def main():
""" main function """
## not in ipython
ip.__interactive__ = 0
header = \
"\n --------------------------------------------------"+\
"\n Analysis tools for ipyrad [v.{}]".format(ip.__version__)+\
"\n svd4tet -- fast quartet and tree inference "+\
"\n --------------------------------------------------"
print(header)
## parse params file input (returns to stdout if --help or --version)
args = parse_command_line()
## if JSON, load it
if args.json:
data = ip.load_json(args.json)
data.outfiles.svdinput = data.outfiles.svdinput
## else create a tmp assembly for the seqarray
else:
if not args.output:
raise IPyradWarningExit(" -o output_prefix required")
if not args.seq:
raise IPyradWarningExit(" -s sequence file required")
## create new JSON (Assembly) object
data = ip.Assembly(args.output, quiet=True)
data.outfiles.svdinput = args.seq
data.set_params(1, "./")
## parse samples from the sequence file
names = []
with iter(open(args.seq, 'r')) as infile:
infile.next().strip().split()
while 1:
try:
names.append(infile.next().split()[0])
except StopIteration:
break
## store as Samples in Assembly
data.samples = {name:ip.Sample(name) for name in names}
## store ipcluster info
data._ipcluster["cores"] = args.cores
if args.MPI:
data._ipcluster["engines"] = "MPI"
else:
data._ipcluster["engines"] = "Local"
## launch ipcluster and register for later destruction
data = ipcontroller_init(data)
## run svd4tet
args = [data, args.boots, args.method, args.nquartets, args.force]
data._clientwrapper(ipa.svd4tet.run, args, 45)
def load_assembly(name, controller="Local", quiet=False, launch=False):
""" loads an ipython dill pickled Assembly object """
## flexible name entry
locations = [name]
locations.append(name + ".assembly")
## does Assembly saved obj exist?
for name in locations:
try:
## load in the Assembly object
with open(name, "rb") as pickin:
data = dill.load(pickin)
## will raise Attribute error if not loaded
fullcurdir = os.path.realpath(os.path.curdir)
name = name.replace(fullcurdir, ".")
if not quiet:
print(" loading Assembly: {} [{}]".\
format(data.name, name))
## Test if our assembly is currently up to date
## How to deal with assembly objects falling out of synch with the
## currently assembly params in the code. If forceupdate is on
## then update the loaded assembly to the current version. If
## forceupdate is not on, then test to check if the loaded
## assembly is current. If it is then fine, if not bail out with
## a hopefully useful error message.
if test_assembly(data):
print(" Attempting to update assembly to newest version.")
data = update_assembly(data)
## relaunch ipcluster
if launch:
data._ipclusterid = ipcontroller_init(nproc="",
controller=controller,
quiet=quiet)
else:
data._ipclusterid = ""
except (IOError, AttributeError):
pass
try:
return data
except UnboundLocalError:
raise AssertionError(
"Attempting to load assembly. File not found: {}".format(name))
def __init__(self, name, controller="Local"):
## obj name
self.name = name
print("New Assembly object `{}` created".format(self.name))
## launch ipcluster and register for later destruction
self.__ipname__ = ipcontroller_init(controller)
## get binaries of dependencies
self.vsearch, self.muscle, self.smalt, self.samtools = getbins()
## link a log history of executed workflow
self.log = []
self._stamp(self.name + " created")
self.statsfiles = ObjDict()
## samples linked
self.samples = ObjDict()
## multiplex files linked
self.barcodes = ObjDict()
## an object for storing data directories for this Assembly
self.dirs = ObjDict()
## the default params dict
self.paramsdict = OrderedDict([
("working_directory", os.path.realpath(os.path.curdir)),
("raw_fastq_path",
os.path.join(os.path.realpath(os.path.curdir), "*.fastq")),
("barcodes_path",
os.path.join(os.path.realpath(os.path.curdir), "*.barcodes.txt")),
("sorted_fastq_path", ""), ("restriction_overhang", ("TGCAG", "")),
("max_low_qual_bases", 5), ("engines_per_job", 4),
("mindepth_statistical", 6), ("mindepth_majrule", 6),
("datatype", 'rad'), ("clust_threshold", .85), ("minsamp", 4),
("max_shared_heterozygosity", .25), ("prefix_outname", self.name),
("phred_Qscore_offset", 33), ("max_barcode_mismatch", 1),
("filter_adapters", 0), ("filter_min_trim_len", 35), ("ploidy", 2),
("max_stack_size", 1000), ("max_Ns_consens", (5, 5)),
("max_Hs_consens", (8, 8)), ("max_SNPs_locus", (100, 100)),
("max_Indels_locus", (5, 99)), ("trim_overhang", (1, 2, 2, 1)),
("hierarchical_clustering", 0), ("assembly_method", "denovo"),
("reference_sequence", "")
])
def load_assembly(name, controller="Local"):
""" loads an ipython pickled Assembly object """
## flexible name entry
if ".assembly" not in name:
name += ".assembly"
## does Assembly save obj exist?
if not os.path.exists(name):
print("cannot find", name, "try entering the full path to file.")
else:
## load in the Assembly object
with open(name, "rb") as pickin:
data = dill.load(pickin)
## relaunch ipcluster
data.__ipname__ = ipcontroller_init(controller)
return data
def __init__(self, name, controller="Local"):
## obj name
self.name = name
print("New Assembly object `{}` created".format(self.name))
## launch ipcluster and register for later destruction
self.__ipname__ = ipcontroller_init(controller)
## get binaries of dependencies
self.vsearch, self.muscle, self.smalt, self.samtools = getbins()
## link a log history of executed workflow
self.log = []
self._stamp(self.name+" created")
self.statsfiles = ObjDict()
## samples linked
self.samples = ObjDict()
## multiplex files linked
self.barcodes = ObjDict()
## an object for storing data directories for this Assembly
self.dirs = ObjDict()
## the default params dict
self.paramsdict = OrderedDict([
("working_directory", os.path.realpath(
os.path.curdir)),
("raw_fastq_path", os.path.join(
os.path.realpath(
os.path.curdir),
"*.fastq")),
("barcodes_path", os.path.join(
os.path.realpath(
os.path.curdir),
"*.barcodes.txt")),
("sorted_fastq_path", ""),
("restriction_overhang", ("TGCAG", "")),
("max_low_qual_bases", 5),
("engines_per_job", 4),
("mindepth_statistical", 6),
("mindepth_majrule", 6),
("datatype", 'rad'),
("clust_threshold", .85),
("minsamp", 4),
("max_shared_heterozygosity", .25),
("prefix_outname", self.name),
("phred_Qscore_offset", 33),
("max_barcode_mismatch", 1),
("filter_adapters", 0),
("filter_min_trim_len", 35),
("ploidy", 2),
("max_stack_size", 1000),
("max_Ns_consens", (5, 5)),
("max_Hs_consens", (8, 8)),
("max_SNPs_locus", (100, 100)),
("max_Indels_locus", (5, 99)),
("trim_overhang", (1, 2, 2, 1)),
("hierarchical_clustering", 0),
("assembly_method", "denovo"),
("reference_sequence", "")
])
def main():
""" main function """
## parse params file input (returns to stdout if --help or --version)
args = parse_command_line()
## create new paramsfile if -n
if args.new:
## Create a tmp assembly and call write_params to write out
## default params.txt file
try:
tmpassembly = ip.core.assembly.Assembly("")
tmpassembly.write_params("params.txt", force=args.force)
except Exception as e:
print(e)
print("\nUse --force to overwrite\n")
sys.exit(2)
print("New file `params.txt` created in {}".\
format(os.path.realpath(os.path.curdir)))
sys.exit(2)
## if showing results, do not do any steps and do not print header
if args.results:
args.steps = ""
print("")
else:
header = \
"\n --------------------------------------------------"+\
"\n ipyrad [v.{}]".format(ip.__version__)+\
"\n Interactive assembly and analysis of RADseq data"+\
"\n --------------------------------------------------"
print(header)
## create new Assembly or load existing Assembly, quit if args.results
if args.params:
parsedict = parse_params(args)
if args.results:
showstats(parsedict)
else:
## run Assembly steps
if args.steps:
## launch ipcluster and register for later destruction
if args.MPI:
controller = "MPI"
#elif args.PBS:
# controller = "PBS"
else:
controller = "Local"
## launch or load assembly with custom profile/pid
data = getassembly(args, parsedict)
## might want to use custom profiles instead of ...
data._ipclusterid = ipcontroller_init(nproc=args.cores,
controller=controller)
## set to print headers
data._headers = 1
## run assembly steps
steps = list(args.steps)
data.run(steps=steps, force=args.force, preview=args.preview)
def main():
""" main function """
## turn off traceback for the CLI
ip.__interactive__ = 0
## parse params file input (returns to stdout if --help or --version)
args = parse_command_line()
## create new paramsfile if -n
if args.new:
## Create a tmp assembly and call write_params to write out
## default params.txt file
try:
tmpassembly = ip.Assembly(args.new, quiet=True)
tmpassembly.write_params("params-{}.txt".format(args.new),
force=args.force)
except Exception as inst:
print(inst)
sys.exit(2)
print("\n New file `params-{}.txt` created in {}\n".\
format(args.new, os.path.realpath(os.path.curdir)))
sys.exit(2)
## if params then must provide action argument with it
if args.params:
if not any([args.branch, args.results, args.steps]):
print("""
Must provide action argument along with -p argument for params file.
e.g., ipyrad -p params-test.txt -r ## shows results
e.g., ipyrad -p params-test.txt -s 12 ## runs steps 1 & 2
""")
sys.exit(2)
## if branching or info do not allow steps in same command, print spacer
if any([args.branch, args.info]):
args.steps = ""
print("")
## always print the header when doing steps
header = \
"\n --------------------------------------------------"+\
"\n ipyrad [v.{}]".format(ip.__version__)+\
"\n Interactive assembly and analysis of RADseq data"+\
"\n --------------------------------------------------"
## if info print the info and exit
if not args.info == False:
if args.info:
ip.paramsinfo(int(args.info))
else:
ip.paramsinfo()
sys.exit(1)
## create new Assembly or load existing Assembly, quit if args.results
elif args.params:
parsedict = parse_params(args)
if args.branch:
branch_assembly(args, parsedict)
elif args.steps:
## print header
print(header)
## run Assembly steps
## launch or load assembly with custom profile/pid
data = getassembly(args, parsedict)
## if cores was entered, limit cores to this number
## otherwise use all available cores. By default _ipcluster[cores]
## is set to detect_cpus in Assembly.__init__)
if args.cores:
data.cpus = args.cores
if args.MPI:
data._ipcluster["engines"] = "MPI"
else:
data._ipcluster["engines"] = "Local"
## launch ipcluster and register for later destruction
data = ipcontroller_init(data)
## set to print headers
data._headers = 1
## run assembly steps
steps = list(args.steps)
data.run(steps=steps, force=args.force, preview=args.preview)
if args.results:
showstats(parsedict)
def main():
""" main function """
## turn off traceback for the CLI
ip.__interactive__ = 0
## parse params file input (returns to stdout if --help or --version)
args = parse_command_line()
## create new paramsfile if -n
if args.new:
## Create a tmp assembly and call write_params to write out
## default params.txt file
try:
tmpassembly = ip.Assembly(args.new, quiet=True)
tmpassembly.write_params("params-{}.txt".format(args.new),
force=args.force)
except Exception as inst:
print(inst)
sys.exit(2)
print("\n New file `params-{}.txt` created in {}\n".\
format(args.new, os.path.realpath(os.path.curdir)))
sys.exit(2)
## if params then must provide action argument with it
if args.params:
if not any([args.branch, args.results, args.steps]):
print("""
Must provide action argument along with -p argument for params file.
e.g., ipyrad -p params-test.txt -r ## shows results
e.g., ipyrad -p params-test.txt -s 12 ## runs steps 1 & 2
""")
sys.exit(2)
## if branching or info do not allow steps in same command, print spacer
if any([args.branch, args.info]):
args.steps = ""
print("")
## always print the header when doing steps
header = \
"\n --------------------------------------------------"+\
"\n ipyrad [v.{}]".format(ip.__version__)+\
"\n Interactive assembly and analysis of RADseq data"+\
"\n --------------------------------------------------"
## if info print the info and exit
if not args.info == False:
if args.info:
ip.paramsinfo(int(args.info))
else:
ip.paramsinfo()
sys.exit(1)
## create new Assembly or load existing Assembly, quit if args.results
elif args.params:
parsedict = parse_params(args)
if args.branch:
branch_assembly(args, parsedict)
elif args.steps:
## print header
print(header)
## run Assembly steps
## launch or load assembly with custom profile/pid
data = getassembly(args, parsedict)
## if cores was entered, limit cores to this number
## otherwise use all available cores. By default _ipcluster[cores]
## is set to detect_cpus in Assembly.__init__)
if args.cores:
data.cpus = args.cores
if args.MPI:
data._ipcluster["engines"] = "MPI"
else:
data._ipcluster["engines"] = "Local"
## launch ipcluster and register for later destruction
data = ipcontroller_init(data)
## set to print headers
data._headers = 1
## run assembly steps
steps = list(args.steps)
data.run(steps=steps, force=args.force, preview=args.preview)
if args.results:
showstats(parsedict)