def load_consequence(consequence=None):
headers = {'Content-Type': 'application/json'}
#resp = requests.post(uri + 'custom/LOAD', headers=headers, auth=auth, data=json.dumps(payload))
# Data definitions
chrom = get_chromosome_number(consequence['Chr']['value'])
chrom_name = chromosome_number2str(chrom)
hgnc = consequence['SYMBOL']['value']
ensembl_id = consequence['Gene']['value']
transcript_ensembl_id = consequence['Feature_ID']['value']
hgmd_name = consequence['RefSeq_ID']['value']
# chromosome
payload = {"id": chrom, "name": chrom_name}
resp = requests.post(uri + 'rest/INSERT/chromosome/X.json',
headers=headers,
auth=auth,
data=json.dumps(payload))
# gene
payload = {"chromosome_id": chrom, "HGNC": hgnc, "ensembl_id": ensembl_id}
resp = requests.post(uri + 'rest/INSERT/gene/X.json',
headers=headers,
auth=auth,
data=json.dumps(payload))
gene_id = resp.id
# transcript
payload = {
"genes_id": gene_id,
"HGMD_name": hgmd_name,
"ensembl_id": transcript_ensembl_id
}
resp = requests.post(uri + 'rest/INSERT/transcript/X.json',
headers=headers,
auth=auth,
data=json.dumps(payload))
return True if resp.status_code == 200 else False
def load_consequence(consequence=None):
headers = {"Content-Type": "application/json"}
# resp = requests.post(uri + 'custom/LOAD', headers=headers, auth=auth, data=json.dumps(payload))
# Data definitions
chrom = get_chromosome_number(consequence["Chr"]["value"])
chrom_name = chromosome_number2str(chrom)
hgnc = consequence["SYMBOL"]["value"]
ensembl_id = consequence["Gene"]["value"]
transcript_ensembl_id = consequence["Feature_ID"]["value"]
hgmd_name = consequence["RefSeq_ID"]["value"]
# chromosome
payload = {"id": chrom, "name": chrom_name}
resp = requests.post(uri + "rest/INSERT/chromosome/X.json", headers=headers, auth=auth, data=json.dumps(payload))
# gene
payload = {"chromosome_id": chrom, "HGNC": hgnc, "ensembl_id": ensembl_id}
resp = requests.post(uri + "rest/INSERT/gene/X.json", headers=headers, auth=auth, data=json.dumps(payload))
gene_id = resp.id
# transcript
payload = {"genes_id": gene_id, "HGMD_name": hgmd_name, "ensembl_id": transcript_ensembl_id}
resp = requests.post(uri + "rest/INSERT/transcript/X.json", headers=headers, auth=auth, data=json.dumps(payload))
return True if resp.status_code == 200 else False
def main():
global options, args
# Be sure to get files bgzipped and tabix indexed
for vcf_file in options.input_vcf:
#if not os.path.isfile(vcf_file + '.gz'):
command_line = "bgzip -c " + vcf_file + " > " + vcf_file + ".gz"
shlex.split(command_line)
retcode = subprocess.check_output(command_line,
stderr=subprocess.STDOUT,
shell=True)
print retcode
#if not os.path.isfile(vcf_file + '.gz.tbi'):
command_line = "tabix -f -p vcf " + vcf_file + ".gz"
shlex.split(command_line)
retcode = subprocess.check_output(command_line,
stderr=subprocess.STDOUT,
shell=True)
print retcode
# First vcf file will be the template file for outputting parameters
template_vcf = vcf.Reader(open(options.input_vcf[0], 'r'))
# Add essential fields in both formats and infos (header information)
template_vcf.formats['FREQ'] = VcfFormat('FREQ', 1, 'String',
'Variant allele frequency')
template_vcf.infos['SFREQ'] = VcfInfo(
'SFREQ', 1, 'Float', 'Maximum variant allele frequency of all samples')
template_vcf.infos['SDP'] = VcfInfo(
'SDP', 1, 'Integer', 'Maximum sequencing depth of all samples')
# Create a list of sorted variant-sites containing chr and position
variant_sites = []
for vcf_file in options.input_vcf:
tmp_vcf = vcf.Reader(open(vcf_file, 'r'))
for record in tmp_vcf:
new_variant_site = (get_chromosome_number(record.CHROM),
record.POS)
if not new_variant_site in variant_sites:
variant_sites.append(new_variant_site)
variant_sites.sort(key=lambda variant: (variant[0], variant[1]))
# Open all files for random access
input_vcf = []
for index, vcf_file in enumerate(options.input_vcf):
input_vcf.append(vcf.Reader(open(vcf_file + '.gz', 'r')))
# Perform tests and checks
if index > 0 and input_vcf[index].samples != template_vcf.samples:
print "INFO: not same sample list in", vcf_file
# Add necessary FORMAT or INFO fields definitions in template
for info in input_vcf[index].infos:
if not info in template_vcf.infos:
template_vcf.infos[info] = input_vcf[index].infos[info]
for myformat in input_vcf[index].formats:
if not myformat in template_vcf.formats:
template_vcf.formats[myformat] = input_vcf[index].formats[
myformat]
# Open output handles
output_vcf = vcf.Writer(open(options.output_vcf, 'w'),
template_vcf,
lineterminator='\n')
output_indels_vcf = vcf.Writer(open(options.output_vcf + '_indels.vcf',
'w'),
template_vcf,
lineterminator='\n')
output_snps_vcf = vcf.Writer(open(options.output_vcf + '_snps.vcf', 'w'),
template_vcf,
lineterminator='\n')
# Now parse each variant-site and fetch information from vcfs:
for my_variant_site in variant_sites:
records = []
for my_vcf in input_vcf:
try:
for record in my_vcf.fetch(
chromosome_number2str(my_variant_site[0]),
my_variant_site[1], my_variant_site[1]):
# vcf.fetch returns also next position if described, must be therefore removed
if record.POS == my_variant_site[1]:
records.append(record)
except KeyError:
# This exception is raised when the primary key is not found in one of the files. No actions required
pass
# master_records are those records for being output to merged vcf. A master record will be created for each
# group of variants from a same variant site that can be merged
master_records = [records[0]]
for record in records[1:]:
add_to_master = False
already_added = False
for master_record in master_records:
if master_record != record:
add_to_master = True
else:
if not master_record.merge(record):
add_to_master = True
else:
already_added = True
if add_to_master and not already_added:
master_records.append(record)
for master_record in master_records:
output_vcf.write_record(master_record)
if master_record.is_snp:
output_snps_vcf.write_record(master_record)
elif master_record.is_indel:
output_indels_vcf.write_record(master_record)
def main():
global options, args
# Be sure to get files bgzipped and tabix indexed
for vcf_file in options.input_vcf:
#if not os.path.isfile(vcf_file + '.gz'):
command_line = "bgzip -c " + vcf_file + " > " + vcf_file + ".gz"
shlex.split(command_line)
retcode = subprocess.check_output(command_line, stderr=subprocess.STDOUT, shell=True)
print retcode
#if not os.path.isfile(vcf_file + '.gz.tbi'):
command_line = "tabix -f -p vcf " + vcf_file + ".gz"
shlex.split(command_line)
retcode = subprocess.check_output(command_line, stderr=subprocess.STDOUT, shell=True)
print retcode
# First vcf file will be the template file for outputting parameters
template_vcf = vcf.Reader(open(options.input_vcf[0], 'r'))
# Add essential fields in both formats and infos (header information)
template_vcf.formats['FREQ'] = VcfFormat('FREQ', 1, 'String', 'Variant allele frequency')
template_vcf.infos['SFREQ'] = VcfInfo('SFREQ', 1, 'Float', 'Maximum variant allele frequency of all samples')
template_vcf.infos['SDP'] = VcfInfo('SDP', 1, 'Integer', 'Maximum sequencing depth of all samples')
# Create a list of sorted variant-sites containing chr and position
variant_sites = []
for vcf_file in options.input_vcf:
tmp_vcf = vcf.Reader(open(vcf_file, 'r'))
for record in tmp_vcf:
new_variant_site = (get_chromosome_number(record.CHROM), record.POS)
if not new_variant_site in variant_sites:
variant_sites.append(new_variant_site)
variant_sites.sort(key=lambda variant: (variant[0], variant[1]))
# Open all files for random access
input_vcf = []
for index, vcf_file in enumerate(options.input_vcf):
input_vcf.append(vcf.Reader(open(vcf_file + '.gz', 'r')))
# Perform tests and checks
if index > 0 and input_vcf[index].samples != template_vcf.samples:
print "INFO: not same sample list in", vcf_file
# Add necessary FORMAT or INFO fields definitions in template
for info in input_vcf[index].infos:
if not info in template_vcf.infos:
template_vcf.infos[info] = input_vcf[index].infos[info]
for myformat in input_vcf[index].formats:
if not myformat in template_vcf.formats:
template_vcf.formats[myformat] = input_vcf[index].formats[myformat]
# Open output handles
output_vcf = vcf.Writer(open(options.output_vcf, 'w'), template_vcf, lineterminator='\n')
output_indels_vcf = vcf.Writer(open(options.output_vcf+'_indels.vcf', 'w'), template_vcf, lineterminator='\n')
output_snps_vcf = vcf.Writer(open(options.output_vcf+'_snps.vcf', 'w'), template_vcf, lineterminator='\n')
# Now parse each variant-site and fetch information from vcfs:
for my_variant_site in variant_sites:
records = []
for my_vcf in input_vcf:
try:
for record in my_vcf.fetch(chromosome_number2str(my_variant_site[0]), my_variant_site[1],
my_variant_site[1]):
# vcf.fetch returns also next position if described, must be therefore removed
if record.POS == my_variant_site[1]:
records.append(record)
except KeyError:
# This exception is raised when the primary key is not found in one of the files. No actions required
pass
# master_records are those records for being output to merged vcf. A master record will be created for each
# group of variants from a same variant site that can be merged
master_records = [records[0]]
for record in records[1:]:
add_to_master = False
already_added = False
for master_record in master_records:
if master_record != record:
add_to_master = True
else:
if not master_record.merge(record):
add_to_master = True
else:
already_added = True
if add_to_master and not already_added:
master_records.append(record)
for master_record in master_records:
output_vcf.write_record(master_record)
if master_record.is_snp:
output_snps_vcf.write_record(master_record)
elif master_record.is_indel:
output_indels_vcf.write_record(master_record)