def star_index(job, args):
download_url(url=args.ref, name='ref.fa', work_dir=job.tempDir)
download_url(url=args.gtf, name='annotation.gtf', work_dir=job.tempDir)
# Run STAR to generate index
star_dir = os.path.join(job.tempDir, args.star_name)
os.mkdir(star_dir)
parameters = [
'--runThreadN',
str(args.cores), '--runMode', 'genomeGenerate', '--genomeDir',
'/data/' + args.star_name, '--genomeFastaFiles', 'ref.fa',
'--sjdbGTFfile', 'annotation.gtf'
]
dockerCall(
job,
tool=
'quay.io/ucsc_cgl/star:2.4.2a--bcbd5122b69ff6ac4ef61958e47bde94001cfe80',
workDir=job.tempDir,
parameters=parameters)
# Compress starIndex into a tarball
star_tar = '{}.tar.gz'.format(args.star_name)
tarball_files(star_tar, file_paths=[star_dir], output_dir=job.tempDir)
# Move to output dir or return
tar_path = os.path.join(job.tempDir, star_tar)
if _move_instead_of_return:
move_files([tar_path], args.output_dir)
else:
return job.fileStore.readGlobalFile(tar_path)
def rsem_index(job, args):
download_url(url=args.ref, name='ref.fa', work_dir=job.tempDir)
download_url(url=args.gtf, name='annotation.gtf', work_dir=job.tempDir)
# Run RSEM to generate reference
rsem_dir = os.path.join(job.tempDir, args.rsem_name)
os.mkdir(rsem_dir)
docker_parameters = [
'--entrypoint', 'rsem-prepare-reference', '-v',
'{}:/data'.format(job.tempDir), '--rm', '--log-driver=none'
]
parameters = [
'-p',
str(args.cores), '--gtf', '/data/annotation.gtf', '/data/ref.fa',
os.path.join('/data', args.rsem_name, args.rsem_name)
]
dockerCall(
job,
tool=
'quay.io/ucsc_cgl/rsem:1.2.25--d4275175cc8df36967db460b06337a14f40d2f21',
parameters=parameters,
dockerParameters=docker_parameters)
# Compress rsemRef into a tarball
rsem_tar = '{}.tar.gz'.format(args.rsem_name)
tarball_files(rsem_tar, file_paths=[rsem_dir], output_dir=job.tempDir)
# Move to output dir
tar_path = os.path.join(job.tempDir, rsem_tar)
if _move_instead_of_return:
move_files([tar_path], args.output_dir)
else:
return job.fileStore.readGlobalFile(tar_path)
def kallisto_index(job, args):
if args.transcriptome:
download_url(url=args.transcriptome,
name='transcriptome.fa',
work_dir=job.tempDir)
else:
_create_transcriptome(job, args, job.tempDir)
# Run Kallisto Index
parameters = [
'index', 'transcriptome.fa', '-i',
'/data/{}.index'.format(args.kallisto_name)
]
dockerCall(
job,
tool=
'quay.io/ucsc_cgl/kallisto:0.43.1--355c19b1fb6fbb85f7f8293e95fb8a1e9d0da163',
workDir=job.tempDir,
parameters=parameters)
# Move to output dir
output_path = os.path.join(job.tempDir, args.kallisto_name + '.index')
if _move_instead_of_return:
move_files([output_path], args.output_dir)
else:
return job.fileStore.readGlobalFile(output_path)
def star_index(job, args):
work_dir = job.fileStore.getLocalTempDir()
download_url(url=args.ref, name='ref.fa', work_dir=work_dir)
download_url(url=args.gtf, name='annotation.gtf', work_dir=work_dir)
# Run STAR to generate index
star_dir = os.path.join(work_dir, args.star_name)
os.mkdir(star_dir)
parameters = [
'--runThreadN',
str(args.cores), '--runMode', 'genomeGenerate', '--genomeDir',
'/data/' + args.star_name, '--genomeFastaFiles', 'ref.fa',
'--sjdbGTFfile', 'annotation.gtf'
]
dockerCall(
job,
tool=
'quay.io/ucsc_cgl/star:2.4.2a--bcbd5122b69ff6ac4ef61958e47bde94001cfe80',
workDir=work_dir,
parameters=parameters)
# Compress starIndex into a tarball
subprocess.check_call(['tar', '-zcvf', star_dir + '.tar.gz', star_dir])
# Move to output dir or return
if _move_instead_of_return:
move_files([star_dir + '.tar.gz'], args.output_dir)
else:
return job.fileStore.readGlobalFile(star_dir + '.tar.gz')
def _create_transcriptome(job, args, work_dir):
# Download files to generate transcriptome
download_url(url=args.ref, name='ref.fa', work_dir=work_dir)
download_url(url=args.gtf, name='annotation.gtf', work_dir=work_dir)
parameters = [
'gtf_to_fasta', '/data/annotation.gtf', '/data/ref.fa',
'/data/transcriptome.fa'
]
dockerCall(job,
tool='limesbonn/tophat2',
workDir=work_dir,
parameters=parameters)
def hera_index(job, args):
# Download input files
download_url(url=args.ref, name='ref.fa', work_dir=job.tempDir)
download_url(url=args.gtf, name='annotation.gtf', work_dir=job.tempDir)
# Run Hera build
hera_dir = os.path.join(job.tempDir, args.hera_name)
os.mkdir(hera_dir)
docker_parameters = [
'--rm', '--log-driver=none', '-v', '{}:/data'.format(job.tempDir),
'--entrypoint=/hera/build/hera_build'
]
parameters = [
'--fasta', '/data/ref.fa', '--gtf', '/data/annotation.gtf', '--outdir',
'/data'
]
dockerCall(job,
tool='jvivian/hera',
workDir=job.tempDir,
parameters=parameters,
dockerParameters=docker_parameters)
# No naming options during creation so fix here
if args.hera_name != 'hera-index':
os.rename(os.path.join(job.tempDir, 'hera-index'), hera_dir)
# Compress
hera_tar = '{}.tar.gz'.format(args.hera_name)
tarball_files(hera_tar, file_paths=[hera_dir], output_dir=job.tempDir)
# Move to output dir
tar_path = os.path.join(job.tempDir, hera_tar)
if _move_instead_of_return:
move_files([tar_path], args.output_dir)
else:
return job.fileStore.readGlobalFile(tar_path)
def hera_index(job, args):
work_dir = job.fileStore.getLocalTempDir()
# Download input files
download_url(url=args.ref, name='ref.fa', work_dir=work_dir)
download_url(url=args.gtf, name='annotation.gtf', work_dir=work_dir)
# Run Hera build
hera_dir = os.path.join(work_dir, args.hera_name)
os.mkdir(hera_dir)
docker_parameters = [
'--rm', '--log-driver=none', '-v', '{}:/data'.format(work_dir),
'--entrypoint=/hera/build/hera_build'
]
parameters = [
'--fasta', '/data/ref.fa', '--gtf', '/data/annotation.gtf', '--outdir',
'/data'
]
dockerCall(job,
tool='jvivian/hera',
workDir=work_dir,
parameters=parameters,
dockerParameters=docker_parameters)
# No naming options during creation so fix here
if args.hera_name != 'hera-index':
os.rename(os.path.join(work_dir, 'hera-index'), hera_dir)
# Compress
subprocess.check_call(['tar', '-zcvf', hera_dir + '.tar.gz', hera_dir])
# Move to output dir
if _move_instead_of_return:
move_files([hera_dir + '.tar.gz'], args.output_dir)
else:
return job.fileStore.readGlobalFile(hera_dir + '.tar.gz')