def _init_parser():
global _parser
_parser = ArgumentParser(
description=("This script runs the SEPP algorithm on an input "
"tree, alignment, fragment file, and RAxML info file."),
conflict_handler='resolve')
_parser.add_argument("-v",
"--version",
action='version',
version="%(prog)s " + version)
decompGroup = _parser.add_argument_group(
"Decomposition Options".upper(), ' '.join([
"These options determine the alignment decomposition size and",
"taxon insertion size. If None is given, then the default",
"is to align/place at 10% of total taxa. "
"The alignment decomosition size must be",
"less than the taxon insertion size."
]))
_parser.groups = dict()
_parser.groups['decompGroup'] = decompGroup
decompGroup.add_argument(
"-A",
"--alignmentSize",
type=int,
dest="alignment_size",
metavar="N",
default=None,
help=("max alignment subset size of N "
"[default: 10%% of the total number of taxa or the placement"
" subset size if given]"))
decompGroup.add_argument(
"-P",
"--placementSize",
type=int,
dest="placement_size",
metavar="N",
default=None,
help=("max placement subset size of N "
"[default: 10%% of the total number of taxa or the alignment "
"length (whichever bigger)]"))
decompGroup.add_argument(
"-F",
"--fragmentChunkSize",
type=int,
dest="max_chunk_size",
metavar="N",
default=20000,
help=("maximum fragment chunk size of N. Helps controlling memory. "
"[default: 20000]"))
decompGroup.add_argument(
"-D",
"--distance",
type=float,
dest="distance",
metavar="DISTANCE",
default=1,
help=("minimum p-distance before stopping the decomposition"
"[default: 1]"))
# uym2 added #
decompGroup.add_argument(
"-M",
"--diameter",
type=float,
dest="maxDiam",
metavar="DIAMETER",
default=None,
help=("maximum tree diameter before stopping the decomposition"
"[default: None]"))
decompGroup.add_argument(
"-S",
"--decomp_strategy",
type=valid_decomp_strategy,
dest="decomp_strategy",
metavar="DECOMP",
default="normal",
# default = "midpoint",
help="decomposition strategy "
"[default: using tree branch length]")
# "[default: only include smallest subsets]")
outputGroup = _parser.add_argument_group("Output Options".upper(),
"These options control output.")
_parser.groups['outputGroup'] = outputGroup
outputGroup.add_argument(
"-p",
"--tempdir",
dest="tempdir",
metavar="DIR",
type=valid_dir_path,
default=get_default_temp_dir(),
help=("Tempfile files will be written to DIR. Full-path required. "
"[default: %(default)s]"))
outputGroup.add_argument("-rt",
"--remtemp",
dest="remtemp",
action="store_true",
help=("Remove tempfile directory. "
"[default: disabled]"))
outputGroup.set_defaults(remtemp=False)
outputGroup.add_argument(
"-o",
"--output",
dest="output",
metavar="OUTPUT",
default="output",
type=valid_file_prefix,
help="output files with prefix OUTPUT. [default: %(default)s]")
outputGroup.add_argument(
"-d",
"--outdir",
dest="outdir",
metavar="OUTPUT_DIR",
default=os.path.curdir,
type=valid_dir_path,
help=("output to OUTPUT_DIR directory. full-path required. "
"[default: %(default)s]"))
inputGroup = _parser.add_argument_group(
"Input Options".upper(), ' '.join([
"These options control input. To run SEPP the following is "
"required. A backbone tree (in newick format), a RAxML_info file "
"(this is the file generated by RAxML during estimation of the "
"backbone tree. Pplacer uses this info file to set model "
"parameters), a backbone alignment file (in fasta format), and a"
" fasta file including fragments. The input sequences are assumed"
" to be DNA unless specified otherwise."
]))
_parser.groups['inputGroup'] = inputGroup
inputGroup.add_argument(
"-c",
"--config",
dest="config_file",
metavar="CONFIG",
type=argparse.FileType('r'),
help=("A config file, including options used to run SEPP. Options"
" provided as command line arguments overwrite config file "
"values for those options. "
"[default: %(default)s]"))
inputGroup.add_argument(
"-t",
"--tree",
dest="tree_file",
metavar="TREE",
type=argparse.FileType('r'),
help="Input tree file (newick format) [default: %(default)s]")
inputGroup.add_argument(
"-r",
"--raxml",
dest="info_file",
metavar="RAXML",
type=argparse.FileType('r'),
help=("RAxML_info file including model parameters, generated by RAxML."
"[default: %(default)s]"))
inputGroup.add_argument("-a",
"--alignment",
dest="alignment_file",
metavar="ALIGN",
type=argparse.FileType('r'),
help="Aligned fasta file [default: %(default)s]")
inputGroup.add_argument("-f",
"--fragment",
dest="fragment_file",
metavar="FRAG",
type=argparse.FileType('r'),
help="fragment file [default: %(default)s]")
inputGroup.add_argument(
"-m",
"--molecule",
dest="molecule",
metavar="MOLECULE",
type=valid_molecule,
default="dna",
help=("Molecule type of sequences. Can be amino, dna, or rna "
"[default: %(default)s]"))
otherGroup = _parser.add_argument_group(
"Other options".upper(), "These options control how SEPP is run")
_parser.groups['otherGroup'] = otherGroup
otherGroup.add_argument(
"-x",
"--cpu",
type=set_cpu,
dest="cpu",
metavar="N",
default=set_cpu(cpu_count()),
help=("Use N cpus "
"[default: number of cpus available on the machine]"))
otherGroup.add_argument("-cp",
"--checkpoint",
type=set_checkpoint,
dest="checkpoint",
metavar="CHCK_FILE",
default=set_checkpoint(None),
help="checkpoint file [default: no checkpointing]")
otherGroup.add_argument(
"-cpi",
"--interval",
type=int,
dest="checkpoint_interval",
metavar="N",
default=3600,
help=("Interval (in seconds) between checkpoint writes. Has effect "
"only with -cp provided. [default: 3600]"))
otherGroup.add_argument("-seed",
"--randomseed",
type=int,
dest="seed",
metavar="N",
default=297834,
help="random seed number. [default: 297834]")
# inputGroup.add_argument("-p", "--package",
# dest="package", metavar="PKG",
# help="package directory"
# "[default: %(default)s]")
#
return _parser
def _init_parser():
global _parser
_parser = ArgumentParser(description=
"This script runs the SEPP algorithm on an input "
"tree, alignment, fragment file, and RAxML info file.", conflict_handler='resolve')
_parser.add_argument("-v", "--version", action='version', version= "%(prog)s " + version)
decompGroup = _parser.add_argument_group("Decomposition Options".upper(),
' '.join(["These options determine the alignment decomposition size and",
"taxon insertion size. If None is given, then the default",
"is to align/place at 10% of total taxa. The alignment decomosition size must be",
"less than the taxon insertion size."]))
_parser.groups = dict()
_parser.groups['decompGroup'] = decompGroup
decompGroup.add_argument("-A", "--alignmentSize", type = int,
dest = "alignment_size", metavar = "N",
default = None,
help = "max alignment subset size of N "
"[default: 10%% of the total number of taxa]")
decompGroup.add_argument("-P", "--placementSize", type = int,
dest = "placement_size", metavar = "N",
default = None,
help = "max placement subset size of N "
"[default: 10%% of the total number of taxa]")
decompGroup.add_argument("-S", "--decomp_strategy", type = valid_decomp_strategy,
dest = "decomp_strategy", metavar = "DECOMP",
default = "normal",
help = "decomposition strategy "
"[default: only include smallest subsets]")
outputGroup = _parser.add_argument_group( "Output Options".upper(),
"These options control output.")
_parser.groups['outputGroup'] = outputGroup
outputGroup.add_argument("-p", "--tempdir",
dest = "tempdir", metavar = "DIR",
type=valid_dir_path,
default = get_default_temp_dir(),
help = "Tempfile files will be written to DIR. Full-path required. "
"[default: %(default)s]")
outputGroup.add_argument("-o", "--output",
dest = "output", metavar = "OUTPUT",
default = "output",
type= valid_file_prefix,
help = "output files with prefix OUTPUT. "
"[default: %(default)s]")
outputGroup.add_argument("-d", "--outdir",
dest = "outdir", metavar = "OUTPUT_DIR",
default = os.path.curdir,
type = valid_dir_path,
help = "output to OUTPUT_DIR directory. full-path required. "
"[default: %(default)s]")
inputGroup = _parser.add_argument_group ("Input Options".upper(),
' '.join(["These options control input. To run SEPP the following is required."
"A backbone tree (in newick format), a RAxML_info file (this is the file generated by RAxML during estimation of the backbone tree. "
"Pplacer uses this info file to set model parameters),"
"a backbone alignment file (in fasta format), and a fasta file including fragments. The input sequences are assumed to be DNA unless specified otherwise."]))
_parser.groups['inputGroup'] = inputGroup
inputGroup.add_argument("-c", "--config",
dest = "config_file", metavar = "CONFIG",
type = argparse.FileType('r'),
help = "A config file, including options used to run SEPP. Options provided as command line arguments overwrite config file values for those options. "
"[default: %(default)s]")
inputGroup.add_argument("-t", "--tree",
dest = "tree_file", metavar = "TREE",
type = argparse.FileType('r'),
help = "Input tree file (newick format) "
"[default: %(default)s]")
inputGroup.add_argument("-r", "--raxml",
dest = "info_file", metavar = "RAXML",
type = argparse.FileType('r'),
help = "RAxML_info file including model parameters, generated by RAxML."
"[default: %(default)s]")
inputGroup.add_argument("-a", "--alignment",
dest = "alignment_file", metavar = "ALIGN",
type = argparse.FileType('r'),
help = "Aligned fasta file "
"[default: %(default)s]")
inputGroup.add_argument("-f", "--fragment",
dest = "fragment_file", metavar = "FRAG",
type = argparse.FileType('r'),
help = "fragment file "
"[default: %(default)s]")
inputGroup.add_argument("-m", "--molecule",
dest = "molecule", metavar = "MOLECULE",
type = valid_molecule,
default = "dna",
help = "Molecule type of sequences. Can be amino, dna, or rna "
"[default: %(default)s]")
otherGroup = _parser.add_argument_group( "Other options".upper(),
"These options control how SEPP is run")
_parser.groups['otherGroup'] = otherGroup
otherGroup.add_argument("-x", "--cpu", type = set_cpu,
dest = "cpu", metavar = "N",
default = set_cpu(cpu_count()),
help = "Use N cpus "
"[default: number of cpus available on the machine]")
otherGroup.add_argument("-cp", "--checkpoint", type = set_checkpoint,
dest = "checkpoint", metavar = "CHCK_FILE",
default = set_checkpoint(None),
help = "checkpoint file "
"[default: no checkpointing]")
otherGroup.add_argument("-cpi", "--interval", type = int,
dest = "checkpoint_interval", metavar = "N",
default = 3600,
help = "Interval (in seconds) between checkpoint writes. Has effect only with -cp provided."
"[default: 3600]")
#inputGroup.add_argument("-p", "--package",
# dest = "package", metavar = "PKG",
# help = "package directory"
# "[default: %(default)s]")
#
return _parser