if run_is_paired_end:
# Aggregate read1s and read2s
read1s, read2s = [], []
for read in reads:
read1, read2 = read.split(':')
read1s.append(read1)
read2s.append(read2)
# Combine reads groups
combined_reads = []
for name, reads_group in [('read1', read1s), ('read2', read2s)]:
combined_read_filename = os.path.join(output_dir, '{}.combined.{}.fastq.gz'.format(lib_prefix, name))
combined_reads.append(combined_read_filename)
staging_delete.append(combined_read_filename)
cat.run(
Parameter(*[read for read in reads_group]),
Redirect(type='1>', dest=combined_read_filename)
)
# Update reads list
reads = [':'.join(combined_reads)]
else:
# Combine reads
combined_read_filename = os.path.join(output_dir, '{}.combined.fastq.gz'.format(lib_prefix))
staging_delete.append(combined_read_filename)
cat.run(
Parameter(*[read for read in reads]),
Redirect(type='1>', dest=combined_read_filename)
)
# Update reads list
reads = [combined_read_filename]
for i, read in enumerate(reads):
if run_is_paired_end:
# Get paired-end reads, construct new filenames
read1, read2 = read.split(':')
trimmed_read1_filename = os.path.join(output_dir,
lib_prefix + '_{}_read1.trimmed.fastq.gz'.format(i))
trimmed_read2_filename = os.path.join(output_dir,
lib_prefix + '_{}_read2.trimmed.fastq.gz'.format(i))
# Run cutadapt
cutadapt.run(
Parameter('--quality-base={}'.format(config['cutadapt']['quality-base'])),
Parameter('--minimum-length=5'),
Parameter('--output={}'.format(trimmed_read1_filename)),
Parameter('--paired-output={}'.format(trimmed_read2_filename)),
Parameter('-a', forward_adapter if forward_adapter else 'ZZZ'),
Parameter('-A', reverse_adapter if reverse_adapter else 'ZZZ'),
Parameter('-q', '30'),
Parameter(read1),
Parameter(read2),
Redirect(type='1>', dest=os.path.join(logs_dir, 'cutadapt.chicago.summary'))
)
# Update reads list
reads[i] = ':'.join([trimmed_read1_filename, trimmed_read2_filename])
else:
# Construct new filename
trimmed_read_filename = os.path.join(output_dir,
lib_prefix + '_{}.trimmed.fastq.gz'.format(i))
# Run cutadapt
cutadapt.run(
# Aggregate read1s and read2s
read1s, read2s = [], []
for read in reads:
read1, read2 = read.split(':')
read1s.append(read1)
read2s.append(read2)
# Combine reads groups
combined_reads = []
for name, reads_group in [('read1', read1s), ('read2', read2s)]:
combined_read_filename = os.path.join(
output_dir,
'{}.combined.{}.fastq.gz'.format(lib_prefix, name))
combined_reads.append(combined_read_filename)
staging_delete.append(combined_read_filename)
cat.run(Parameter(*[read for read in reads_group]),
Redirect(type='1>', dest=combined_read_filename))
# Update reads list
reads = [':'.join(combined_reads)]
else:
# Combine reads
combined_read_filename = os.path.join(
output_dir, '{}.combined.fastq.gz'.format(lib_prefix))
staging_delete.append(combined_read_filename)
cat.run(Parameter(*[read for read in reads]),
Redirect(type='1>', dest=combined_read_filename))
# Update reads list
reads = [combined_read_filename]
# Trim adapters with cutadapt
__author__ = 'Dominic Fitzgerald'
import sys
from dive.components import Software, Parameter, Redirect
sample = sys.argv[1]
# Instantiate software
# Software(software_name, software_path)
picard = Software('picard', '/path/to/java /path/to/picard.jar')
# Run software
# Put as many Parameter and Redirect as needed
# Order matters, so generally Redirect should be last
# Parameter('arguments', 'separated', 'by', 'spaces')
picard.run(
Parameter('I=' + sample),
Parameter('O=/path/to/output'),
Parameter('-T', 'SplitNCigarReads'),
Redirect(type='>', dest='out.txt')
)
# Will produce and execute:
# /path/to/java /path/to/picard.jar I=/path/to/input.bam O=/path/to/output -T SplitNCigarReads > out.txt
if run_is_paired_end:
# Aggregate read1s and read2s
read1s, read2s = [], []
for reads_set in reads:
read1, read2 = reads_set.split(':')
read1s.append(read1)
read2s.append(read2)
# Combine reads groups
combined_reads = []
for name, reads_group in [('read1', read1s), ('read2', read2s)]:
combined_read_filename = os.path.join(output_dir, '{}.combined.{}.fastq.gz'.format(lib_prefix, name))
combined_reads.append(combined_read_filename)
staging_delete.append(combined_read_filename)
cat.run(
Parameter(*[read for read in reads_group]),
Redirect(type='1>', dest=combined_read_filename)
)
# Update reads list
reads = [':'.join(combined_reads)]
else:
# Combine reads
combined_read_filename = os.path.join(output_dir, '{}.combined.fastq.gz'.format(lib_prefix))
staging_delete.append(combined_read_filename)
cat.run(
Parameter(*[read for read in reads]),
Redirect(type='1>', dest=combined_read_filename)
)
# Update reads list
reads = [combined_read_filename]
__author__ = 'Dominic Fitzgerald'
import sys
from dive.components import Software, Parameter, Redirect
sample = sys.argv[1]
# Instantiate software
# Software(software_name, software_path)
picard = Software('picard', '/path/to/java /path/to/picard.jar')
# Run software
# Put as many Parameter and Redirect as needed
# Order matters, so generally Redirect should be last
# Parameter('arguments', 'separated', 'by', 'spaces')
picard.run(Parameter('I=' + sample), Parameter('O=/path/to/output'),
Parameter('-T', 'SplitNCigarReads'),
Redirect(type='>', dest='out.txt'))
# Will produce and execute:
# /path/to/java /path/to/picard.jar I=/path/to/input.bam O=/path/to/output -T SplitNCigarReads > out.txt
