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 = parse4vcf2tiledb()
args, extr = argparser.parse_known_args()
print(args)
if args.index == None:
idx = int(os.getenv('AWS_BATCH_JOB_ARRAY_INDEX'))
else:
idx = args.index
loader_path, callset_path, vid_path = download_required_files(args.loader_s3_path, args.callset_s3_path, args.vid_s3_path)
if os.getenv('GETEBS'):
initEBS(WORKDIR)
else:
if not os.path.exists(WORKDIR):
os.mkdir(WORKDIR)
if not os.path.exists(PVCFDIR):
os.mkdir(PVCFDIR)
# Run program
run_vcf2tiledb_no_s3(WORKDIR, idx, loader_path, callset_path, vid_path, args.chr)
if not os.getenv('SKIP_UPLOAD'):
print("Uploading to %s" % (args.results_s3_path) )
upload_folder(args.results_s3_path, PVCFDIR)
print ("Completed vcf2tiledb")
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 upload_bam(bam_s3_path, local_folder_path):
"""
Uploads results folder containing the bam file (and associated output)
:param bam_s3_path: S3 path to upload the alignment results to
:param local_folder_path: local path containing the alignment results
"""
upload_folder(bam_s3_path, local_folder_path)
def upload_results(folder_s3_path, local_folder_path):
"""
Uploads results folder (and associated output)
:param folder_s3_path: S3 path to upload the assembly results to
:param local_folder_path: local path containing the assembly results
"""
upload_folder(folder_s3_path, local_folder_path)
def upload_results(results_path, working_dir):
"""
Uploads results folder containing the bam file (and associated output)
:param bam_s3_path: S3 path to upload the alignment results to
:param local_folder_path: local path containing the alignment results
"""
upload_folder(results_path, os.path.join(working_dir, 'preqc'))
upload_folder(results_path, os.path.join(working_dir, 'fragsizes'))
def main():
argparser = parse_args()
args, extr = argparser.parse_known_args()
print(args)
ref_idx = args.ref_s3_path + '.fai'
if args.sample_s3_path.rpartition('.')[-1] == 'bam':
input_idx = args.sample_s3_path + '.bai'
elif args.sample_s3_path.rpartition('.')[-1] == 'cram':
input_idx = args.sample_s3_path + '.crai'
else:
raise Exception("Unknown input type")
if os.getenv('GETEBS'):
initEBS(WORKDIR)
else:
if not os.path.exists(WORKDIR):
os.mkdir(WORKDIR)
ref_path, ref_idx_path, input_path, idx_path, region_path = download_required_files(
WORKDIR, args.ref_s3_path, ref_idx, args.sample_s3_path, input_idx,
args.regions)
output_dir = WORKDIR + '/results'
os.mkdir(output_dir)
output_prefix = output_dir + '/{SAMPLE}.hg38.realign.bqsr'.format(
SAMPLE=args.sample_name)
# Run program
run_xatlas_basic(args.sample_name, input_path, ref_path, args.threads,
region_path, output_prefix, output_dir)
if not os.getenv('SKIP_UPLOAD'):
print("Uploading to %s" % (args.results_s3_path))
upload_folder(args.results_s3_path, output_dir)
print("Completed xatlas for %s" % args.sample_name)
# check refdata cmd = "ls -l refdata-cellranger-GRCh38-1.2.0" subprocess.check_call(shlex.split(cmd)) # Run Cellranger MKFASTQ and COUNT ############################################ # cellranger mkfastqs cmd = 'cellranger mkfastq --id=tiny-bcl-output --run=tiny-bcl/cellranger-tiny-bcl-1.2.0/ --csv=tiny-bcl/cellranger-tiny-bcl-samplesheet-1.2.0.csv' subprocess.check_call(shlex.split(cmd)) # # use full path for reference transcriptome # # cellranger count cmd = 'cellranger count --id=test_sample --fastqs=tiny-bcl-output/outs/fastq_path/p1/s1 --sample=test_sample --expect-cells=1000 --localmem=3 --chemistry=SC3Pv2 --transcriptome=refdata-cellranger-GRCh38-1.2.0' subprocess.check_call(shlex.split(cmd)) # # Copy data back to S3 # ########################### # copy mkfastq outputs s3_path = 's3://' + inst_bucket + '/tiny-bcl-output' fcs_files_path = 'tiny-bcl-output' upload_folder(s3_path, fcs_files_path) # copy count outputs s3_path = 's3://' + inst_bucket + '/test_sample' fcs_files_path = 'test_sample' upload_folder(s3_path, fcs_files_path)
