def run(items):
"""Normalization and log2 ratio calculation plus CNV calling for full cohort.
- Combine coverage of each region for each sample
- Prepare read counts for each sample
- Normalize coverages in cohort by gene and sample, and calculate log2 ratios
- Call amplifications and deletions
"""
items = [utils.to_single_data(x) for x in items]
work_dir = _sv_workdir(items[0])
input_backs = list(set(filter(lambda x: x is not None,
[dd.get_background_cnv_reference(d, "seq2c") for d in items])))
coverage_file = _combine_coverages(items, work_dir, input_backs)
read_mapping_file = _calculate_mapping_reads(items, work_dir, input_backs)
normal_names = []
if input_backs:
with open(input_backs[0]) as in_handle:
for line in in_handle:
if len(line.split()) == 2:
normal_names.append(line.split()[0])
normal_names += [dd.get_sample_name(x) for x in items if population.get_affected_status(x) == 1]
seq2c_calls_file = _call_cnv(items, work_dir, read_mapping_file, coverage_file, normal_names)
items = _split_cnv(items, seq2c_calls_file, read_mapping_file, coverage_file)
return items
def run(items):
"""Normalization and log2 ratio calculation plus CNV calling for full cohort.
- Combine coverage of each region for each sample
- Prepare read counts for each sample
- Normalize coverages in cohort by gene and sample, and calculate log2 ratios
- Call amplifications and deletions
"""
items = [utils.to_single_data(x) for x in items]
work_dir = _sv_workdir(items[0])
input_backs = list(
set(
filter(
lambda x: x is not None,
[dd.get_background_cnv_reference(d, "seq2c") for d in items])))
coverage_file = _combine_coverages(items, work_dir, input_backs)
read_mapping_file = _calculate_mapping_reads(items, work_dir, input_backs)
normal_names = []
if input_backs:
with open(input_backs[0]) as in_handle:
for line in in_handle:
if len(line.split()) == 2:
normal_names.append(line.split()[0])
normal_names += [
dd.get_sample_name(x) for x in items
if population.get_affected_status(x) == 1
]
seq2c_calls_file = _call_cnv(items, work_dir, read_mapping_file,
coverage_file, normal_names)
items = _split_cnv(items, seq2c_calls_file, read_mapping_file,
coverage_file)
return items
def find_case_control(items):
"""Find case/control items in a population of multiple samples.
"""
cases = []
controls = []
for data in items:
if population.get_affected_status(data) == 1:
controls.append(data)
else:
cases.append(data)
return cases, controls
def find_case_control(items):
"""Find case/control items in a population of multiple samples.
"""
cases = []
controls = []
for data in items:
if population.get_affected_status(data) == 1:
controls.append(data)
else:
cases.append(data)
return cases, controls
def run(items):
"""Normalization and log2 ratio calculation plus CNV calling for full cohort.
- Combine coverage of each region for each sample
- Prepare read counts for each sample
- Normalize coverages in cohort by gene and sample, and calculate log2 ratios
- Call amplifications and deletions
"""
items = [utils.to_single_data(x) for x in items]
work_dir = _sv_workdir(items[0])
coverage_file = _combine_coverages(items, work_dir)
read_mapping_file = _calculate_mapping_reads(items, work_dir)
normal_names = [dd.get_sample_name(x) for x in items if population.get_affected_status(x) == 1]
seq2c_calls_file = _call_cnv(items, work_dir, read_mapping_file, coverage_file, normal_names)
items = _split_cnv(items, seq2c_calls_file, read_mapping_file)
return items
def run(items):
"""Normalization and log2 ratio calculation plus CNV calling for full cohort.
- Combine coverage of each region for each sample
- Prepare read counts for each sample
- Normalize coverages in cohort by gene and sample, and calculate log2 ratios
- Call amplifications and deletions
"""
items = [utils.to_single_data(x) for x in items]
work_dir = _sv_workdir(items[0])
coverage_file = _combine_coverages(items, work_dir)
read_mapping_file = _calculate_mapping_reads(items, work_dir)
normal_names = [dd.get_sample_name(x) for x in items if population.get_affected_status(x) == 1]
seq2c_calls_file = _call_cnv(items, work_dir, read_mapping_file, coverage_file, normal_names)
_split_cnv(items, seq2c_calls_file)
return items
