def run(self):
for output in self.output():
pipeline_utils.confirm_path(output.path)
wait_time = random.uniform(0, 3)
time.sleep(wait_time)
sys.stdout.flush()
while not pipeline_utils.add_thread_count(global_vars.thread_file, 1):
time.sleep(1.2)
for i, input_file in enumerate(self.input()):
cmd = 'grep "ChrID" %s' % input_file.path #| awk '$17 >= 3' > $file_out
p1 = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
# outs, err = p.communicate()
cmd = "awk '$17>=%s'" % self.cfg['pindel_min_reads']
p2 = subprocess.Popen(cmd,
stdout=subprocess.PIPE,
stdin=p1.stdout,
shell=True)
# outs, err = p.communicate()
outs, err = p2.communicate()
with open(self.output()[i].path, 'wb') as f:
f.write(outs)
while not pipeline_utils.sub_thread_count(global_vars.thread_file, 1):
time.sleep(1.2)
def run(self):
for output in self.output():
pipeline_utils.confirm_path(output.path)
wait_time = random.uniform(0, 3)
time.sleep(wait_time)
sys.stdout.flush()
while not pipeline_utils.add_thread_count(global_vars.thread_file, 1):
time.sleep(1.2)
sample_dict = {
output.path.split('/')[-1].split('.pindel.bed')[0]: output.path
for output in self.output()[:-1]
}
misc_utils.filter_pindel(
pindel_files=[input_file.path for input_file in self.input()],
sample_dict=sample_dict,
project_dir=self.project_dir,
all_samples_output=self.output()[-1].path,
min_reads=self.cfg['pindel_min_reads'],
min_qual=self.cfg['pindel_min_qual'],
max_inv_length=self.cfg['pindel_max_inv_length'])
while not pipeline_utils.sub_thread_count(global_vars.thread_file, 1):
time.sleep(1.2)
def run(self):
for output in self.output():
pipeline_utils.confirm_path(output.path)
wait_time = random.uniform(0, 3)
time.sleep(wait_time)
sys.stdout.flush()
while not pipeline_utils.add_thread_count(global_vars.thread_file, 1):
time.sleep(1.2)
for i, input_file in enumerate(self.input()[:-1]):
cmd = 'sort-bed %s' % input_file.path
# print(cmd)
p1 = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
cmd = [
'bedtools', 'intersect', '-wa', '-u', '-sorted', '-a', 'stdin',
'-b', self.cfg['exons_bed']
]
cmd = ' '.join(cmd)
p2 = subprocess.Popen(cmd,
stdout=subprocess.PIPE,
stdin=p1.stdout,
shell=True)
# print(cmd)
cmd = [
"bedmap", "--echo", "--echo-map-id-uniq", "--delim", r"'\t'",
"-", self.cfg['genmap']
]
cmd = " ".join(cmd)
# print(cmd)
p3 = subprocess.Popen(cmd,
stdout=subprocess.PIPE,
stdin=p2.stdout,
shell=True)
outs, err = p3.communicate()
with open(self.output()[i].path, 'wb') as f:
f.write(str.encode('#gffTags\n'))
f.write(outs)
while not pipeline_utils.sub_thread_count(global_vars.thread_file, 1):
time.sleep(1.2)
def run(self):
pipeline_utils.confirm_path(self.output().path)
wait_time = random.uniform(0, 3)
time.sleep(wait_time)
sys.stdout.flush()
while not pipeline_utils.add_thread_count(global_vars.thread_file, 1):
time.sleep(1)
cmd = [
self.cfg['freebayes_location'], '-f', self.cfg['fasta_file'], '-t',
self.cfg['library_bed'],
self.input()[0].path
]
print(' '.join(cmd))
sys.stdout.flush()
p1 = subprocess.Popen(' '.join(cmd),
stdout=subprocess.PIPE,
shell=True)
# outs, err = p.communicate()
cmd = [self.cfg['vcffilter_location'], '-f', '"QUAL > 20"']
p2 = subprocess.Popen(' '.join(cmd),
stdout=subprocess.PIPE,
stdin=p1.stdout,
shell=True)
cmd = ['vcf-sort']
p3 = subprocess.Popen(' '.join(cmd),
stdout=subprocess.PIPE,
stdin=p2.stdout,
shell=True)
# outs, err = p.communicate()
outs, err = p3.communicate()
with open(self.output().path, 'wb') as f:
f.write(outs)
while not pipeline_utils.sub_thread_count(global_vars.thread_file, 1):
time.sleep(1)
def run(self):
for output in self.output():
pipeline_utils.confirm_path(output.path)
cmd = 'python3 %s segment %s -m %s --drop-low-coverage -o %s' % (
self.cfg['cnvkit_location'], self.input().path,
self.cfg['cnvkit_seg_method'], self.output()[0].path)
cmd = cmd.split(' ')
pipeline_utils.command_call(cmd, self.output())
cmd = 'python3 %s segmetrics %s -s %s --ci --std --mean -o %s' % (
self.cfg['cnvkit_location'], self.input().path,
self.output()[0].path, self.output()[1].path)
cmd = cmd.split(' ')
pipeline_utils.command_call(cmd, self.output())
cmd = 'python3 %s call %s -i %s_T -m threshold --filter ci --sample-sex female -t=-1.1,-0.4,0.3,0.7 -o %s' % (
self.cfg['cnvkit_location'], self.output()[1].path, self.case,
self.output()[2].path)
cmd = cmd.split(' ')
pipeline_utils.command_call(cmd, self.output())
cmd = 'python3 %s scatter %s -s %s -o %s' % (
self.cfg['cnvkit_location'], self.input().path,
self.output()[2].path, self.output()[3].path)
cmd = cmd.split(' ')
pipeline_utils.command_call(cmd, self.output())
cmd = 'python3 %s genemetrics %s -s %s -t %s -m %s -o %s' % (
self.cfg['cnvkit_location'], self.input().path,
self.output()[2].path, self.cfg['cnvkit_genemetrics_threshold'],
self.cfg['cnvkit_genemetrics_minprobes'], self.output()[4].path)
cmd = cmd.split(' ')
pipeline_utils.command_call(cmd, self.output())
#repurpose command call for piped commands
wait_time = random.uniform(0, 3)
time.sleep(wait_time)
sys.stdout.flush()
while not pipeline_utils.add_thread_count(global_vars.thread_file, 1):
time.sleep(1.2)
cmd = 'python3 %s genemetrics %s -s %s' % (self.cfg['cnvkit_location'],
self.input().path,
self.output()[2].path)
cmd = cmd.split(' ')
p1 = subprocess.Popen(cmd, stdout=subprocess.PIPE)
# outs, err = p.communicate()
cmd = 'tail -n+2'
cmd = cmd.split(' ')
p2 = subprocess.Popen(cmd, stdout=subprocess.PIPE, stdin=p1.stdout)
# outs, err = p.communicate()
cmd = 'cut -f1'
cmd = cmd.split(' ')
p3 = subprocess.Popen(cmd, stdout=subprocess.PIPE, stdin=p2.stdout)
# outs, err = p.communicate()
cmd = 'sort'
cmd = cmd.split(' ')
p4 = subprocess.Popen(cmd, stdout=subprocess.PIPE, stdin=p3.stdout)
outs, err = p4.communicate()
with open('%s_segment_genes.txt' % self.case, 'wb') as f:
f.write(outs)