def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--input_files',
type=str,
help='S3 paths for input files',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
argparser.add_argument('--working_dir', type=str, default='/scratch')
argparser.add_argument('--results_path', type=str, default='/scratch')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
# Download fastq files and reference files
print('Downloading FASTQs')
fastq_files = generate_input_string(args.input_files, working_dir)
print('Running Kraken')
kraken_folder = run_kraken(args.cmd_args, fastq_files, working_dir)
print('Uploading results to %s' % args.results_path)
upload_folder(args.results_path, kraken_folder)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print('Completed')
def main():
argparser = ArgumentParser()
argparser.add_argument('--vcf_s3_path',
type=str,
help='VCF s3 path',
required=True)
argparser.add_argument('--annotated_vcf_s3_path',
type=str,
help='Annotated vcf s3 path',
required=True)
argparser.add_argument('--working_dir', type=str, default='/scratch')
argparser.add_argument('--cmd_args',
type=str,
help='arguments/options for snpeff',
default='-t')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
print('Downloading vcf')
local_vcf_path = download_file(args.vcf_s3_path, working_dir)
print('Running snpeff')
annotated_vcf_path = run_snpeff(local_vcf_path, args.cmd_args, working_dir)
print('Uploading %s to %s' %
(annotated_vcf_path, args.annotated_vcf_s3_path))
upload_file(args.annotated_vcf_s3_path, annotated_vcf_path)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print('Completed')
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--bam_s3_path',
type=str,
help='BAM s3 path',
required=True)
file_path_group.add_argument('--bai_s3_path',
type=str,
help='BAM Index s3 path',
required=True)
file_path_group.add_argument('--vcf_s3_path',
type=str,
help='VCF s3 path',
required=True)
file_path_group.add_argument('--reference_s3_path',
type=str,
help='Reference file s3 path',
required=True)
file_path_group.add_argument('--reference_index_s3_path',
type=str,
help='Reference file index s3 path',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--memory',
type=str,
help='Memory (in GB) for strelka to use',
default=28)
run_group.add_argument('--cmd_args',
type=str,
help='Additional arguments for platypus',
default='')
argparser.add_argument('--working_dir', type=str, default='/scratch')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
print("Downloading bam")
local_bam_path = download_file(args.bam_s3_path, working_dir)
local_bai_path = download_file(args.bai_s3_path, working_dir)
print("BAM and index donwloaded to %s and %s" %
(local_bam_path, local_bai_path))
print("Downloading reference")
local_reference_path = download_file(args.reference_s3_path, working_dir)
local_reference_index_path = download_file(args.reference_index_s3_path,
working_dir)
print("Reference downloaded to %s. Index to %s" %
(local_reference_path, local_reference_index_path))
print("Running Strelka")
local_vcf_path = run_strelka(local_bam_path, local_reference_path,
args.memory, args.cmd_args, working_dir)
print("Uploading %s to %s" % (local_vcf_path, args.vcf_s3_path))
upload_folder(args.vcf_s3_path, local_vcf_path)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print("Completed")
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--input_file',
type=str,
help='s3 path',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
argparser.add_argument('--working_dir', type=str, default='/docker_share')
argparser.add_argument('--results_path', type=str, default='/scratch')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
# Download fastq files and reference files
print('Downloading FASTQs')
input_file = download_fastq_file(args.input_file, working_dir)
print('Running busco')
busco_folder = run_busco(args.cmd_args, input_file, working_dir)
print('Uploading results to %s' % args.results_path)
upload_results(args.results_path, busco_folder)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print('Completed')
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--bam_s3_folder_path',
type=str,
help='BAM s3 path',
required=True)
file_path_group.add_argument('--fastq1_s3_path',
type=str,
help='FASTQ1 s3 path',
required=True)
file_path_group.add_argument('--fastq2_s3_path',
type=str,
help='FASTQ2 s3 path',
required=True)
file_path_group.add_argument('--reference_s3_path',
type=str,
help='reference file',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--memory',
type=str,
help='Memory for Isaac in GB',
default='76')
run_group.add_argument('--cmd_args',
type=str,
help='Arguments for Isaac',
default=' ')
argparser.add_argument('--working_dir', type=str, default='/scratch')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
# Download fastq files and reference files
print('Downloading FASTQs')
fastq_folder_path = download_fastq_files(args.fastq1_s3_path,
args.fastq2_s3_path, working_dir)
print('Downloading Reference')
reference_folder_path = download_reference(args.reference_s3_path,
working_dir)
print('Running Isaac')
bam_folder_path = run_isaac(reference_folder_path, fastq_folder_path,
args.memory, args.cmd_args, working_dir)
print('Uploading results to %s' % args.bam_s3_folder_path)
upload_bam(args.bam_s3_folder_path, bam_folder_path)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print('Completed')
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument(
'--input_flags',
type=str,
help='All the flags for the files, in correct order',
required=True)
file_path_group.add_argument(
'--input_files',
type=str,
help='All the S3 file locations, in correct order',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
argparser.add_argument('--working_dir', type=str, default='/scratch')
argparser.add_argument('--results_path', type=str, default='/scratch')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
print('Downloading files and forming input parameters')
print('input flags', args.input_flags)
print('input_files', args.input_files)
input_arguments = generate_input_string(args.input_files, args.input_flags,
working_dir)
#Download to container the fastq files
try:
print('Running SPAdes')
results_folder_path = run_spades(input_arguments, args.cmd_args,
working_dir)
except Exception as e:
upload_results(args.results_path, working_dir)
upload_results(args.results_path, results_folder_path)
print('Cleaning the working dir')
delete_working_dir(working_dir)
print('Completed')
"""
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--bam_s3_path',
type=str,
help='BAM s3 path',
required=True)
file_path_group.add_argument('--reference_s3_path',
type=str,
help='reference file',
required=True)
file_path_group.add_argument('--bam_stats_s3_path',
type=str,
help='S3 Path to upload stats',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--cmd_args',
type=str,
help='Arguments for platypus',
default='')
argparser.add_argument('--working_dir', type=str, default='/scratch')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
print("Downloading bam")
local_bam_path = download_file(args.bam_s3_path, working_dir)
print("BAM downloaded to %s" % local_bam_path)
print("Downloading reference")
local_reference_path = download_file(args.reference_s3_path, working_dir)
print("Reference downloaded to %s." % local_reference_path)
print("Running samtools stats")
local_stats_path = run_samtools_stats(local_bam_path, local_reference_path,
args.cmd_args, working_dir)
print("Uploading %s to %s" % (local_stats_path, args.bam_stats_s3_path))
upload_file(args.bam_stats_s3_path, local_stats_path)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print("Completed")
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--fastq1_s3_path',
type=str,
help='FASTQ1 s3 path',
required=True)
file_path_group.add_argument('--fastq2_s3_path',
type=str,
help='FASTQ2 s3 path',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
argparser.add_argument('--working_dir', type=str, default='/scratch')
argparser.add_argument('--results_path', type=str, default='/scratch')
args = argparser.parse_args()
working_dir = generate_working_dir(args.working_dir)
# Download fastq files and reference files
print('Downloading FASTQs')
fastq_files = '{0} {1}'.format(
download_fastq_file(args.fastq1_s3_path, working_dir),
download_fastq_file(args.fastq2_s3_path, working_dir))
print('Running trim_galore')
trimmed_folder = run_trim_galore(args.cmd_args, fastq_files, working_dir)
print('Uploading results to %s' % args.results_path)
upload_bam(args.results_path, trimmed_folder)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print('Completed')
"""
def main():
args = parseArguments()
logging.basicConfig(level=args.log_level)
logger.info("Run cohort-matcher Docker CLI v%s", __version__)
logger.info(args)
working_dir = generate_working_dir(args.working_dir)
# Download fastq files and reference files
logger.info('Downloading bam sheets')
set1_bamsheet = download_file(args.set1_s3_path, working_dir)
set2_bamsheet = download_file(args.set2_s3_path, working_dir)
# Download reference bundles
if args.set1_reference == 'hg19' or args.set2_reference == 'hg19':
logger.info("Downloading hg19 reference bundle")
download_file('s3://bmsrd-ngs-repo/reference/hg19-cohort-matcher.tar.bz2', working_dir)
logger.info("Uncompressing hg19 reference bundle")
uncompress(os.path.join(working_dir, 'hg19-cohort-matcher.tar.bz2'), working_dir)
if args.set2_reference == 'GRCh37' or args.set2_reference == 'GRCh37':
logger.info("Downloading GRCh37 reference bundle")
download_file('s3://bmsrd-ngs-repo/reference/GRCh37-cohort-matcher.tar.bz2', working_dir)
logger.info("Uncompressing GRCh37 reference bundle")
uncompress(os.path.join(working_dir, 'GRCh37-cohort-matcher.tar.bz2', working_dir))
# Run cohort-matcher
logger.info('Running cohort-matcher')
if args.max_jobs is None:
max_jobs = multiprocessing.cpu_count()
else:
max_jobs = args.max_jobs
output_folder_path = run_cohort_matcher(args.log_level, set1_bamsheet, set2_bamsheet,
args.set1_reference, args.set2_reference,
working_dir, args.output_prefix, max_jobs)
logger.info('Uploading results to %s', args.s3_output_folder_path)
#upload_bam(args.bam_s3_folder_path, bam_folder_path)
logger.info('Cleaning up working dir')
delete_working_dir(working_dir)
logger.info('Completed')
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--vcf_s3_path',
type=str,
help='VCF s3 path',
required=True)
file_path_group.add_argument('--bam_s3_path',
type=str,
help='BAM s3 path',
required=True)
file_path_group.add_argument('--bai_s3_path',
type=str,
help='BAI s3 path',
required=True)
file_path_group.add_argument('--results_s3_path',
type=str,
help='S3 Path to upload stats',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--cmd_args',
type=str,
help='Additional Arguments',
default=None,
nargs='*',
action='store',
dest='opt_list')
#argparser.add_argument('--working_dir', type=str, default='/scratch')
args = argparser.parse_args()
total_size = 0
for obj in [args.vcf_s3_path, args.bam_s3_path, args.bai_s3_path]:
total_size += get_size(obj)
# add more for formatting loss
total_size += 2e9
total_size = int(total_size)
print("Total Size := {0}".format(total_size))
# Declare expected disk usage, triggers host's EBS script (ecs-ebs-manager)
with open("/TOTAL_SIZE", "w") as text_file:
text_file.write("{0}".format(total_size))
print("Waiting EBS")
# Wait for EBS to appear
while not os.path.isdir('/scratch'):
time.sleep(5)
# Wait for mount verification
while not os.path.ismount('/scratch'):
time.sleep(1)
working_dir = generate_working_dir('/scratch')
print("Downloading vcf")
local_vcf_path = download_file(args.vcf_s3_path, working_dir)
print("VCF downloaded to %s" % local_vcf_path)
print("Downloading bam")
local_bam_path = download_file(args.bam_s3_path, working_dir)
print("BAM downloaded to %s" % local_bam_path)
print("Downloading bam index")
local_bam_index_path = download_file(args.bai_s3_path, working_dir)
print("BAM index downloaded to %s" % local_bam_index_path)
print("Running verifybamid")
local_stats_path = run_verifybamid_basic(local_vcf_path, local_bam_path,
local_bam_index_path,
args.opt_list, working_dir)
for ext in ['.selfSM', '.bestSM', '.depthSM', '.log']:
if os.path.exists(local_stats_path + ext):
print("Uploading %s to %s" %
(local_stats_path + ext, args.results_s3_path + ext))
upload_file(args.results_s3_path + ext, local_stats_path + ext)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print("Completed")
def main():
argparser = ArgumentParser()
file_path_group = argparser.add_argument_group(title='File paths')
file_path_group.add_argument('--fastq1_s3_path',
type=str,
help='FASTQ1 s3 path',
required=True)
file_path_group.add_argument('--fastq2_s3_path',
type=str,
help='FASTQ2 s3 path',
required=True)
run_group = argparser.add_argument_group(title='Run command args')
run_group.add_argument('--preproc_cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
run_group.add_argument('--index_cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
run_group.add_argument('--preqc_cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
run_group.add_argument('--preqc_report_cmd_args',
type=str,
help='Arguments for preprocessing',
default=' ')
argparser.add_argument('--working_dir', type=str, default='/scratch')
argparser.add_argument('--results_folder', type=str)
args = argparser.parse_args()
#working_dir = os.path.join(args.working_dir, 'fa534753-c43b-4591-8bd5-2ffdd1123a33')
working_dir = generate_working_dir(args.working_dir)
# Download fastq files and reference files
print('Downloading FASTQs')
fastq_files = '{0} {1}'.format(
download_fastq_file(args.fastq1_s3_path, working_dir),
download_fastq_file(args.fastq2_s3_path, working_dir))
print('Running preprocess')
preprocessed_file = run_preprocess(args.preproc_cmd_args, fastq_files,
working_dir)
time.sleep(10)
print('Running index')
indexed_file = run_index(preprocessed_file, args.index_cmd_args,
working_dir)
#indexed_file = ''
time.sleep(10)
print('Running preqc')
preqc_file = run_preqc(indexed_file, args.preqc_cmd_args,
args.preqc_report_cmd_args, working_dir)
print('Uploading results to %s' % args.results_folder)
upload_results(args.results_folder, working_dir)
print('Cleaning up working dir')
delete_working_dir(working_dir)
print('Completed')
"""