def main(argv):
''''''
parser = argparse.ArgumentParser(description='Generates a Slurm script for running fastqc on various sequence data files')
parser.add_argument("-j", "--cores", nargs=1, metavar='N', type=int, default=[1], help="The maximum number of cores to use, 0=exclusive. [Default: 1]")
parser.add_argument("-p", "--partition", nargs=1, metavar="partition", default=["8hour"], choices=['bigmem', '8hour', 'compute'], help="The partition (or queue) to submit job to")
parser.add_argument("rawfile", nargs="+", help="Files or directory of raw fastq/a sequences to process. If directory, -f filter is used to select files within.")
parser.add_argument("-f", "--dir-filter", nargs=1, metavar='filter', default=["*.f*q"], help="A filter to match files when searching a directory. [Default: \"*.f*q]\"")
#parser.add_argument("-k", "--kraken-file", nargs="+", help="Files or directory of kraken_classified fastq/a sequences. If directory, -K filter is used to select files within.")
#parser.add_argument("-K", "--kraken-dir-filter", nargs=1, metavar='filter', default=["*_classified.f*q"], help="A filter to match files when searching a kraken result directory. [Default: \"*_classified.f*q\"]")
args = parser.parse_args(argv[1:])
common.writecmd(argv)
#print args
# expand files
rawfiles=common.expandFiles(args.rawfile, args.dir_filter[0])
#krakenfiles=common.expandFiles(args.kraken_file, args.kraken_dir_filter[0])
error=False
if len(rawfiles) == 0:
sys.stderr.write("No RAW files found: '%s'\n" % (" ".join(args.rawfile)))
error=True
#if len(krakenfiles) == 0:
# sys.stderr.write("No KRAKEN files found: '%s'\n" % (" ".join(args.kraken_file)))
# error=True
if error:
return 1
## make the variable parts of script
vars={}
vars["rawfiles"] = " ".join(rawfiles)
#vars["krakenfiles"] = " ".join(krakenfiles)
if args.cores[0] == 0:
vars["slurmheader"] = common.makeExclusiveHeader(partition=args.partition[0])
vars["cores"] = "16"
else:
vars["slurmheader"] = common.makeHeader(partition=args.partition[0], ntasks=args.cores[0])
vars["cores"] = args.cores[0]
#vars["slurmheader"] = common.makeHeader(partition=args.partition[0], cores=1)
vars["fastqcversion"] = subprocess.check_output(["rad-pipeline_module_version", "fastqc"]).rstrip()
vars["parallelversion"] = subprocess.check_output(["rad-pipeline_module_version", "parallel"]).rstrip()
vars["radpipelineversion"] = subprocess.check_output(["rad-pipeline_module_version", "rad-pipeline"]).rstrip()
vars["CMD"] = " ".join(argv)
jobscript = common.loadTemplate("fastqc.slurm")
#print jobscript
print jobscript.format(**vars)
return 0
def main(argv):
''''''
parser = argparse.ArgumentParser(description='Generates a slurm script for running pear of a selection of files')
parser.add_argument("-j", "--cores", nargs=1, metavar='N', type=int, default=[8], help="The number of cores to use, 0=exclusive. [Default: 8]")
parser.add_argument("-p", "--partition", nargs=1, metavar="partition", default=["8hour"], choices=['bigmem', '8hour', 'compute'], help="The partition (or queue) to submit job to [Default: 8hour]")
parser.add_argument("file", nargs="+", help="Files or directory to process. If directory, -f filter is used to select files within.")
parser.add_argument("-f", "--dir-filter", nargs=1, metavar='filter', default=["*_R1*.f*q*"], help="A filter to match files when searching a directory. [Default: \"*_R1*.f*q*\"]")
parser.add_argument("-t", "--time", nargs=1, metavar='time', default=["01:00:00"], help="Job max runtime. [Default: 01:00:00]")
parser.add_argument("-T", "--filename-trim", nargs=1, metavar='trim', default=[".f*q"], help="Bash REGEX to trim extension from end of filename. [Default: '.f*q']")
args = parser.parse_args(argv[1:])
common.writecmd(argv)
#print args
## make the variable parts of script
vars={}
if args.cores[0] == 0:
vars["cores"] = "16"
else:
vars["cores"] = args.cores[0]
if vars["cores"] > 8 and args.partition[0] == "8hour":
args.partition[0] = "compute"
if args.cores[0] == 0:
vars["slurmheader"] = common.makeExclusiveHeader(partition=args.partition[0], time=args.time[0])
else:
vars["slurmheader"] = common.makeHeader(partition=args.partition[0], ntasks=args.cores[0], time=args.time[0])
files = []
for f in args.file:
if '*' in f or '?' in f or os.path.exists(f):
if os.path.isdir(f):
files.append("%s/%s" % (f, args.dir_filter[0]))
else:
files.append(f)
else:
sys.stderr.write("Warning: file '%s' does not exist and will be ignored\n")
vars["files"] = " ".join(files)
vars["pearversion"] = subprocess.check_output(["carlaseq_module_version", "pear-gcc"]).rstrip()
vars["trim"] = args.filename_trim[0]
vars["CMD"] = " ".join(argv)
jobscript = common.loadTemplate("pear.slurm")
print jobscript.format(**vars)
return 0
def main(argv):
''''''
parser = argparse.ArgumentParser(description='Generates a Slurm script for running blast against the probes on various fasta files')
parser.add_argument("-j", "--cores", nargs=1, metavar='N', type=int, default=[1], help="The maximum number of cores to use, 0=exclusive. [Default: 1]")
parser.add_argument("-p", "--partition", nargs=1, metavar="partition", default=["8hour"], choices=['bigmem', '8hour', 'compute', 'long'], help="The partition (or queue) to submit job to")
parser.add_argument("rawfile", nargs="+", help="Files or directory of raw fastq/a sequences to process. If directory, -f filter is used to select files within.")
parser.add_argument("-f", "--dir-filter", nargs=1, metavar='filter', default=["*.f*a"], help="A filter to match files when searching a directory. [Default: \"*.f*a\"]")
parser.add_argument("-t", "--filename-trim", nargs=1, metavar='trim', default=[".*"], help="Bash REGEX to trim extension from end of filename. [Default: \".*\"]")
parser.add_argument("-d", "--probe-database", nargs=1, metavar='database', default=["probes.fasta"], help="Filename of probes database fasta file [Default: probes.fasta]")
args = parser.parse_args(argv[1:])
common.writecmd(argv)
# expand files
rawfiles=common.expandFiles(args.rawfile, args.dir_filter[0])
error=False
if len(rawfiles) == 0:
sys.stderr.write("No RAW files found: '%s'\n" % (" ".join(args.rawfile)))
error=True
if error:
return 1
## make the variable parts of script
vars={}
vars["rawfiles"] = " ".join(rawfiles)
if args.cores[0] == 0:
vars["slurmheader"] = common.makeExclusiveHeader(partition=args.partition[0])
vars["cores"] = "16"
else:
vars["slurmheader"] = common.makeHeader(partition=args.partition[0], ntasks=args.cores[0])
vars["cores"] = args.cores[0]
vars["blastversion"] = subprocess.check_output(["carlaseq_module_version", "blast+"]).rstrip()
vars["biostreamtoolsversion"] = subprocess.check_output(["carlaseq_module_version", "biostreamtools-gcc"]).rstrip()
vars["trim"] = args.filename_trim[0]
vars["probes"] = args.probe_database[0]
vars["CMD"] = " ".join(argv)
jobscript = common.loadTemplate("blastprobes.slurm")
print jobscript.format(**vars)
return 0
def main(argv):
''''''
parser = argparse.ArgumentParser(description='Generates a slurm script for running kraken of a selection of files')
parser.add_argument("-j", "--cores", nargs=1, metavar='N', type=int, default=[0], help="The number of cores to use, 0=exclusive. [Default: 0]")
parser.add_argument("-p", "--partition", nargs=1, metavar="partition", default=["bigmem"], choices=['bigmem', '8hour', 'compute'], help="The partition (or queue) to submit job to")
parser.add_argument("file", nargs="+", help="Files or directory to process. If directory, -f filter is used to select files within.")
parser.add_argument("-f", "--dir-filter", nargs=1, metavar='filter', default=["*_R?.f*q*"], help="A filter to match files when searching a directory. [Default: '*_R?.f*q*']")
args = parser.parse_args(argv[1:])
common.writecmd(argv)
# expand files
rawfiles=common.expandFiles(args.file, args.dir_filter[0])
#print args
## make the variable parts of script
vars={}
if args.cores[0] == 0:
vars["slurmheader"] = common.makeExclusiveHeader(partition=args.partition[0])
else:
vars["slurmheader"] = common.makeHeader(partition=args.partition[0], ntasks=args.cores[0], mem="16000")
# files = []
# for f in args.file:
# if '*' in f or '?' in f or os.path.exists(f):
# if os.path.isdir(f):
# files.append("%s/%s" % (f, args.dir_filter[0]))
# else:
# files.append(f)
# else:
# sys.stderr.write("Warning: file '%s' does not exist and will be ignored\n")
vars["files"] = " ".join(rawfiles)
vars["krakenversion"] = subprocess.check_output(["carlaseq_module_version", "kraken"]).rstrip()
vars["CMD"] = " ".join(argv)
jobscript = common.loadTemplate("kraken.slurm")
print jobscript.format(**vars)
return 0
def main(argv):
''''''
parser = argparse.ArgumentParser(description='Generates a Slurm script for running fastqc on various sequence data files')
parser.add_argument("-j", "--cores", nargs=1, metavar='N', type=int, default=[1], help="The maximum number of cores to use, 0=exclusive. [Default: 1]")
parser.add_argument("-p", "--partition", nargs=1, metavar="partition", default=["8hour"], choices=['bigmem', '8hour', 'compute'], help="The partition (or queue) to submit job to")
parser.add_argument("rawfile", nargs="+", help="Files or directory of raw fastq/a sequences to process. If directory, -f filter is used to select files within.")
parser.add_argument("-f", "--dir-filter", nargs=1, metavar='filter', default=["*.f*q*"], help="A filter to match files when searching a directory. [Default: '*.f*q*']")
parser.add_argument("-t", "--filename-trim", nargs=1, metavar='trim', default=[".f*q*"], help="Bash REGEX to trim extension from end of filename. [Default: '.f*q*']")
args = parser.parse_args(argv[1:])
common.writecmd(argv)
# expand files
rawfiles=common.expandFiles(args.rawfile, args.dir_filter[0])
if len(rawfiles) == 0:
sys.stderr.write("No RAW files found: '%s'\n" % (" ".join(args.rawfile)))
return 1
## make the variable parts of script
vars={}
vars["rawfiles"] = " ".join(rawfiles)
if args.cores[0] == 0:
vars["slurmheader"] = common.makeExclusiveHeader(partition=args.partition[0])
vars["cores"] = "16"
else:
vars["slurmheader"] = common.makeHeader(partition=args.partition[0], ntasks=args.cores[0])
vars["cores"] = args.cores[0]
vars["trim"] = args.filename_trim[0]
vars["CMD"] = " ".join(argv)
jobscript = common.loadTemplate("fastqc.slurm")
print jobscript.format(**vars)
return 0
def main(argv):
''''''
parser = argparse.ArgumentParser(
description=
'Generates a slurm script for running pear of a selection of files')
parser.add_argument(
"-j",
"--cores",
nargs=1,
metavar='N',
type=int,
default=[8],
help="The number of cores to use, 0=exclusive. [Default: 8]")
parser.add_argument(
"-p",
"--partition",
nargs=1,
metavar="partition",
default=["8hour"],
choices=['bigmem', '8hour', 'compute'],
help="The partition (or queue) to submit job to [Default: 8hour]")
parser.add_argument(
"file",
nargs="+",
help=
"Files or directory to process. If directory, -f filter is used to select files within."
)
parser.add_argument(
"-f",
"--dir-filter",
nargs=1,
metavar='filter',
default=["*_R1_*.f*q*"],
help=
"A filter to match files when searching a directory. [Default: \"*_R1_*.f*q*\"]"
)
parser.add_argument("-t",
"--time",
nargs=1,
metavar='time',
default=["01:00:00"],
help="Job max runtime. [Default: 01:00:00]")
args = parser.parse_args(argv[1:])
common.writecmd(argv)
#print args
## make the variable parts of script
vars = {}
if args.cores[0] == 0:
vars["cores"] = "16"
else:
vars["cores"] = args.cores[0]
if vars["cores"] > 8 and args.partition[0] == "8hour":
args.partition[0] = "compute"
if args.cores[0] == 0:
vars["slurmheader"] = common.makeExclusiveHeader(
partition=args.partition[0], time=args.time[0])
else:
vars["slurmheader"] = common.makeHeader(partition=args.partition[0],
ntasks=args.cores[0],
time=args.time[0])
files = []
for f in args.file:
if '*' in f or '?' in f or os.path.exists(f):
if os.path.isdir(f):
files.append("%s/%s" % (f, args.dir_filter[0]))
else:
files.append(f)
else:
sys.stderr.write(
"Warning: file '%s' does not exist and will be ignored\n")
vars["files"] = " ".join(files)
vars["pearversion"] = subprocess.check_output(
["rad-pipeline_module_version", "pear-gcc"]).rstrip()
vars["radpipelineversion"] = subprocess.check_output(
["rad-pipeline_module_version", "rad-pipeline"]).rstrip()
vars["CMD"] = " ".join(argv)
jobscript = common.loadTemplate("pear.slurm")
print jobscript.format(**vars)
return 0
def main(argv):
''''''
parser = argparse.ArgumentParser(
description=
'Generates a Slurm script for optimising stacks denovo_map.pl')
parser.add_argument(
"-j",
"--cores",
nargs=1,
metavar='N',
type=int,
default=[0],
help="Total number of cores to use, 0=exclusive. [Default: 0]")
parser.add_argument(
"--cores-task",
nargs=1,
metavar='T',
type=int,
default=[2],
help="Number of cores each task (trial) uses. [Default: 2]")
parser.add_argument("-p",
"--partition",
nargs=1,
metavar="partition",
default=["compute"],
choices=['bigmem', '8hour', 'compute'],
help="The partition (or queue) to submit job to")
parser.add_argument(
"-m",
"--m-target",
nargs=1,
metavar='N',
type=int,
help="The target (i.e. centre) value to use for -m option.")
parser.add_argument(
"--m-count",
nargs=1,
metavar='N',
type=int,
default=[2],
help=
"The number of values to use either side of -m option. [Default: 2]")
parser.add_argument(
"-n",
"--n-target",
nargs=1,
metavar='N',
type=int,
help="The target (i.e. centre) value to use for -n option.")
parser.add_argument(
"--n-count",
nargs=1,
metavar='N',
type=int,
default=[2],
help=
"The number of values to use between d and D for -n option. [Default: 2]"
)
parser.add_argument(
"-M",
"--M-target",
nargs=1,
metavar='N',
type=int,
help="The target (i.e. centre) value to use for -M option.")
parser.add_argument(
"--M-count",
nargs=1,
metavar='N',
type=int,
default=[2],
help=
"The number of values to use between d and D for -n option. [Default: 2]"
)
parser.add_argument(
"--denovo-opts",
nargs=1,
metavar='OPTS',
default=["-S -t"],
help=
"Other command line options to pass to denovo_map.pl. [Default: -S -t]"
)
parser.add_argument(
"--keep-denovo-log",
nargs=1,
metavar='N',
type=bool,
default=[False],
help="The batch id to use for denovo_map.pl [Default: False]")
parser.add_argument(
"--batch-id",
nargs=1,
metavar='N',
type=int,
default=[2],
help="The batch id to use for denovo_map.pl [Default: 2]")
parser.add_argument(
"file",
nargs="+",
help=
"Files or directory to process. If directory, -f filter is used to select files within."
)
parser.add_argument(
"-f",
"--dir-filter",
nargs=1,
metavar='filter',
default=["*.f*q"],
help=
"A filter to match files when searching a directory. [Default: *.f*q]"
)
args = parser.parse_args(argv[1:])
common.writecmd(argv)
errors = False
if args.m_target is None:
sys.stderr.write("Error: option -m (--m-target) is required\n")
errors = True
if args.n_target is None:
sys.stderr.write("Error: option -n (--n-target) is required\n")
errors = True
if args.M_target is None:
sys.stderr.write("Error: option -M (--M-target) is required\n")
errors = True
if errors:
return 1
## make the variable parts of script
subs = {}
if args.cores[0] == 0:
subs['slurmheader'] = common.makeExclusiveHeader(
partition=args.partition[0], mem="64000")
args.cores[0] = 16
else:
subs['slurmheader'] = common.makeHeader(partition=args.partition[0],
ntasks=args.cores[0])
files = []
for f in args.file:
if '*' in f or '?' in f or os.path.exists(f):
if os.path.isdir(f):
files.append("%s/%s" % (f, args.dir_filter[0]))
else:
files.append(f)
else:
sys.stderr.write(
"Warning: file '%s' does not exist and will be ignored\n" % f)
subs['files'] = " ".join(files)
subs['stacksversion'] = subprocess.check_output(
["rad-pipeline_module_version", "stacks-gcc"]).rstrip()
vars["parallelversion"] = subprocess.check_output(
["rad-pipeline_module_version", "parallel"]).rstrip()
vars["radpipelineversion"] = subprocess.check_output(
["rad-pipeline_module_version", "rad-pipeline"]).rstrip()
subs['mvalues'] = " ".join(
map(
str,
range(args.m_target[0] - args.m_count[0],
args.m_target[0] + args.m_count[0] + 1)))
subs['nvalues'] = " ".join(
map(
str,
range(args.n_target[0] - args.n_count[0],
args.n_target[0] + args.n_count[0] + 1)))
subs['Mvalues'] = " ".join(
map(
str,
range(args.M_target[0] - args.M_count[0],
args.M_target[0] + args.M_count[0] + 1)))
subs['CMD'] = " ".join(argv)
if args.keep_denovo_log[0]:
subs['nocpdenovo'] = ""
else:
subs['nocpdenovo'] = "#"
subs['corestask'] = args.cores_task[0]
subs['paralleljobs'] = str(int(args.cores[0] / args.cores_task[0]))
subs['denovoopts'] = args.denovo_opts[0]
subs['batchid'] = args.batch_id[0]
## validate inputs ##
filecount = 0
if len(files) > 0:
cmd = ["bash", "-c", 'ls -1 %s' % (" ".join(files))]
#cmd.extend(files)
filelist = subprocess.check_output(cmd).rstrip()
#print "'%s'"%filelist
filecount = len(filelist.split("\n"))
if filecount < 2 or filecount > 6:
sys.stderr.write(
"Warning: suboptimal number of samples (%s). You should use 2 to 6 representitive samples.\n"
% filecount)
jobscript = common.loadTemplate("denovo_opt2.slurm")
if jobscript != "":
print jobscript.format(**subs)
else:
sys.stderr.write(
"Error: failed to find template 'denovo_opt1.slurm'\n")
return 0