def _generate_read_alignment_stats(
self,
lib_names,
result_bam_paths,
unaligned_reads_paths,
output_stats_path,
):
"""Manage the generation of alingment statistics."""
raw_stat_data_writer = RawStatDataWriter(pretty=True)
read_files_and_jobs = {}
if not self._file_needs_to_be_created(output_stats_path):
return
with concurrent.futures.ProcessPoolExecutor(
max_workers=self._args.processes) as executor:
for (
lib_name,
read_alignment_bam_path,
unaligned_reads_path,
) in zip(lib_names, result_bam_paths, unaligned_reads_paths):
read_aligner_stats = ReadAlignerStats()
read_files_and_jobs[lib_name] = executor.submit(
read_aligner_stats.count,
read_alignment_bam_path,
unaligned_reads_path,
)
# Evaluate thread outcome
self._check_job_completeness(read_files_and_jobs.values())
read_files_and_stats = dict([
(lib_name, job.result())
for lib_name, job in read_files_and_jobs.items()
])
raw_stat_data_writer.write(read_files_and_stats, output_stats_path)
def _evaluet_job_and_generate_stat_file(self, read_files_and_jobs):
raw_stat_data_writer = RawStatDataWriter(pretty=True)
# Evaluate thread outcome
self._check_job_completeness(read_files_and_jobs.values())
if not self._file_needs_to_be_created(
self._paths.read_processing_stats_path):
return
# Create a dict of the read file names and the processing
# counting results
read_files_and_stats = dict(
[(lib_name, job.result()) for lib_name, job in
read_files_and_jobs.items()])
raw_stat_data_writer.write(
read_files_and_stats, self._paths.read_processing_stats_path)
def _evaluet_job_and_generate_stat_file(self, read_files_and_jobs):
raw_stat_data_writer = RawStatDataWriter(pretty=True)
# Evaluate thread outcome
self._check_job_completeness(read_files_and_jobs.values())
if not self._file_needs_to_be_created(
self._paths.read_processing_stats_path):
return
# Create a dict of the read file names and the processing
# counting results
read_files_and_stats = dict(
[(lib_name, job.result()) for lib_name, job in
read_files_and_jobs.items()])
raw_stat_data_writer.write(
read_files_and_stats, self._paths.read_processing_stats_path)
def generate_read_alignment_stats(
self, filenames, BAM_files, output_path, output_file):
"""Manage the generation of alingment statistics."""
raw_stat_data_writer = RawStatDataWriter(pretty=True)
read_files_and_jobs = {}
with concurrent.futures.ProcessPoolExecutor(
max_workers=self._args.processes) as executor:
for (filename, BAM_file) in zip(
filenames, BAM_files):
read_aligner_stats = ReadAlignerStats()
read_files_and_jobs[filename] = executor.submit(
read_aligner_stats.count, BAM_files, "NA")
# Evaluate thread outcome
self._helpers.check_job_completeness(read_files_and_jobs.values())
read_files_and_stats = dict(
[(filename, job.result())
for filename, job in read_files_and_jobs.items()])
raw_stat_data_writer.write(
read_files_and_stats, output_file)
def _generate_read_alignment_stats(
self, lib_names, result_bam_paths, unaligned_reads_paths,
output_stats_path):
"""Manage the generation of alingment statistics."""
raw_stat_data_writer = RawStatDataWriter(pretty=True)
read_files_and_jobs = {}
if not self._file_needs_to_be_created(output_stats_path):
return
with concurrent.futures.ProcessPoolExecutor(
max_workers=self._args.processes) as executor:
for (lib_name, read_alignment_bam_path,
unaligned_reads_path) in zip(
lib_names, result_bam_paths, unaligned_reads_paths):
read_aligner_stats = ReadAlignerStats()
read_files_and_jobs[lib_name] = executor.submit(
read_aligner_stats.count, read_alignment_bam_path,
unaligned_reads_path)
# Evaluate thread outcome
self._check_job_completeness(read_files_and_jobs.values())
read_files_and_stats = dict(
[(lib_name, job.result())
for lib_name, job in read_files_and_jobs.items()])
raw_stat_data_writer.write(read_files_and_stats, output_stats_path)