def run_pipeline(reads, options):
# Instantiate options
output_dir = options['output_dir']
logs_dir = options['logs_dir']
lib_prefix = options['lib_prefix']
step = options['step']
config = options['config']
run_is_paired_end = options['run_is_paired_end']
cutadapt = Software('cutadapt', config['cutadapt']['path'])
fastqc = Software('FastQC', config['fastqc']['path'])
bwa_aln = Software('BWA aln', config['bwa']['path'] + ' aln')
bwa_sampe = Software('BWA sampe', config['bwa']['path'] + ' sampe')
config = options['config']
run_is_paired_end = options['run_is_paired_end']
# Keep list of items to delete
staging_delete = ['tmp']
try:
forward_adapter = options['extra_info']['forward_adapter']
reverse_adapter = options['extra_info']['reverse_adapter']
sailfish_libtype = options['extra_info']['sailfish_libtype']
except KeyError, e:
# TODO Make better exception message
raise KeyError('Some needed extra_info not given.')
# Establish Software instances
cat = Software('cat', '/bin/cat')
cutadapt = Software('cutadapt', config['cutadapt']['path'])
kallisto = Software('kallisto', config['kallisto']['path'])
sailfish = Software('sailfish', config['sailfish']['path'])
# Combine reads with extra sequencing depth
if step <= 1 and len(reads) >= 2:
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
config = options['config']
run_is_paired_end = options['run_is_paired_end']
try:
run_is_stranded = True if options['extra_info']['run_is_stranded'].lower() == 'true' else False
cufflinks_lib_type = options['extra_info']['cufflinks_lib_type']
htseq_stranded = options['extra_info']['htseq_stranded'] # yes|no|reverse
forward_adapter = options['extra_info']['forward_adapter']
reverse_adapter = options['extra_info']['reverse_adapter']
except KeyError, e:
# TODO Make better exception message
raise KeyError('Some needed extra_info not given.')
# Establish Software instances
cutadapt = Software('Cutadapt', config['cutadapt']['path'])
star = Software('STAR Two-Pass', config['STAR']['path'])
novosort = Software('Novosort', config['novosort']['path'])
samtools_flagstat = Software('Samtools Flagstat', config['samtools_flagstat']['path'])
cufflinks = Software('Cufflinks', config['cufflinks']['path'])
htseq = Software('HTSeq', config['htseq']['path'])
# Housekeeping
star_output = []
novosort_outfile = ''
if htseq_stranded not in ['yes', 'no', 'reverse']:
raise ValueError('htseq_stranded is not yes|no|reverse')
if cufflinks_lib_type not in ['ff-firststrand',
'ff-secondstrand',
'ff-unstranded',
'fr-firststrand',
config = options['config']
run_is_paired_end = options['run_is_paired_end']
# Keep list of items to delete
staging_delete = ['tmp']
try:
forward_adapter = options['extra_info']['forward_adapter']
reverse_adapter = options['extra_info']['reverse_adapter']
sailfish_libtype = options['extra_info']['sailfish_libtype']
except KeyError, e:
# TODO Make better exception message
raise KeyError('Some needed extra_info not given.')
# Establish Software instances
cat = Software('cat', '/bin/cat')
cutadapt = Software('cutadapt', config['cutadapt']['path'])
kallisto = Software('kallisto', config['kallisto']['path'])
sailfish = Software('sailfish', config['sailfish']['path'])
# Combine reads with extra sequencing depth
if step <= 1 and len(reads) >= 2:
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
__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
star_output = []
# Keep list of items to delete
staging_delete = ['tmp']
# Get extra options
try:
forward_adapter = options['extra_info']['forward_adapter']
reverse_adapter = options['extra_info']['reverse_adapter']
run_is_stranded = True if options['extra_info']['run_is_stranded'].lower() == 'true' else False
except KeyError, e:
# TODO Make better exception message
raise KeyError('Some needed extra_info not given.')
# Establish software instances
cat = Software('cat', '/bin/cat')
cutadapt = Software('cutadapt', config['cutadapt']['path'])
star = Software('STAR', config['STAR']['path'])
rsem = Software('RSEM', config['RSEM']['path'])
bedGraph_to_bw = Software('bedGraphToBigWig', config['bedGraphToBigWig']['path'])
if step <= 1 and len(reads) >= 2:
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
__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