def fq_trimming(pipeline,
fq1_files,
fq2_files,
clinseq_barcode,
ref,
outdir,
maxcores=1):
fq1_abs = [normpath(x) for x in fq1_files]
fq2_abs = [normpath(x) for x in fq2_files]
logging.debug("Trimming {} and {}".format(fq1_abs, fq2_abs))
pairs = [(fq1_abs[k], fq2_abs[k]) for k in range(len(fq1_abs))]
fq1_trimmed = []
fq2_trimmed = []
for fq1, fq2 in pairs:
skewer = Skewer()
skewer.input1 = fq1
skewer.input2 = fq2
skewer.output1 = outdir + "/skewer/libs/{}".format(
os.path.basename(fq1))
skewer.output2 = outdir + "/skewer/libs/{}".format(
os.path.basename(fq2))
skewer.stats = outdir + "/skewer/libs/skewer-stats-{}.log".format(
os.path.basename(fq1))
skewer.threads = maxcores
skewer.jobname = "skewer/{}".format(os.path.basename(fq1))
skewer.scratch = pipeline.scratch
skewer.is_intermediate = True
fq1_trimmed.append(skewer.output1)
fq2_trimmed.append(skewer.output2)
pipeline.add(skewer)
cat1 = Cat()
cat1.input = fq1_trimmed
cat1.output = outdir + "/skewer/{}-concatenated_1.fastq.gz".format(
clinseq_barcode)
cat1.jobname = "cat1/{}".format(clinseq_barcode)
cat1.is_intermediate = True
pipeline.add(cat1)
cat2 = Cat()
cat2.input = fq2_trimmed
cat2.jobname = "cat2/{}".format(clinseq_barcode)
cat2.output = outdir + "/skewer/{}-concatenated_2.fastq.gz".format(
clinseq_barcode)
cat2.is_intermediate = True
pipeline.add(cat2)
return cat1.output, cat2.output
def align_se(pipeline, fq1_files, clinseq_barcode, ref, outdir, maxcores, remove_duplicates=True):
"""
Align single end data
:param pipeline:
:param fq1_files:
:param lib:
:param ref:
:param outdir:
:param maxcores:
:param remove_duplicates:
:return:
"""
logging.debug("Aligning files: {}".format(fq1_files))
fq1_abs = [normpath(x) for x in fq1_files]
fq1_trimmed = []
for fq1 in fq1_abs:
skewer = Skewer()
skewer.input1 = fq1
skewer.input2 = None
skewer.output1 = outdir + "/skewer/{}".format(os.path.basename(fq1))
skewer.output2 = outdir + "/skewer/unused-dummyfq2-{}".format(os.path.basename(fq1))
skewer.stats = outdir + "/skewer/skewer-stats-{}.log".format(os.path.basename(fq1))
skewer.threads = maxcores
skewer.jobname = "skewer/{}".format(os.path.basename(fq1))
skewer.scratch = pipeline.scratch
skewer.is_intermediate = True
fq1_trimmed.append(skewer.output1)
pipeline.add(skewer)
cat1 = Cat()
cat1.input = fq1_trimmed
cat1.output = outdir + "/skewer/{}_1.fastq.gz".format(clinseq_barcode)
cat1.jobname = "cat/{}".format(clinseq_barcode)
cat1.is_intermediate = False
pipeline.add(cat1)
bwa = Bwa()
bwa.input_fastq1 = cat1.output
bwa.input_reference_sequence = ref
bwa.remove_duplicates = remove_duplicates
library_id = parse_prep_id(clinseq_barcode)
sample_string = compose_sample_str(extract_unique_capture(clinseq_barcode))
bwa.readgroup = "\"@RG\\tID:{rg_id}\\tSM:{rg_sm}\\tLB:{rg_lb}\\tPL:ILLUMINA\"".format(\
rg_id=clinseq_barcode, rg_sm=sample_string, rg_lb=library_id)
bwa.threads = maxcores
bwa.output = "{}/{}.bam".format(outdir, clinseq_barcode)
bwa.scratch = pipeline.scratch
bwa.jobname = "bwa/{}".format(clinseq_barcode)
bwa.is_intermediate = False
pipeline.add(bwa)
return bwa.output
def __init__(self, outdir, first, second, third, **kwargs):
PypedreamPipeline.__init__(self, outdir, **kwargs)
rnd1 = Urandom()
rnd1.output = outdir + "/" + first
self.add(rnd1)
rnd2 = Ifail()
rnd2.output = outdir + "/" + second
self.add(rnd2)
cat1 = Cat()
cat1.input = [rnd1.output, rnd2.output]
cat1.output = outdir + "/" + third
self.add(cat1)
def __init__(self, outdir, first, second, third, **kwargs):
PypedreamPipeline.__init__(self, outdir, **kwargs)
rnd1 = Urandom()
rnd1.jobname = "urandom-{}".format(first)
rnd1.output = outdir + "/" + first
rnd1.threads = 1
self.add(rnd1)
rnd2 = Urandom()
rnd2.jobname = "urandom-{}".format(second)
rnd2.output = outdir + "/" + second
rnd2.is_intermediate = True
self.add(rnd2)
cat1 = Cat()
cat1.jobname = "cat1-{}".format(third)
cat1.input = [rnd1.output, rnd2.output]
cat1.output = outdir + "/" + third
self.add(cat1)
def align_pe(pipeline, fq1_files, fq2_files, clinseq_barcode, ref, outdir, maxcores=1, remove_duplicates=True):
"""
align paired end data
:param pipeline:
:param fq1_files:
:param fq2_files:
:param lib:
:param ref:
:param outdir:
:param maxcores:
:param remove_duplicates:
:return:
"""
fq1_abs = [normpath(x) for x in fq1_files]
fq2_abs = [normpath(x) for x in fq2_files]
logging.debug("Trimming {} and {}".format(fq1_abs, fq2_abs))
pairs = [(fq1_abs[k], fq2_abs[k]) for k in range(len(fq1_abs))]
fq1_trimmed = []
fq2_trimmed = []
for fq1, fq2 in pairs:
skewer = Skewer()
skewer.input1 = fq1
skewer.input2 = fq2
skewer.output1 = outdir + "/skewer/libs/{}".format(os.path.basename(fq1))
skewer.output2 = outdir + "/skewer/libs/{}".format(os.path.basename(fq2))
skewer.stats = outdir + "/skewer/libs/skewer-stats-{}.log".format(os.path.basename(fq1))
skewer.threads = maxcores
skewer.jobname = "skewer/{}".format(os.path.basename(fq1))
skewer.scratch = pipeline.scratch
skewer.is_intermediate = True
fq1_trimmed.append(skewer.output1)
fq2_trimmed.append(skewer.output2)
pipeline.add(skewer)
cat1 = Cat()
cat1.input = fq1_trimmed
cat1.output = outdir + "/skewer/{}-concatenated_1.fastq.gz".format(clinseq_barcode)
cat1.jobname = "cat1/{}".format(clinseq_barcode)
cat1.is_intermediate = True
pipeline.add(cat1)
cat2 = Cat()
cat2.input = fq2_trimmed
cat2.jobname = "cat2/{}".format(clinseq_barcode)
cat2.output = outdir + "/skewer/{}-concatenated_2.fastq.gz".format(clinseq_barcode)
cat2.is_intermediate = True
pipeline.add(cat2)
bwa = Bwa()
bwa.input_fastq1 = cat1.output
bwa.input_fastq2 = cat2.output
bwa.input_reference_sequence = ref
bwa.remove_duplicates = remove_duplicates
library_id = parse_prep_id(clinseq_barcode)
sample_string = compose_sample_str(extract_unique_capture(clinseq_barcode))
bwa.readgroup = "\"@RG\\tID:{rg_id}\\tSM:{rg_sm}\\tLB:{rg_lb}\\tPL:ILLUMINA\"".format(\
rg_id=clinseq_barcode, rg_sm=sample_string, rg_lb=library_id)
bwa.threads = maxcores
bwa.output = "{}/{}.bam".format(outdir, clinseq_barcode)
bwa.jobname = "bwa/{}".format(clinseq_barcode)
bwa.scratch = pipeline.scratch
bwa.is_intermediate = False
pipeline.add(bwa)
return bwa.output