def merge_fastq_files(
technology_platform, barcode_fastq: [str], output_stem: str,
genomic_fastq: [str]) -> (str, int):
"""annotates genomic fastq with barcode information; merging the two files.
:param technology_platform: class from platforms.py that defines the
characteristics of the data being processed
:param barcode_fastq: list of str names of fastq files containing barcode
information
:param output_stem: str, stem for output files
:param genomic_fastq: list of str names of fastq files containing genomic
information
:returns str merged_fastq: name of merged fastq file
"""
log.info('Merging genomic reads and barcode annotations.')
merged_fastq = fastq.merge_paired(
merge_function=technology_platform.merge_function,
fout=output_stem + '_merged.fastq',
genomic=genomic_fastq,
barcode=barcode_fastq)
# delete genomic/barcode fastq files after merged.fastq creation
log.info('Removing original fastq file for memory management.')
delete_fastq = ' '.join(['rm'] + genomic_fastq + barcode_fastq)
io.ProcessManager(delete_fastq).run_all()
return merged_fastq
def merge_fastq_files(
technology_platform,
barcode_fastq: [str],
output_stem: str,
genomic_fastq: [str],
) -> (str, int):
"""annotates genomic fastq with barcode information; merging the two files.
:param technology_platform: class from platforms.py that defines the
characteristics of the data being processed
:param barcode_fastq: list of str names of fastq files containing barcode
information
:param output_stem: str, stem for output files
:param genomic_fastq: list of str names of fastq files containing genomic
information
:returns str merged_fastq: name of merged fastq file
"""
# hack:
# Due to the non-platform agnostic glob behavior,
# it is possible that L001_R1 is merged with L002_R2 (not L001_R2).
# to avoid this problem, we first sort.
# this is a temporary hacky solution
barcode_fastq = sorted(barcode_fastq)
genomic_fastq = sorted(genomic_fastq)
log.info("Merging genomic reads and barcode annotations.")
for bar_fq, gen_fq in zip(barcode_fastq, genomic_fastq):
log.info("Merge {} with {}".format(os.path.basename(bar_fq),
os.path.basename(gen_fq)))
merged_fastq = fastq.merge_paired(
merge_function=technology_platform.merge_function,
fout=output_stem + "_merged.fastq",
genomic=genomic_fastq,
barcode=barcode_fastq,
)
# delete genomic/barcode fastq files after merged.fastq creation
# log.info('Removing original fastq file for memory management.')
# delete_fastq = ' '.join(['rm'] + genomic_fastq + barcode_fastq)
# io.ProcessManager(delete_fastq).run_all()
return merged_fastq