def create_read_array(bamfile, index, aws_upload_key, min_poly_t,
max_transcript_length):
"""Create or download a ReadArray object.
:param max_transcript_length:
:param str bamfile: filename of .bam file
:param str index: directory containing index files
:param str aws_upload_key: key where aws files should be uploaded
:param int min_poly_t: minimum number of poly_t nucleotides for a read to be valid
:returns ReadArray, UploadManager: ReadArray object, bamfile ProcessManager
"""
log.info('Filtering aligned records and constructing record database.')
# Construct translator
translator = GeneIntervals(
index + 'annotations.gtf', max_transcript_length=max_transcript_length)
read_array = ReadArray.from_alignment_file(
bamfile, translator, min_poly_t)
# converting sam to bam and uploading to S3, else removing bamfile
if aws_upload_key:
log.info('Uploading bam file to S3.')
upload_bam = 'aws s3 mv {fname} {s3link}{prefix}_Aligned.out.bam'.format(
fname=bamfile, s3link=aws_upload_key, prefix=args.output_prefix)
print(upload_bam)
upload_manager = io.ProcessManager(upload_bam)
upload_manager.run_all()
else:
log.info('Removing bamfile for memory management.')
rm_bamfile = 'rm %s' % bamfile
io.ProcessManager(rm_bamfile).run_all()
upload_manager = None
return read_array, upload_manager
def align_fastq_records(
merged_fastq, dir_, star_args, star_index, n_proc,
aws_upload_key) -> (str, str, io.ProcessManager):
"""
Align fastq records.
:param merged_fastq: str, path to merged .fastq file
:param dir_: str, stem for output files
:param star_args: dict, extra keyword arguments for STAR
:param star_index: str, file path to directory containing STAR index
:param n_proc: int, number of STAR processes to initiate
:param aws_upload_key: str, location to upload files, or None if seqc was
initiated from a merged fastq file.
:return bamfile, input_data, upload_manager: (str, str, io.ProcessManager)
name of .sam file containing aligned reads, indicator of which data was used as
input, and a ProcessManager for merged fastq files
"""
log.info('Aligning merged fastq records.')
alignment_directory = dir_ + '/alignments/'
os.makedirs(alignment_directory, exist_ok=True)
if star_args is not None:
star_kwargs = dict(a.strip().split('=') for a in star_args)
else:
star_kwargs = {}
bamfile = star.align(
merged_fastq, star_index, n_proc, alignment_directory,
**star_kwargs)
if aws_upload_key:
log.info('Gzipping merged fastq file.')
if pigz:
pigz_zip = "pigz --best -k -f {fname}".format(fname=merged_fastq)
else:
pigz_zip = "gzip -kf {fname}".format(fname=merged_fastq)
pigz_proc = io.ProcessManager(pigz_zip)
pigz_proc.run_all()
pigz_proc.wait_until_complete() # prevents slowing down STAR alignment
merged_fastq += '.gz' # reflect gzipped nature of file
log.info('Uploading gzipped merged fastq file to S3.')
merge_upload = 'aws s3 mv {fname} {s3link}'.format(
fname=merged_fastq, s3link=aws_upload_key)
upload_manager = io.ProcessManager(merge_upload)
upload_manager.run_all()
else:
log.info('Removing merged fastq file for memory management.')
rm_merged = 'rm %s' % merged_fastq
io.ProcessManager(rm_merged).run_all()
upload_manager = None
return bamfile, upload_manager
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