def test_fastq_path(self):
"""
test that the components of the path to the files are in place
"""
files = find_fastqs(library='NA12877-N-03098121-TD1-TT1', libdir='tests/libraries')
self.assertIn(self.libdir, files[0][0])
self.assertIn(self.library, files[0][0])
def data_available_for_clinseq_barcode(libdir, clinseq_barcode):
"""
Check that data is available for the specified clinseq barcode in the specified library folder.
:param libdir: Directory name where fastqs are organised.
:param clinseq_barcode: A valid clinseq barcode string
:return: True if data is available, False otherwise
"""
if not clinseq_barcode_is_valid(clinseq_barcode):
raise ValueError("Invalid clinseq barcode: " + clinseq_barcode)
filedir = os.path.join(libdir, clinseq_barcode)
if not os.path.exists(filedir):
logging.warn(
"Dir {} does not exists for {}. Not using library.".format(
filedir, clinseq_barcode))
return False
if find_fastqs(clinseq_barcode, libdir) == (None, None):
logging.warn("No fastq files found for {} in dir {}".format(
clinseq_barcode, filedir))
return False
logging.debug("Library {} has data. Using it.".format(clinseq_barcode))
return True
def test_find_fq_gz(self):
"""
test that files on the format *_1.fq.gz / *_2.fq.gz are found
"""
files = find_fastqs(library=self.library, libdir=self.libdir)
files_basenames = [os.path.basename(f) for f in files[0]] + [os.path.basename(f) for f in files[1]]
self.assertIn('bar_1.fq.gz', files_basenames)
self.assertIn('bar_2.fq.gz', files_basenames)
def configure_umi_processing(self):
# configure for UMI SNV calling pipeline
#
capture_to_barcodes = self.get_unique_capture_to_clinseq_barcodes()
for unique_capture in capture_to_barcodes.keys():
capture_kit = unique_capture.capture_kit_id
for clinseq_barcode in capture_to_barcodes[unique_capture]:
trimmed_fqfiles = fq_trimming(
self,
fq1_files=find_fastqs(clinseq_barcode, self.libdir)[0],
fq2_files=find_fastqs(clinseq_barcode, self.libdir)[1],
clinseq_barcode=clinseq_barcode,
ref=self.refdata['bwaIndex'],
outdir="{}/bams/{}".format(self.outdir, capture_kit),
maxcores=self.maxcores)
bam_file = self.configure_fastq_to_bam(
fq_files=trimmed_fqfiles,
clinseq_barcode=clinseq_barcode,
capture_kit=capture_kit)
realigned_bam = self.configure_alignment_with_umi(
bamfile=bam_file,
clinseq_barcode=clinseq_barcode,
capture_kit=capture_kit,
jobname='1')
consensus_reads = self.configure_consensus_reads_calling(
bam=realigned_bam,
clinseq_barcode=clinseq_barcode,
capture_kit=capture_kit)
realigned_bam2 = self.configure_alignment_with_umi(
bamfile=consensus_reads,
clinseq_barcode=clinseq_barcode,
capture_kit=capture_kit,
jobname='2')
filtered_bam = self.configure_consensus_read_filter(
bam=realigned_bam2,
clinseq_barcode=clinseq_barcode,
capture_kit=capture_kit)
clip_overlap_bam = self.configure_clip_overlapping(
bam=filtered_bam,
clinseq_barcode=clinseq_barcode,
capture_kit=capture_kit)
mark_dups_bam = self.configure_markdups(
bamfile=realigned_bam, unique_capture=unique_capture)
self.set_capture_bam(unique_capture, filtered_bam, self.umi)
def test_find_RN_DDD(self):
"""
test that files on the format *R1_nnn.fastq.gz/*R2_nnn.fastq.gz are found
"""
files = find_fastqs(library=self.library, libdir=self.libdir)
files_basenames = [os.path.basename(f) for f in files[0]] + [os.path.basename(f) for f in files[1]]
self.assertIn('baz_R1_001.fastq.gz', files_basenames)
self.assertIn('baz_R2_001.fastq.gz', files_basenames)
self.assertIn('baz_R1_999.fastq.gz', files_basenames)
self.assertIn('baz_R2_999.fastq.gz', files_basenames)
def test_find_fastqs_for_no_library(self):
"""
test that find_fastqs return (None,None) if called with library=None
"""
files = find_fastqs(library=None, libdir=self.libdir)
self.assertEqual(files, (None, None))
