def do_auxiliary_profile_data(self):
self.progress.new('Splitting "%s"' % self.bin_id)
self.progress.update('Subsetting the auxiliary data (for profile db)')
new_auxiliary_profile_data_path = dbops.get_auxiliary_data_path_for_profile_db(
self.bin_profile_db_path)
parent_auxiliary_profile_data_path = self.summary.auxiliary_data_path
bin_profile_auxiliary = auxiliarydataops.AuxiliaryDataForSplitCoverages(
new_auxiliary_profile_data_path,
self.contigs_db_hash,
create_new=True)
parent_profile_auxiliary = auxiliarydataops.AuxiliaryDataForSplitCoverages(
parent_auxiliary_profile_data_path,
self.summary.a_meta['contigs_db_hash'])
for split_name in self.split_names:
sample_coverages = parent_profile_auxiliary.get(split_name)
for sample_name in sample_coverages:
bin_profile_auxiliary.append(split_name, sample_name,
sample_coverages[sample_name])
bin_profile_auxiliary.store()
bin_profile_auxiliary.close()
parent_profile_auxiliary.close()
if self.compress_auxiliary_data:
self.progress.update(
'Compressing the profile db auxiliary data file ...')
utils.gzip_compress_file(new_auxiliary_profile_data_path)
self.progress.end()
def do_auxiliary_profile_data(self):
self.progress.new('Splitting "%s"' % self.bin_id)
self.progress.update('Subsetting the auxiliary data (for profile db)')
new_auxiliary_profile_data_path = dbops.get_auxiliary_data_path_for_profile_db(self.bin_profile_db_path)
parent_auxiliary_profile_data_path = self.summary.auxiliary_data_path
bin_profile_auxiliary = auxiliarydataops.AuxiliaryDataForSplitCoverages(new_auxiliary_profile_data_path,
self.contigs_db_hash,
create_new=True)
parent_profile_auxiliary = auxiliarydataops.AuxiliaryDataForSplitCoverages(parent_auxiliary_profile_data_path,
self.summary.a_meta['contigs_db_hash'])
for split_name in self.split_names:
sample_coverages = parent_profile_auxiliary.get(split_name)
for sample_name in sample_coverages:
bin_profile_auxiliary.append(split_name, sample_name, sample_coverages[sample_name])
bin_profile_auxiliary.store()
bin_profile_auxiliary.close()
parent_profile_auxiliary.close()
if self.compress_auxiliary_data:
self.progress.update('Compressing the profile db auxiliary data file ...')
utils.gzip_compress_file(new_auxiliary_profile_data_path)
self.progress.end()
def store_short_reads_for_splits(self):
self.sanity_check()
if not self.sanity_checked:
raise ConfigError(
"store_short_reads_for_splits :: Cannot be called before running sanity_check"
)
short_reds_for_splits_dict = self.get_short_reads_for_splits_dict()
self.progress.new("Storing reads")
self.progress.update("...")
if self.split_R1_and_R2:
for read_type in sorted(list(short_reds_for_splits_dict.keys())):
output_file_path = '%s_%s.fa' % (self.output_file_prefix,
read_type)
utils.store_dict_as_FASTA_file(
short_reds_for_splits_dict[read_type], output_file_path)
if self.gzip:
utils.gzip_compress_file(output_file_path)
output_file_path = output_file_path + ".gz"
self.run.info('Output file for %s' % read_type,
output_file_path,
progress=self.progress)
self.progress.end()
self.run.info('Num paired-end reads stored',
pp(len(short_reds_for_splits_dict['R1'])),
mc='green',
nl_before=1)
self.run.info('Num unpaired reads stored',
pp(len(short_reds_for_splits_dict['UNPAIRED'])),
mc='green')
else:
output_file_path = self.output_file_path or 'short_reads.fa'
utils.store_dict_as_FASTA_file(short_reds_for_splits_dict['all'],
output_file_path)
if self.gzip:
utils.gzip_compress_file(output_file_path)
output_file_path = output_file_path + ".gz"
self.progress.end()
self.run.info('Output file for all short reads', output_file_path)
self.run.info('Num reads stored',
pp(len(short_reds_for_splits_dict['all'])),
mc='green')
def store_short_reads_for_splits(self):
self.sanity_check()
if not self.sanity_checked:
raise ConfigError("store_short_reads_for_splits :: Cannot be called before running sanity_check")
short_reds_for_splits_dict = self.get_short_reads_for_splits_dict()
self.progress.new("Storing reads")
self.progress.update("...")
if self.split_R1_and_R2:
for read_type in sorted(list(short_reds_for_splits_dict.keys())):
output_file_path = '%s_%s.fa' % (self.output_file_prefix, read_type)
utils.store_dict_as_FASTA_file(short_reds_for_splits_dict[read_type], output_file_path)
if self.gzip:
utils.gzip_compress_file(output_file_path)
output_file_path = output_file_path + ".gz"
self.run.info('Output file for %s' % read_type, output_file_path, progress=self.progress)
self.progress.end()
self.run.info('Num paired-end reads stored',pp(len(short_reds_for_splits_dict['R1'])), mc='green', nl_before=1)
self.run.info('Num unpaired reads stored',pp(len(short_reds_for_splits_dict['UNPAIRED'])), mc='green')
else:
output_file_path = self.output_file_path or 'short_reads.fa'
utils.store_dict_as_FASTA_file(short_reds_for_splits_dict['all'], output_file_path)
if self.gzip:
utils.gzip_compress_file(output_file_path)
output_file_path = output_file_path + ".gz"
self.progress.end()
self.run.info('Output file for all short reads',output_file_path)
self.run.info('Num reads stored', pp(len(short_reds_for_splits_dict['all'])), mc='green')