def run_test(
basic: Basic,
code: str,
name: str,
res_type: type_res = None,
err_type: type_err = None,
value: type_value = None,
repl: bool = True,
) -> None:
if not isinstance(res_type, list):
res_type = [res_type] if res_type else []
if not isinstance(value, list):
value = [value] if value is not None else []
try:
results = basic.run(code, name, repl)
assert len(results) == len(res_type)
for i, res in enumerate(results):
assert res_type and isinstance(res, res_type[i])
if value and value[i] is not Ellipsis:
if res.value != value[i]:
print(res.value, value[i])
assert res.value == value[i]
except Error as err:
assert err_type and isinstance(err, err_type)
else:
assert err_type is None
def main(debug: bool = False) -> None:
basic = Basic()
while True:
text = input("basic > ")
try:
results = basic.run(text, "<stdin>", True, debug)
for result in results:
print(result)
except Error as err:
print_error(err)
def main(file_name: str) -> None:
with open(file_name, "r") as f:
code = f.read()
basic = Basic()
try:
results = basic.run(code, file_name)
for result in results:
print(result)
except Error as err:
print_error(err)
def submit(self, number=None, mem="15G"):
"""
number: how many jobs to submit:
"all", "last_one"
"""
handle = open(self.sample_list_file, "r")
samples = handle.readlines()
if number == "last_one":
last_one = samples[-1].split("\t")[0]
last_one_pbs = os.path.join(self.pbs_dir, last_one + ".pbs")
cmd = "qsub -l nodes=1:ppn=%s -l mem=%s %s" % (self.threads, mem,
last_one_pbs)
p = Basic.run(cmd, wkdir=self.pbs_dir)
print(p.stdout.read())
if number == "all":
for one_sample in samples:
one = one_sample[-1].split("\t")[0]
one_pbs = os.path.join(self.pbs_dir, one + ".pbs")
cmd = "qsub -l nodes=1:ppn=%s -l mem=%s %s" % (self.threads,
mem, one_pbs)
p = Basic.run(cmd, wkdir=self.pbs_dir)
print(p.stdout.read())
print("finish submit pbs!")
def process(self, sampleID=None, fastq_1=None, fastq_2=None):
oneSample_dir = os.path.join(self.bam_dir, sampleID)
if not os.path.exists(oneSample_dir):
os.makedirs(oneSample_dir)
log_file = os.path.join(oneSample_dir, sampleID + ".log.txt")
#step1. bwa mapping to whole genome
sort_bam = os.path.join(oneSample_dir, sampleID + ".sort.bam")
cmd = """%s mem -R '@RG\\tID:GRCH37\\tSM:%s\\tLB:\\tPL:ILLUMINA' -t %s %s %s %s|%s view -@ %s -Shu -|%s sort -@ %s -o %s - > %s;\n""" % \
(self.bwa, sampleID, self.threads, self.whole_genome, fastq_1, fastq_2, self.samtools, self.threads,self.samtools, self.threads,\
sort_bam, log_file)
Basic.run(cmd=cmd, wkdir=self.prefix)
##step1.1 bwa index for bam file
cmd = """%s index %s;\n""" % (self.samtools, sort_bam)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step2. filter out read mapped in bam file
MT_bam = os.path.join(oneSample_dir, sampleID + ".MT.bam")
cmd = "%s view -bh %s chrM -o %s;\n" % (self.samtools, sort_bam,
MT_bam)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step3. obtain unique mapped reads
MT_bam_unique = os.path.join(oneSample_dir,
sampleID + ".unique.MT.bam")
MT_bam_noneUnique = os.path.join(oneSample_dir,
sampleID + ".noneUnique.MT.bam")
cmd = "%s view -h %s | grep -v -e 'XA:Z:' -e 'SA:Z:' | samtools view -b > %s;" % \
(self.samtools, MT_bam, MT_bam_unique)
Basic.run(cmd=cmd, wkdir=self.prefix)
cmd = "%s view -h %s | grep -e 'XA:Z:' -e 'SA:Z:' | samtools view -b > %s;" % \
(self.samtools, MT_bam, MT_bam_noneUnique)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step4. mpileup
p_sort_bam = os.path.join(oneSample_dir, sampleID + ".p.sort.bam")
cmd = "%s sort -@ 7 -o %s %s;\n" % (self.samtools, p_sort_bam,
MT_bam_unique)
Basic.run(cmd=cmd, wkdir=self.prefix)
mpile_file = os.path.join(self.mpile_dir, sampleID + ".mpile.file")
cmd = "%s mpileup -B -Q 30 -d 1000000 -L 10000 -f %s %s > %s;" % (
self.samtools, self.ref_genome, p_sort_bam, mpile_file)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step5. call heteroplasmy
# heteroplasmy
heteroplasmy_raw = os.path.join(oneSample_dir, sampleID + ".mp.raw")
cmd = '%s -i %s -o %s;\n' % (self.het_raw, mpile_file,
heteroplasmy_raw)
Basic.run(cmd=cmd, wkdir=self.prefix)
heteropasmy = os.path.join(self.mpile_dir,
sampleID + ".heteroplasmy.txt")
cmd = 'python2 %s --loose %s --chi %s -d %s --mle %s -i %s -o %s' \
%(self.het_filter, "0.003,0.003", "0.0", "1000", "0", heteroplasmy_raw, heteropasmy)
Basic.run(cmd=cmd, wkdir=self.prefix)
print("finish detetcting!")
def new_process(self, sampleID=None, fastq_1=None, fastq_2=None):
oneSample_dir = os.path.join(self.bam_dir, sampleID)
if not os.path.exists(oneSample_dir):
os.makedirs(oneSample_dir)
log_file = os.path.join(oneSample_dir, sampleID + ".log.txt")
#step1. bwa mapping to whole genome
sort_bam = os.path.join(oneSample_dir, sampleID + ".sort.bam")
cmd = """%s mem -R '@RG\\tID:GRCH37\\tSM:%s\\tLB:mitochondira\\tPL:ILLUMINA' -t %s %s %s %s|%s view -@ %s -Shu -|%s sort -@ %s -o %s - > %s;\n""" % \
(self.bwa, sampleID, self.threads, self.whole_genome, fastq_1, fastq_2, self.samtools, self.threads,self.samtools, self.threads,\
sort_bam, log_file)
Basic.run(cmd=cmd, wkdir=self.prefix)
cmd = """%s index %s;\n""" % (self.samtools, sort_bam)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step2. filter out read mapped in bam file
bamio = bamIO(
bam_file=
"/home/zyang/Project/mitochondria/pnas_data/luo_pipeline/work_test/bam/ERR452358/ERR452358.sort.bam"
)
MTbam = bamio.run()
cmd = """%s index %s;\n""" % (self.samtools, MTbam)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step3. mark duplicate
marked_duplicated_bam = os.path.join(oneSample_dir,
sampleID + ".mkdup.bam")
mkmatrix = os.path.join(oneSample_dir, sampleID + ".mkdup.matrix.txt")
cmd = self.markduplicate(input_bam=MTbam,
marked_duplicated_bam=marked_duplicated_bam,
marked_dup_metrics_txt=mkmatrix)
Basic.run(cmd=cmd, wkdir=self.prefix)
bamio.sample_meta_infor["befor_mkduped_read"] = bamio.mapped_read(
input_bam=MTbam)
cmd = """%s index %s;\n""" % (self.samtools, marked_duplicated_bam)
Basic.run(cmd=cmd, wkdir=self.prefix)
bamio.sample_meta_infor["after_mkduped_read"] = bamio.mapped_read(
input_bam=marked_duplicated_bam)
#step4. local realignment
localRealign_bam = os.path.join(oneSample_dir,
sampleID + ".localRealign.bam")
cmd = self.localRealignment(input_bam=marked_duplicated_bam,
output_bam=localRealign_bam)
Basic.run(cmd=cmd, wkdir=self.prefix)
cmd = """%s index %s;\n""" % (self.samtools, localRealign_bam)
Basic.run(cmd=cmd, wkdir=self.prefix)
bamio.sample_meta_infor["after_local_realign"] = bamio.mapped_read(
input_bam=localRealign_bam)
#step5. mismatch filter
mismatch_bam = os.path.join(oneSample_dir,
sampleID + ".mismatchFilter.bam")
bamio.limit_mismatch(input_bam=localRealign_bam,
output_bam=mismatch_bam,
mismatch_num=1)
cmd = """%s index %s;\n""" % (self.samtools, localRealign_bam)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step5. mpileup
p_sort_bam = os.path.join(oneSample_dir, sampleID + ".p.sort.bam")
MT_bam_unique = os.path.join(oneSample_dir,
sampleID + ".unique.MT.bam")
cmd = "%s view -h %s | grep -v -e 'XA:Z:' -e 'SA:Z:' | samtools view -b > %s;" % \
(self.samtools, mismatch_bam, MT_bam_unique)
Basic.run(cmd=cmd, wkdir=self.prefix)
cmd = "%s sort -@ 7 -o %s %s;\n" % (self.samtools, p_sort_bam,
MT_bam_unique)
Basic.run(cmd=cmd, wkdir=self.prefix)
mpile_file = os.path.join(self.mpile_dir, sampleID + ".mpile.file")
cmd = "%s mpileup -B -Q 20 -q 20 -d 1000000 -L 10000 -f %s %s > %s;" % (
self.samtools, self.ref_genome, MT_bam_unique, mpile_file)
Basic.run(cmd=cmd, wkdir=self.prefix)
#step5. call heteroplasmy
# heteroplasmy
heteroplasmy_raw = os.path.join(oneSample_dir, sampleID + ".mp.raw")
cmd = '%s -i %s -o %s;\n' % (self.het_raw, mpile_file,
heteroplasmy_raw)
Basic.run(cmd=cmd, wkdir=self.prefix)
heteropasmy = os.path.join(self.mpile_dir,
sampleID + ".heteroplasmy.txt")
cmd = 'python2 %s --loose %s --chi %s -d %s --mle %s -i %s -o %s' \
%(self.het_filter, "0.003,0.003", "0.0", "1000", "0", heteroplasmy_raw, heteropasmy)
Basic.run(cmd=cmd, wkdir=self.prefix)
print("finish heteroplasmy detecting!")
print(bamio.sample_meta_infor)
