def run_is_complete(self):
"""
Check everyone except NTC has the CNV logs
"""
results_path = Path(self.results_dir)
for sample in self.sample_names:
skip_sample = False
#get the total number of reads in the sample
hs_metrics_file = results_path.joinpath(sample).glob(
f'*{sample}*_HsMetrics.txt')
hs_metrics_file = list(hs_metrics_file)[0]
parsed_hs_metrics_data = parsers.parse_hs_metrics_file(
hs_metrics_file)
total_reads = int(parsed_hs_metrics_data.get('total_reads'))
#CNVKit will not run if number of reads is less than 2 million
if total_reads < 2000000:
skip_sample = True
for ntc in self.ntc_patterns:
if ntc in sample:
skip_sample = True
break
if skip_sample == True:
continue
for marker in self.run_complete_markers:
globbed_marker = results_path.joinpath(sample).glob(marker)
if len(list(globbed_marker)) < 1:
return False
return True
def get_hs_metrics(self):
results_path = Path(self.results_dir)
run_hs_metrics_dict = {}
for sample in self.sample_names:
hs_metrics_file = results_path.glob(f'post_processing/results/metrics/*{sample}_hs_metrics.txt')
hs_metrics_file = list(hs_metrics_file)[0]
parsed_hs_metrics_data = parsers.parse_hs_metrics_file(hs_metrics_file)
run_hs_metrics_dict[sample] = parsed_hs_metrics_data
return run_hs_metrics_dict
def get_hs_metrics(self):
results_path = Path(self.results_dir)
run_hs_metrics_dict = {}
for sample in self.sample_names:
hs_metrics_file = results_path.joinpath(sample).glob(
f'*{sample}*_HsMetrics.txt')
hs_metrics_file = list(hs_metrics_file)[0]
parsed_hs_metrics_data = parsers.parse_hs_metrics_file(
hs_metrics_file)
run_hs_metrics_dict[sample] = parsed_hs_metrics_data
return run_hs_metrics_dict
def run_is_valid(self):
"""
Look for files which have to be present for a run level pipeline to have completed \
correctly.
Look for files which if present indicate the pipeline has not finished correctly e.g. intermediate files.
"""
results_path = Path(self.results_dir)
for sample in self.sample_names:
skip_sample = False
#get the total number of reads in the sample
hs_metrics_file = results_path.joinpath(sample).glob(
f'*{sample}*_HsMetrics.txt')
hs_metrics_file = list(hs_metrics_file)[0]
parsed_hs_metrics_data = parsers.parse_hs_metrics_file(
hs_metrics_file)
total_reads = int(parsed_hs_metrics_data.get('total_reads'))
#CNVKit will not run for the sample if number of reads is less than 2 million
if total_reads < 2000000:
skip_sample = True
for ntc in self.ntc_patterns:
if ntc in sample:
skip_sample = True
break
if skip_sample == True:
continue
for file in self.run_sample_expected_files:
found_file = results_path.joinpath(sample).glob(file)
if len(list(found_file)) != 1:
return False
for file in self.run_expected_files:
found_file = results_path.glob(file)
if len(list(found_file)) != 1:
return False
# check file we do not want to be there are not there
for file in self.run_not_expected_files:
found_file = results_path.glob(file)
if len(list(found_file)) > 0:
return False
return True