def get_and_submit_bam_stats(self):
from reademptionlib.readalignerstats import ReadAlignerStats
get_bam_stats = ReadAlignerStats()
total_aligned_reads = []
total_uniquely_aligned_reads = []
all_aligned_reads = []
for sample_or_stats_total, sub_dic in (
get_bam_stats.count(self._args.input_coverage, "NA")).items():
for stats_total, value in sub_dic.items():
if sample_or_stats_total == 'stats_total':
if stats_total == 'no_of_uniquely_aligned_reads':
total_uniquely_aligned_reads.append(value)
if stats_total == 'no_of_aligned_reads':
total_aligned_reads.append(value)
else:
for align_type, Nr in value.items():
if align_type == 'no_of_aligned_reads':
all_aligned_reads.append(Nr)
min_no_of_aligned_reads = min(all_aligned_reads)
if not self._args.normalize_by_uniquely:
no_of_aligned_reads = "".join([
'{:.1f}'.format(x) for x in total_aligned_reads])
else:
no_of_aligned_reads = "".join([
'{:.1f}'.format(x) for x in total_uniquely_aligned_reads])
jobs = []
with concurrent.futures.ProcessPoolExecutor(
max_workers=self._args.processes) as executor:
jobs.append(executor.submit(
self.create_coverage_files_TK, float(no_of_aligned_reads),
float(min_no_of_aligned_reads)))
self._check_job_completeness(jobs)
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 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)