list()
r2s = list()
for i in file_list:
f = i.file
r = get_r_orientation(f.path)
if r == "R1":
r1s.append(f)
if r == "R2":
r2s.append(f)
for f in r1s:
self.r1.append(f.path)
fastq1 = f.path
expected_r2 = 'R2'.join(fastq1.rsplit('R1', 1))
fastq2 = self._get_fastq_from_list(expected_r2, r2s)
if fastq2:
self.r2.append(fastq2.path)
else:
print("No fastq R2 found for %s" % f.path)
self.paired = False
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 _set_pu(self):
"""
Creating a list of PU values; used by argos pipeline as scatter input
Only iterating across r1s since r1 and r2 should have the same metadata
"""
pu = list()
for f in self.r1:
metadata = get_file(f).metadata
if 'poolednormal' in self.sample_name.lower():
flowcell_id = 'PN_FCID'
r = get_r_orientation(f)
barcode_index = spoof_barcode(os.path.basename(f), r)
else:
flowcell_id = metadata['flowCellId']
barcode_index = metadata['barcodeIndex']
platform_unit = flowcell_id
if barcode_index:
platform_unit = '_'.join([flowcell_id, barcode_index])
pu.append(platform_unit)
return pu