def organism_filter(
fastq_r1, fastq_r2, filtered_fastq_r1, filtered_fastq_r2,
detailed_metrics, summary_metrics, tempdir, cell_id, params,
reference, docker_image=None, filter_contaminated_reads=False,
):
# fastq screen tries to skip if files from old runs are available
if os.path.exists(tempdir):
shutil.rmtree(tempdir)
helpers.makedirs(tempdir)
tagged_fastq_r1, tagged_fastq_r2 = run_fastq_screen_paired_end(
fastq_r1, fastq_r2, tempdir, params, docker_image=docker_image
)
reader = fastqutils.PairedTaggedFastqReader(tagged_fastq_r1, tagged_fastq_r2)
counts = reader.gather_counts()
write_detailed_counts(counts, detailed_metrics, cell_id)
write_summary_counts(counts, summary_metrics, cell_id)
if filter_contaminated_reads:
filter_reads(
tagged_fastq_r1, tagged_fastq_r2, filtered_fastq_r1,
filtered_fastq_r2, reference
)
else:
# use the full tagged fastq downstream
# with organism type information in readname
re_tag_reads(tagged_fastq_r1, filtered_fastq_r1)
re_tag_reads(tagged_fastq_r2, filtered_fastq_r2)
def organism_filter(fastq_r1, fastq_r2, filtered_fastq_r1, filtered_fastq_r2,
detailed_metrics, summary_metrics, tempdir, cell_id,
params):
# fastq screen tries to skip if files from old runs are available
if os.path.exists(tempdir):
shutil.rmtree(tempdir)
helpers.makedirs(tempdir)
tagged_fastq_r1, tagged_fastq_r2 = run_fastq_screen_paired_end(
fastq_r1,
fastq_r2,
tempdir,
params,
)
reader = fastqutils.PairedTaggedFastqReader(tagged_fastq_r1,
tagged_fastq_r2)
counts = reader.gather_counts()
write_detailed_counts(counts, detailed_metrics, cell_id, params)
write_summary_counts(counts, summary_metrics, cell_id, params)
utils.filter_tag_reads(tagged_fastq_r1, tagged_fastq_r2, filtered_fastq_r1,
filtered_fastq_r2, params)
def filter_reads(input_r1, input_r2, output_r1, output_r2, reference):
reader = fastqutils.PairedTaggedFastqReader(input_r1, input_r2)
with helpers.getFileHandle(output_r1,
'wt') as writer_r1, helpers.getFileHandle(
output_r2, 'wt') as writer_r2:
for read_1, read_2 in reader.filter_read_iterator(reference):
read_1 = reader.add_tag_to_read_comment(read_1)
read_2 = reader.add_tag_to_read_comment(read_2)
for line in read_1:
writer_r1.write(line)
for line in read_2:
writer_r2.write(line)
def filter_tag_reads(input_r1, input_r2, output_r1, output_r2, params):
genomes = [v['name'] for v in params['genomes']]
if not params['filter_tags']:
filter_tags = set()
else:
filter_tags = set(params['filter_tags'])
reader = fastqutils.PairedTaggedFastqReader(input_r1, input_r2)
with helpers.getFileHandle(output_r1,
'wt') as writer_r1, helpers.getFileHandle(
output_r2, 'wt') as writer_r2:
for read_1, read_2 in reader.filter_read_iterator(
genomes, filter_tags):
read_1 = reader.add_tag_to_read_comment(read_1)
read_2 = reader.add_tag_to_read_comment(read_2)
for line in read_1:
writer_r1.write(line)
for line in read_2:
writer_r2.write(line)