def test_programs(self):
"""Identify programs and versions used in analysis.
"""
with make_workdir() as workdir:
config = load_config(
get_post_process_yaml(self.automated_dir, workdir))
print programs._get_versions(config)
def test_1_parallel_vcf_combine(self):
"""Parallel combination of VCF files, split by chromosome.
"""
files = [
os.path.join(self.var_dir, "S1-variants.vcf"),
os.path.join(self.var_dir, "S2-variants.vcf")
]
ref_file = os.path.join(self.data_dir, "genomes", "hg19", "seq",
"hg19.fa")
with make_workdir() as workdir:
config = load_config(
get_post_process_yaml(self.automated_dir, workdir))
config["algorithm"] = {}
region_dir = os.path.join(self.var_dir, "S1_S2-combined-regions")
if os.path.exists(region_dir):
shutil.rmtree(region_dir)
if os.path.exists(self.combo_file):
os.remove(self.combo_file)
with prun.start({
"type": "local",
"cores": 1
}, [[config]], config) as run_parallel:
vcfutils.parallel_combine_variants(files, self.combo_file,
ref_file, config, run_parallel)
for fname in files:
if os.path.exists(fname + ".gz"):
subprocess.check_call(["gunzip", fname + ".gz"])
if os.path.exists(fname + ".gz.tbi"):
os.remove(fname + ".gz.tbi")
def test_2_vcf_exclusion(self):
"""Exclude samples from VCF files.
"""
ref_file = os.path.join(self.data_dir, "genomes", "hg19", "seq", "hg19.fa")
with make_workdir() as workdir:
config = load_config(get_post_process_yaml(self.automated_dir, workdir))
config["algorithm"] = {}
out_file = utils.append_stem(self.combo_file, "-exclude")
to_exclude = ["S1"]
if os.path.exists(out_file):
os.remove(out_file)
vcfutils.exclude_samples(self.combo_file, out_file, to_exclude, ref_file, config)
def test_2_vcf_exclusion(self):
"""Exclude samples from VCF files.
"""
ref_file = os.path.join(self.data_dir, "genomes", "hg19", "seq", "hg19.fa")
with make_workdir() as workdir:
config = load_config(get_post_process_yaml(self.data_dir, workdir))
config["algorithm"] = {}
out_file = utils.append_stem(self.combo_file, "-exclude")
to_exclude = ["S1"]
if os.path.exists(out_file):
os.remove(out_file)
vcfutils.exclude_samples(self.combo_file, out_file, to_exclude, ref_file, config)
def test_3_vcf_split_combine(self):
"""Split a VCF file into SNPs and indels, then combine back together.
"""
with make_workdir() as workdir:
config = load_config(get_post_process_yaml(self.automated_dir, workdir))
config["algorithm"] = {}
ref_file = os.path.join(self.data_dir, "genomes", "hg19", "seq", "hg19.fa")
fname = os.path.join(self.var_dir, "S1-variants.vcf")
snp_file, indel_file = vcfutils.split_snps_indels(fname, ref_file, config)
merge_file = "%s-merge%s.gz" % os.path.splitext(fname)
vcfutils.combine_variant_files([snp_file, indel_file], merge_file, ref_file,
config)
for f in [snp_file, indel_file, merge_file]:
self._remove_vcf(f)
def test_3_vcf_split_combine(self):
"""Split a VCF file into SNPs and indels, then combine back together.
"""
with make_workdir() as workdir:
config = load_config(get_post_process_yaml(self.data_dir, workdir))
config["algorithm"] = {}
ref_file = os.path.join(self.data_dir, "genomes", "hg19", "seq", "hg19.fa")
fname = os.path.join(self.var_dir, "S1-variants.vcf")
snp_file, indel_file = vcfutils.split_snps_indels(fname, ref_file, config)
merge_file = "%s-merge%s.gz" % os.path.splitext(fname)
vcfutils.combine_variant_files([snp_file, indel_file], merge_file, ref_file,
config)
for f in [snp_file, indel_file, merge_file]:
self._remove_vcf(f)
def test_2_vcf_exclusion(self):
"""Exclude samples from VCF files.
"""
# Be back compatible with 0.7.6 -- remove after 0.7.7 release
if prun is None:
return
ref_file = os.path.join(self.data_dir, "genomes", "hg19", "seq", "hg19.fa")
with make_workdir() as workdir:
config = load_config(get_post_process_yaml(self.data_dir, workdir))
config["algorithm"] = {}
out_file = utils.append_stem(self.combo_file, "-exclude")
to_exclude = ["S1"]
if os.path.exists(out_file):
os.remove(out_file)
vcfutils.exclude_samples(self.combo_file, out_file, to_exclude, ref_file, config)
def test_1_parallel_vcf_combine(self):
"""Parallel combination of VCF files, split by chromosome.
"""
files = [os.path.join(self.var_dir, "S1-variants.vcf"), os.path.join(self.var_dir, "S2-variants.vcf")]
ref_file = os.path.join(self.data_dir, "genomes", "hg19", "seq", "hg19.fa")
with make_workdir() as workdir:
config = load_config(get_post_process_yaml(self.automated_dir, workdir))
config["algorithm"] = {}
region_dir = os.path.join(self.var_dir, "S1_S2-combined-regions")
if os.path.exists(region_dir):
shutil.rmtree(region_dir)
if os.path.exists(self.combo_file):
os.remove(self.combo_file)
with prun.start({"type": "local", "cores": 1}, [[config]], config) as run_parallel:
vcfutils.parallel_combine_variants(files, self.combo_file, ref_file, config, run_parallel)
for fname in files:
if os.path.exists(fname + ".gz"):
subprocess.check_call(["gunzip", fname + ".gz"])
if os.path.exists(fname + ".gz.tbi"):
os.remove(fname + ".gz.tbi")
def test_programs(self):
"""Identify programs and versions used in analysis.
"""
with make_workdir() as workdir:
config = load_config(get_post_process_yaml(self.data_dir, workdir))
print programs._get_versions(config)