def cli(context, repeats_file):
"""Annotate str variants with str status"""
repeat_information = {}
with open(repeats_file, 'r') as file_handle:
repeat_information = parse_repeat_file(file_handle)
if not repeat_information:
LOG.warning("Could not find any repeat info")
context.abort()
header = [
"hgnc_id", "hgnc_symbol", "repid", "ru", "normal_max",
"pathologic_min", "disease"
]
table_line = "| {0} | {1} | {2} | {3} | {4} | {5} | {6} |"
click.echo(
table_line.format(header[0], header[1], header[2], header[3],
header[4], header[5], header[6]))
click.echo(
table_line.format('-------', '-------', '-------', '-------',
'-------', '-------', '-------'))
for entry in repeat_information:
click.echo(
table_line.format(
repeat_information[entry][header[0]],
repeat_information[entry][header[1]],
repeat_information[entry][header[2]],
repeat_information[entry][header[3]],
repeat_information[entry][header[4]],
repeat_information[entry][header[5]],
repeat_information[entry][header[6]],
))
def test_parse_repeat_file(repeats_file_handle):
## GIVEN a file handle with repeat lines
## WHEN parsing the repeat info
repeats_info = parse_repeat_file(repeats_file_handle)
## THEN assert that there are some repeat info returned
assert repeats_info
def cli(context, vcf, repeats_file, loglevel):
"""Annotate str variants with str status"""
coloredlogs.install(level=loglevel)
header_string = 'STR_STATUS'
repeat_information = None
with open(repeats_file, 'r') as file_handle:
repeat_information = parse_repeat_file(file_handle)
if not repeat_information:
LOG.warning("Could not find any repeat info")
context.abort()
vcf_obj = VCF(vcf)
vcf_obj.add_info_to_header({
"ID":
header_string,
"Number":
'A',
"Type":
"String",
"Description":
"Repeat expansion status. Alternatives in ['normal', 'pre_mutation', 'full_mutation']"
})
print_headers(vcf_obj)
for var in vcf_obj:
repeat_string = get_repeat_info(var, repeat_information)
if repeat_string:
var.INFO[header_string] = repeat_string
click.echo(str(var).rstrip())
def test_parse_malformaed_repeat_line_wrong_value():
## GIVEN a some malformed repeat info lines
repeats_info_lines = [
"#hgnc_id hgnc_symbol repid ru normal_max pathologic_min disease",
"10548 ATXN1 ATXN1 CAG hello 45 SCA1"
]
## WHEN parsing the repeat info
## THEN assert that an exception is raised
with pytest.raises(ValueError):
repeats_info = parse_repeat_file(repeats_info_lines)
def test_parse_repeat_line():
## GIVEN a some repeat info lines
repeats_info_lines = [
"#hgnc_id hgnc_symbol repid ru normal_max pathologic_min disease",
"10548 ATXN1 ATXN1 CAG 35 45 SCA1"
]
## WHEN parsing the repeat info
repeats_info = parse_repeat_file(repeats_info_lines)
## THEN assert that the expected repeat info is there
assert 'ATXN1' in repeats_info
## THEN assert that the hgnc_id is there
assert repeats_info['ATXN1']['hgnc_id'] == 10548
assert repeats_info['ATXN1']['hgnc_symbol'] == 'ATXN1'
assert repeats_info['ATXN1']['repid'] == 'ATXN1'
assert repeats_info['ATXN1']['ru'] == 'CAG'
assert repeats_info['ATXN1']['normal_max'] == 35
assert repeats_info['ATXN1']['pathologic_min'] == 45
assert repeats_info['ATXN1']['disease'] == 'SCA1'
def cli(context, repeats_file):
"""Table print repeat info"""
repeat_information = {}
with open(repeats_file, 'r') as file_handle:
repeat_information = parse_repeat_file(file_handle,
repeats_file_type='json')
if not repeat_information:
LOG.warning("Could not find any repeat info")
context.abort()
header = [
"HGNCId", "LocusId", "DisplayRU", "InheritanceMode", "normal_max",
"pathologic_min", "Disease", "SourceDisplay", "SourceId"
]
table_line = "| {0} | {1} | {2} | {3} | {4} | {5} | {6} | {7} | {8} |"
click.echo(
table_line.format(header[0], header[1], header[2], header[3],
header[4], header[5], header[6], header[7],
header[8]))
click.echo(
table_line.format('-------', '-------', '-------', '-------',
'-------', '-------', '-------', '-------',
'-------'))
for entry in repeat_information:
click.echo(
table_line.format(
repeat_information[entry][header[0]],
entry,
repeat_information[entry][header[2]],
repeat_information[entry][header[3]],
repeat_information[entry][header[4]],
repeat_information[entry][header[5]],
repeat_information[entry][header[6]],
repeat_information[entry][header[7]],
repeat_information[entry][header[8]],
))
def cli(context, vcf, family_id, repeats_file, loglevel):
"""Annotate str variants with str status"""
coloredlogs.install(level=loglevel)
LOG.info("Running stranger version %s", __version__)
repeat_information = None
repeats_file_type = 'tsv'
if repeats_file.endswith('.json'):
repeats_file_type = 'json'
LOG.info("Parsing repeats file %s", repeats_file)
with open(repeats_file, 'r') as file_handle:
repeat_information = parse_repeat_file(file_handle, repeats_file_type)
if not repeat_information:
LOG.warning("Could not find any repeat info")
context.abort()
header_definitions = [
{
'id':
'STR_STATUS',
'num':
'A',
'type':
'String',
'desc':
'Repeat expansion status. Alternatives in [normal, pre_mutation, full_mutation]'
},
{
'id': 'STR_NORMAL_MAX',
'num': '1',
'type': 'Integer',
'desc': 'Max number of repeats allowed to call as normal'
},
{
'id': 'STR_PATHOLOGIC_MIN',
'num': '1',
'type': 'Integer',
'desc': 'Min number of repeats required to call as pathologic'
},
{
'id': 'SourceDisplay',
'num': '1',
'type': 'String',
'desc': 'Source for variant definition, display'
},
{
'id': 'Source',
'num': '1',
'type': 'String',
'desc': 'Source collection for variant definition'
},
{
'id': 'SourceId',
'num': '1',
'type': 'String',
'desc': 'Source id for variant definition'
},
{
'id': 'SweGenMean',
'num': '1',
'type': 'Float',
'desc': 'Average number of repeat unit copies in population'
},
{
'id':
'SweGenStd',
'num':
'1',
'type':
'Float',
'desc':
'Standard deviation of number of repeat unit copies in population'
},
{
'id': 'DisplayRU',
'num': '1',
'type': 'String',
'desc': 'Display repeat unit familiar to clinician'
},
{
'id': 'InheritanceMode',
'num': '1',
'type': 'String',
'desc': 'Main mode of inheritance for disorder'
},
{
'id': 'HGNCId',
'num': '1',
'type': 'Integer',
'desc': 'HGNC gene id for associated disease gene'
},
{
'id':
'RankScore',
'num':
'1',
'type':
'String',
'desc':
'RankScore for variant in this family as family(str):score(int)'
},
{
'id': 'Disease',
'num': '1',
'type': 'String',
'desc': 'Associated disorder'
},
]
stranger_headers = []
for hdef in header_definitions:
header = '##INFO=<ID={0},Number={1},Type={2},Description="{3}">'.format(
hdef.get('id'), hdef.get('num'), hdef.get('type'),
hdef.get('desc'))
stranger_headers.append(header)
if vcf.endswith('.gz'):
LOG.info("Vcf is zipped")
vcf_handle = getreader('utf-8')(gzip.open(vcf), errors='replace')
else:
vcf_handle = open(vcf, mode='r', encoding='utf-8', errors='replace')
LOG.info("Parsing variants from %s", vcf)
for line in vcf_handle:
line = line.rstrip()
if line.startswith('#'):
if line.startswith('##'):
click.echo(line)
continue
# Print the new header lines describing stranger annotation
for header in stranger_headers:
click.echo(header)
# Print the vcf header line
header_info = line[1:].split('\t')
click.echo(line)
continue
variant_info = dict(zip(header_info, line.split('\t')))
variant_info['alts'] = variant_info['ALT'].split(',')
variant_info['info_dict'] = get_info_dict(variant_info['INFO'])
repeat_data = get_repeat_info(variant_info, repeat_information)
if repeat_data:
variant_info['info_dict']['STR_STATUS'] = repeat_data[
'repeat_strings']
variant_info['info_dict']['STR_NORMAL_MAX'] = str(
repeat_data['lower'])
variant_info['info_dict']['STR_PATHOLOGIC_MIN'] = str(
repeat_data['upper'])
variant_info['info_dict']['RankScore'] = ':'.join(
[str(family_id),
str(repeat_data['rank_score'])])
for annotate_repeat_key in ANNOTATE_REPEAT_KEYS:
if repeat_data.get(annotate_repeat_key):
variant_info['info_dict'][annotate_repeat_key] = str(
repeat_data[annotate_repeat_key])
click.echo(get_variant_line(variant_info, header_info))
def cli(context, vcf, repeats_file, loglevel):
"""Annotate str variants with str status"""
coloredlogs.install(level=loglevel)
LOG.info("Running stranger version %s", __version__)
repeat_information = None
repeats_file_type = 'tsv'
if repeats_file.endswith('.json'):
repeats_file_type = 'json'
LOG.info("Parsing repeats file %s", repeats_file)
with open(repeats_file, 'r') as file_handle:
repeat_information = parse_repeat_file(file_handle, repeats_file_type)
if not repeat_information:
LOG.warning("Could not find any repeat info")
context.abort()
header_definitions = [
{
'id': 'STR_STATUS', 'num': 'A', 'type': 'String',
'desc': 'Repeat expansion status. Alternatives in [normal, pre_mutation, full_mutation]'
},
{
'id': 'STR_NORMAL_MAX', 'num': '1', 'type': 'Integer',
'desc': 'Max number of repeats allowed to call as normal'
},
{
'id': 'STR_FULLMUT_MIN', 'num': '1', 'type': 'Integer',
'desc': 'Min number of repeats required to call as full mutation'
}
]
stranger_headers = []
for hdef in header_definitions:
header = '##INFO=<ID={0},Number={1},Type={2},Description="{3}">'.format(
hdef.get('id'), hdef.get('num'), hdef.get('type'), hdef.get('desc'))
stranger_headers.append(header)
if vcf.endswith('.gz'):
LOG.info("Vcf is zipped")
vcf_handle = getreader('utf-8')(gzip.open(vcf), errors='replace')
else:
vcf_handle = open(vcf, mode='r', encoding='utf-8', errors='replace')
LOG.info("Parsing variants from %s", vcf)
for line in vcf_handle:
line = line.rstrip()
if line.startswith('#'):
if line.startswith('##'):
click.echo(line)
continue
# Print the new header lines describing stranger annotation
for header in stranger_headers:
click.echo(header)
# Print the vcf header line
header_info = line[1:].split('\t')
click.echo(line)
continue
variant_info = dict(zip(header_info, line.split('\t')))
variant_info['alts'] = variant_info['ALT'].split(',')
variant_info['info_dict'] = get_info_dict(variant_info['INFO'])
repeat_data = get_repeat_info(variant_info, repeat_information)
if repeat_data:
variant_info['info_dict']['STR_STATUS'] = repeat_data['repeat_strings']
variant_info['info_dict']['STR_NORMAL_MAX'] = str(repeat_data['lower'])
variant_info['info_dict']['STR_FULLMUT_MIN'] = str(repeat_data['upper'])
click.echo(get_variant_line(variant_info, header_info))