def average_exome_coverage(args):
out_file = args.out
if file_exists(out_file):
return out_file
with file_transaction(out_file) as tx_out_file:
# dfs = [_calc_total_exome_coverage(bam, bed_file) for bam in in_bams]
resources = {'name': 'bedtools', 'mem': 12, 'cores': 1}
cluster.send_job(_calc_total_exome_coverage, args.bams, args, resources)
# df = rbind(dfs)
# df.to_csv(tx_out_file, mode='a', index=False, header=["r10", "r25", "r50", "region", "size", "sample"])
return out_file
def average_exome_coverage(args):
out_file = args.out
if file_exists(out_file):
return out_file
with file_transaction(out_file) as tx_out_file:
# dfs = [_calc_total_exome_coverage(bam, bed_file) for bam in in_bams]
resources = {'name': 'bedtools', 'mem': 12, 'cores': 1}
cluster.send_job(_calc_total_exome_coverage, args.bams, args,
resources)
# df = rbind(dfs)
# df.to_csv(tx_out_file, mode='a', index=False, header=["r10", "r25", "r50", "region", "size", "sample"])
return out_file
def test_cluster(self):
def fake_fn(n, args):
print 'inside function with %s' % n
time.sleep(n * 2)
start = time.time()
parser = ArgumentParser(description="Test cluster")
parser = arguments.myargs(parser)
args = parser.parse_args()
logger.info(args)
resources = {'name': 'step1', 'mem': 1, 'cores': 1}
cluster.send_job(fake_fn, [1, 2], args, resources)
logger.info('It took %.3f minutes without ipython' %
((time.time() - start) / 60))
def detect(args):
assert args.files, "Need a set of fastq files"
for mem in [6, 8, 10, 12, 14, 16, 18, 20, 24]:
safe_makedir("mem%s" % mem)
resources = {'name': "mem%s" % mem, 'mem': mem, 'cores': 1}
data = _prepare_samples(args)
data = _update_algorithm(data, resources)
data = cluster.send_job(trymemory, data, args, resources)
def detect_positions(data, args):
assert args.reference, "Need --reference"
assert args.index, "Need --index"
assert args.files, "Need a set of fastq files"
assert args.snp, "Need --snp"
resources = {'name': 'trimming', 'mem': 4, 'cores': 1}
data = _update_algorithm(data, resources)
data = cluster.send_job(prepare, data, args, resources)
resources = {'name': 'align', 'mem': 2, 'cores': 8}
data = _update_algorithm(data, resources)
data = cluster.send_job(create_bam, data, args, resources)
resources = {'name': 'bissnp', 'mem': 3, 'cores': 8}
data = _update_algorithm(data, resources)
data = cluster.send_job(call_variations, data, args, resources)
resources = {'name': 'report', 'mem': 2, 'cores': 5}
data = _update_algorithm(data, resources)
data = cluster.send_job(create_report, data, args, resources)
def link_sites(data, args):
assert args.files, "Need a set of fastq files"
assert args.out, "Need prefix"
resources = {'name': 'link', 'mem': 6, 'cores': 1}
workdir = args.out
workdir = op.abspath(safe_makedir(workdir))
data = _update_algorithm(data, resources)
data = cluster.send_job(detect_asm, data, args, resources)
vcf_res = [sample[0]['asm'] for sample in data]
vcf_merged = op.join(workdir, args.out + ".vcf")
post_processing(vcf_res, vcf_merged, op.join(workdir, "link"))
def bias_exome_coverage(args):
resources = {'name': 'bias', 'mem': 1, 'cores': 1}
cluster.send_job(calculate_bias_over_multiple_regions, args.bams, args, resources)
def calculate_cg_depth_coverage(args):
resources = {'name': 'vcf_stats', 'mem': 1, 'cores': 1}
cluster.send_job(calc_variants_stats, args.bams, args, resources)
def average_exome_coverage(data, args):
# dfs = [_calc_total_exome_coverage(bam, bed_file) for bam in in_bams]
safe_makedir(args.out)
resources = {'name': 'bedtools', 'mem': 8, 'cores': 1}
data = _update_algorithm(data, resources)
cluster.send_job(_calc_total_exome_coverage, data, args, resources)
def bias_exome_coverage(data, args):
safe_makedir(args.out)
resources = {'name': 'bias', 'mem': 1, 'cores': 1}
data = _update_algorithm(data, resources)
cluster.send_job(calculate_bias_over_multiple_regions, data, args, resources)
def calculate_cg_depth_coverage(data, args):
safe_makedir(args.out)
resources = {'name': 'vcf_stats', 'mem': 2, 'cores': 1}
data = _update_algorithm(data, resources)
cluster.send_job(calc_variants_stats, data, args, resources)
import time
from argparse import ArgumentParser
from ichwrapper import arguments, cluster, fake
from ichwrapper.log import logger
if __name__ == "__main__":
start = time.time()
parser = ArgumentParser(description="Test cluster")
parser = arguments.myargs(parser)
parser.add_argument("--cmd", default=False, action='store_true')
args = parser.parse_args()
# args = parser.parse_args(["--parallel", "ipython", "--local"])
logger.info(args)
resources = {'name': 'step1', 'mem': 1, 'cores': 1}
data = [{'num': 1}, {'num': 2}]
data = cluster.update_samples(data, resources, args)
cluster.send_job(fake.fake_fn, data, args, resources)
if args.cmd:
cluster.send_job(fake.fake_cmd_fn, data, args, resources)
logger.info('It took %.3f minutes with ipython' % ((time.time()-start)/60))
def calculate_cg_depth_coverage(args):
resources = {'name': 'vcf_stats', 'mem': 1, 'cores': 1}
cluster.send_job(calc_variants_stats, args.bams, args, resources)
def bias_exome_coverage(args):
resources = {'name': 'bias', 'mem': 1, 'cores': 1}
cluster.send_job(calculate_bias_over_multiple_regions, args.bams, args,
resources)
