def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.add_argument(
"--maf",
help="input MAF file",
required=True,
type=os.path.abspath,
)
parser.add_argument("--out",
help="output MVF file",
type=os.path.abspath,
required=True)
parser.add_argument("--ref-tag",
"--reftag",
help="old reference tag")
parser.add_argument(
"--mvf-ref-label",
"--mvfreflabel",
default="REF",
help=("new label for reference sample (default='REF')"))
parser.add_argument(
"--sample-tags",
"--sampletags",
nargs="*",
required=True,
help=("one or more TAG:NEWLABEL or TAG, items, "
"if TAG found in sample label, replace with "
"NEW (or TAG if NEW not specified) "
"NEW and TAG must each be unique."))
parser.addarg_linebuffer()
parser.addarg_overwrite()
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.add_argument("--out",
type=os.path.abspath,
help="Output path of FASTA file.",
required=True)
parser.addarg_regions()
parser.addarg_sample_indices()
parser.addarg_sample_labels()
parser.add_argument(
"--label-type",
"--labeltype",
choices=('long', 'short'),
default='long',
help=("Long labels with all metadata or short ids"))
parser.add_argument("--output-data",
"--outputdata",
choices=("dna", "rna", "prot"),
help="Output dna, rna or prot data.")
parser.add_argument(
"--buffer",
type=int,
default=10,
help="size (Mbp) of write buffer for each sample")
parser.add_argument(
"--temp_dir",
"--tempdir",
default=".",
help="directory to write temporary fasta files")
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.addarg_sample_indices()
parser.addarg_sample_labels()
parser.addarg_windowsize()
parser.addarg_mincoverage()
parser.add_argument("--output-lists", action="store_true")
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.add_argument("--mvf",
nargs="*",
type=os.path.abspath,
required=True,
help="One or more mvf files.")
parser.addarg_out()
parser.add_argument(
"--new-contigs",
"--newcontigs",
action="store_true",
help=("By default, contigs are matched between files "
"using their text labels in the header. "
"Use this option to turn matching off and treat "
"each file's contigs as distinct."))
parser.add_argument(
"--newsamples",
action="store_true",
help=("By default, samples are matched between files "
"using their text labels in the header. "
"Use this option to turn matching off and treat "
"each file's sample columns as distinct."))
parser.add_argument(
"--main_header_file",
"--mainheaderfile",
help=("Output file will use same headers as "
"this input file (default=first in list)."))
parser.addarg_linebuffer()
parser.addarg_overwrite()
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.addarg_contig_ids()
parser.addarg_contig_labels()
parser.addarg_sample_indices()
parser.addarg_sample_labels()
parser.addarg_mincoverage()
parser.addarg_windowsize()
parser.add_argument(
"--base-match",
"--basematch",
help="String of bases to match (i.e. numerator).")
parser.add_argument(
"--base-total",
"--basetotal",
help="String of bases for total (i.e. denominator).")
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.addarg_gff()
parser.add_argument("--filter-annotation",
"--filterannotation",
help=("Skip entries in the GFF file that "
"contain this string in their 'Notes'"))
parser.add_argument(
"--nongenic-mode",
"--nongenicmode",
action="store_true",
help=("Instead of returning annotated genes, "
"return the non-genic regions without "
"without changing contigs or coordinates"))
parser.add_argument(
"--nongenic-margin",
"--nongenicmargin",
type=int,
default=0,
help=("for --unnanotated-mode, only retain "
"positions that are this number of bp away "
"from an annotated region boundary"))
parser.addarg_linebuffer()
parser.addarg_overwrite()
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.addarg_sample_indices(nmin=2)
parser.addarg_sample_labels(nmin=2)
parser.addarg_windowsize()
parser.addarg_mincoverage()
parser.add_argument("--data-type",
"--datatype",
choices=("dna", "prot"),
help=("Data type to compare."
"(This option is only needed for codon "
" MVF files, others will default.)"))
parser.add_argument("--ambig",
choices=("random2", "random3"),
help=("By default, ambiguous nucleotides are "
"excluded. This option will include "
"sets of ambiguous characters by "
"randomly choosing one of the options "
"for: RYMKWS ('random2') or "
"RYMKWS+BDHV ('random3')"))
parser.add_argument(
"--emit-counts",
action="store_true",
help=("output additional file that presents "
"the raw counts of pairwise patterns for "
"each sample pair tested for each window"))
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.add_argument("--gff",
type=os.path.abspath,
help=("Input GFF3 file. If GFF3 not provided, "
"alignments are assumed to be "
"in-frame coding sequences."))
parser.add_argument("--output-data",
"--outputdata",
choices=['protein', 'codon'],
default="codon",
help=("protein=single data column "
"of protein alleles; "
"codon=four columns with: "
"protein frame1 frame2 frame3"))
parser.add_argument("--filter-annotation",
"--filterannotation",
help=("skip GFF entries with text "
"matching this in their 'Notes' field"))
parser.addarg_linebuffer()
parser.addarg_overwrite()
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.add_argument("--gff",
type=os.path.abspath,
help=("Input GFF3 file. If GFF3 not provided, "
"alignments are assumed to be "
"in-frame coding sequences."))
parser.add_argument("--output-data",
"--outputdata",
choices=['protein', 'codon'],
default="codon",
help=("protein=single data column "
"of protein alleles; "
"codon=four columns with: "
"protein frame1 frame2 frame3"))
parser.add_argument("--filter-annotation",
"--filterannotation",
help=("skip GFF entries with text "
"matching this in their 'Notes' field"))
parser.add_argument("--parent-gene-prefix",
"--parentgeneprefix",
default="gene:",
help=("Parent genes prefix when interpreting"
"GFF files. For GFF3 files, 'gene:' "
"is standard, but for older or custom "
"GFF files this may vary. Use 'none' "
"to make empty."))
parser.addarg_linebuffer()
parser.addarg_overwrite()
parser.add_argument(
"--verbose",
action="store_true",
help="""Output excessive data to screen for debugging""")
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.addarg_gff()
parser.add_argument("--filter-annotation",
"--filterannotation",
help=("Skip entries in the GFF file that "
"contain this string in their 'Notes'"))
parser.add_argument(
"--nongenic-mode",
"--nongenicmode",
action="store_true",
help=("Instead of returning annotated genes, "
"return the non-genic regions without "
"without changing contigs or coordinates"))
parser.add_argument(
"--nongenic-margin",
"--nongenicmargin",
type=int,
default=0,
help=("for --unnanotated-mode, only retain "
"positions that are this number of bp away "
"from an annotated region boundary"))
parser.add_argument("--gene-prefix",
"--geneprefix",
default="mRNA:",
help=("Gene entry prefix when interpreting"
"GFF files. For GFF3 files, 'mRNA:' "
"is standard, but for older or custom "
"GFF files this may vary. Use 'none' "
"to make empty."))
parser.addarg_linebuffer()
parser.addarg_overwrite()
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.add_argument("--vcf",
type=os.path.abspath,
help="VCF input file")
parser.add_argument("--out", required=True, help="output MVF file")
parser.add_argument(
"--out-flavor",
"--outflavor",
default="dna",
choices=['dna', 'dnaqual', 'dnaqual-indel', 'dna-indel'],
help=("choose output MVF flavor to include "
"quality scores and/or indels"))
parser.add_argument("--mask-depth",
"--maskdepth",
type=int,
default=1,
help="below this read depth mask with N/n")
parser.add_argument(
"--low-depth",
"--lowdepth",
type=int,
default=3,
help=("below this read depth coverage, "
"convert to lower case set to 0 to disable"))
parser.add_argument(
"--mask-qual",
"--maskqual",
type=int,
default=3,
help=("low quality cutoff, bases replaced by N/- "
"set to 0 to disable"))
parser.add_argument(
"--low-qual",
"--lowqual",
type=int,
default=20,
help=("below this quality convert to lower case "
"set to 0 to disable"))
parser.add_argument(
"--contig-ids",
"--contigids",
nargs='*',
help=("manually specify one or more contig ids "
"as ID;VCFLABE;MVFLABEL, note that "
"VCFLABEL must match EXACTLY the contig string "
"labels in the VCF file"))
parser.add_argument(
"--sample-replace",
"--samplereplace",
nargs="*",
help=("one or more TAG:NEWLABEL or TAG, items, "
"if TAG found in sample label, replace with "
"NEW (or TAG if NEW not specified) "
"NEW and TAG must each be unique"))
parser.add_argument(
"--ref-label",
"--reflabel",
default="REF",
help="label for reference sample (default='REF')")
parser.add_argument("--alleles-from",
"--allelesfrom",
default=None,
help="""get additional alignment columns
from INFO fields (:-separated)""")
parser.addarg_linebuffer()
parser.add_argument(
"--no-autoindex",
"--noautoindex",
action="store_true",
help="do not automatically index contigs from the VCF")
parser.add_argument(
"--field-sep",
"--fieldsep",
default="TAB",
choices=['TAB', 'SPACE', 'DBLSPACE', 'COMMA', 'MIXED'],
help="""VCF field separator (default='TAB')""")
parser.add_argument(
"--qual",
action="store_true",
help="""Include Phred genotype quality (GQ) scores""")
parser.addarg_overwrite()
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.add_argument("--fasta",
nargs='*',
required=True,
help="input FASTA file(s)")
parser.add_argument("--out", required=True, help="output MVF file")
parser.add_argument("--flavor",
choices=['dna', 'protein'],
help="type of file [dna] or protein",
default='dna')
parser.add_argument(
"--contig-ids",
"--contigids",
nargs='*',
help=("manually specify one or more contig ids "
"as ID:LABEL"))
parser.add_argument(
"--sample-replace",
"--samplereplace",
nargs="*",
help=("one or more TAG:NEWLABEL or TAG, items, "
"if TAG found in sample label, replace with "
"NEW (or TAG if NEW not specified) "
"NEW and TAG must each be unique"))
parser.add_argument("--ref-label",
"--reflabel",
default="REF",
help="label for reference sample")
parser.add_argument("--read-buffer",
"--readbuffer",
type=int,
default=100000,
help="number of lines to hold in READ buffer")
parser.add_argument("--write-buffer",
"--writebuffer",
type=int,
default=100000,
help="number of lines to hold in WRITE buffer")
parser.add_argument("--field-sep",
"--fieldsep",
nargs='*',
default=None,
choices=[
'TAB', 'SPACE', 'DBLSPACE', 'COMMA',
'MIXED', 'PIPE', 'AT', 'UNDER', 'DBLUNDER'
],
help=("FASTA field separator; assumes "
"'>database accession locus' format"))
parser.add_argument("--contig-field",
"--contigfield",
type=int,
help=("When headers are split by --field-sep, "
"the 0-based index of the contig id."))
parser.add_argument(
"--contig-by-file",
"--contigbyfile",
action="store_true",
help=("Contigs are designated by separate files."))
parser.add_argument("--sample-field",
"--samplefield",
type=int,
help=("when headers are split by --field-sep, "
"the 0-based index of the sample id"))
parser.add_argument("--manual-coord",
"--manualcoord",
nargs='*',
help=("manually specify reference coordinates "
"for each file in the format "
"CONTIGID:START..STOP, ..."))
parser.addarg_overwrite()
return parser
def generate_argparser():
"""Generate argparse parser
"""
pallette = Pallette()
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.add_argument("--out-prefix",
"--outprefix",
help="Output prefix (not required).")
parser.addarg_sample_indices(nmin=3)
parser.addarg_sample_labels(nmin=3)
parser.addarg_outgroup_indices(nmin=1)
parser.addarg_outgroup_labels(nmin=1)
parser.addarg_windowsize()
parser.add_argument(
"--contig-labels",
"--contiglabels",
nargs=1,
help=("Enter the ids of one or more contigs in the "
"order they will appear in the chromoplot (as "
"comma-separated list)"
"(defaults to all ids in order present in MVF)"))
parser.add_argument(
"--contig-ids",
"--contigids",
"--contigs",
nargs=1,
help=("Enter the labels of one or more contigs in the "
"order they will appear in the chromoplot (as "
"comma-separated list)"
"(defaults to all ids in order present in MVF)"))
parser.add_argument(
"--majority",
action="store_true",
help=("Plot only 100% shading in the majority track "
" rather than shaded proportions in all tracks."))
parser.add_argument(
"--info-track",
"--infotrack",
action="store_true",
help=("Include an additional coverage information "
"track that will show empty, uninformative, "
"and informative loci. (Useful for "
"ranscriptomes/RAD or other reduced sampling."))
parser.add_argument("--empty-mask",
"--emptymask",
choices=pallette.colornames,
default="none",
help="Mask empty regions with this color.")
parser.add_argument(
"--yscale",
default=20,
type=int,
help=("Height (in number of pixels) for each track"))
parser.add_argument(
"--xscale",
default=1,
type=int,
help="Width (in number of pixels) for each window")
parser.add_argument("--colors",
nargs=3,
choices=pallette.colornames,
help="three colors to use for chromoplot")
parser.add_argument(
"--plot-type",
"--plottype",
choices=["graph", "image"],
default="image",
help=("PNG image (default) or graph via matplotlib "
"(experimental)"))
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.add_argument("--out",
type=os.path.abspath,
help="Output Phylip file.",
required=True)
parser.addarg_regions()
parser.add_argument(
"--label-type",
"--labeltype",
choices=('long', 'short'),
default='short',
help="Long labels with all metadata or short ids")
parser.add_argument("--output-data",
"--outputdata",
choices=("dna", "rna", "prot"),
help="Output dna, rna or prot data.")
parser.addarg_sample_indices()
parser.addarg_sample_labels()
parser.add_argument(
"--buffer",
type=int,
default=100000,
help="size (bp) of write buffer for each sample")
parser.add_argument(
"--temp_dir",
"--tempdir",
default=".",
help="directory to write temporary fasta files")
parser.add_argument("--partition",
action="store_true",
help=("Output a CSV partitions file with RAxML"
"formatting for use in partitioned "
"phylogenetic methods."))
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.addarg_sample_indices()
parser.addarg_sample_labels()
parser.addarg_contig_ids()
parser.addarg_contig_labels()
parser.addarg_windowsize()
parser.add_argument("--raxml-outgroups",
"--raxmloutgroups",
help=("Comma-separated list of outgroup "
"taxon labels to use in RAxML."))
parser.add_argument("--root-with",
"--rootwith",
help=("Comma-separated list of taxon labels "
"to root trees with after RAxML"))
parser.add_argument("--output-contig-labels",
"--outputcontiglabels",
action="store_true",
help=("Output will use contig labels "
"instead of id numbers."))
parser.add_argument("--output-empty",
"--outputempty",
action="store_true",
help=("Include entries of windows "
"with no data in output."))
parser.add_argument(
"--choose-allele",
"--chooseallele",
"--hapmode",
default="none",
dest="choose_allele",
choices=[
"none", "randomone", "randomboth", "major", "minor",
"majorminor"
],
help=("Chooses how heterozygous alleles are "
"handled. (none=no splitting (default); "
"randomone=pick one allele randomly "
"(recommended); randomboth=pick two alleles "
"randomly, but keep both; major=pick the "
"more common allele; minor=pick the less "
"common allele; majorminor= pick the major in "
"'a' and minor in 'b'"))
parser.add_argument("--min-sites",
"--minsites",
type=int,
default=100,
help="minimum number of sites ")
parser.add_argument(
"--min-seq-coverage",
"--minseqcoverage",
type=float,
default=0.1,
help=("proportion of total alignment a sequence"
"must cover to be retianed [0.1]"))
parser.add_argument("--min-depth",
"--mindepth",
type=int,
default=4,
help=("minimum number of alleles per site"))
parser.add_argument(
"--bootstrap",
type=int,
help=("turn on rapid bootstrapping for RAxML and "
"perform specified number of replicates"))
parser.add_argument("--raxml-model",
"--raxmlmodel",
default="GTRGAMMA",
help=("choose RAxML model"))
parser.add_argument("--raxml-path",
"--raxmlpath",
default="raxml",
help="RAxML path for manual specification.")
parser.add_argument(
"--raxml-opts",
"--raxmlopts",
default="",
help=("specify additional RAxML arguments as a "
"double-quotes encased string"))
parser.add_argument(
"--duplicate-seq",
"--duplicateseq",
default="dontuse",
choices=["dontuse", "keep", "remove"],
help=("dontuse=remove duplicate sequences prior to "
"RAxML tree inference, then add them to the "
"tree manually as zero-branch-length sister "
"taxa; keep=keep in for RAxML tree inference "
"(may cause errors for RAxML); "
"remove=remove entirely from alignment"))
parser.add_argument("--temp-dir",
"--tempdir",
default='./raxmltemp',
type=os.path.abspath,
help=("Temporary directory path"))
parser.add_argument("--temp-prefix",
"--tempprefix",
default="mvftree",
help=("Temporary file prefix"))
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_gff()
parser.addarg_out()
parser.addarg_samples()
parser.addarg_windowsize()
parser.addarg_mincoverage()
parser.add_argument(
"--allele-groups",
"--allelegroups",
nargs='*',
help=("GROUP1:LABEL,LABEL GROUP2:LABEL,LABEL "))
parser.add_argument("--species-groups",
"--speciesgroups",
nargs='*')
parser.add_argument(
"--chi-test",
"--chitest",
help=("Input two number values for expected "
"Nonsynonymous and Synonymous expected values."))
parser.add_argument(
"--target",
nargs="*",
help=("Specify the taxa labels that define the "
"target lineage-specific branch to be tested."))
parser.add_argument("--num-target-species",
"--targetspec",
type=int,
default=1,
help=("Specify the minimum number of "
"taxa in the target set "
"that are required to conduct analysis"))
parser.add_argument("--output-align",
"--outputalign",
help=("Output alignment to this file path in "
"phylip format."))
parser.add_argument(
"--outgroup",
help=("Specify sample name with which to root trees."))
parser.add_argument(
"--use-labels",
"--uselabels",
action="store_true",
help="Use contig labels instead of IDs in output.")
parser.add_argument("--codeml-path",
"--codemlpath",
default="codeml",
type=os.path.abspath,
help="Full path for PAML codeml executable.")
parser.add_argument("--raxml-path",
"--raxmlpath",
type=os.path.abspath,
default="raxml",
help="Full path to RAxML program executable.")
parser.add_argument("--start-contig",
"--startcontig",
type=int,
default=0,
help="Numerical ID for the starting contig.")
parser.add_argument("--end-contig",
"--endcontig",
type=int,
default=100000000,
help="Numerical id for the ending contig.")
parser.add_argument(
"--paml-tmp",
"--pamltmp",
default="pamltmp",
type=os.path.abspath,
help="path for temporary folder for PAML output files")
parser.add_argument(
"--all-sample-trees",
"--allsampletrees",
action="store_true",
help=("Makes trees from all samples instead of "
"only the most complete sequence from "
"each species"))
parser.add_argument(
"--branch-lrt",
"--branchlrt",
type=os.path.abspath,
help=("Specify the output file for and turn on the "
"RAxML-PAML format LRT test scan for "
"selection on the target branch in addition "
"to the basic patterns scan"))
parser.add_argument("--verbose",
action="store_true",
help="additional screen output")
return parser
def generate_argparser():
"""Generate argparse parser
"""
parser = MvfArgumentParser()
parser.addarg_mvf()
parser.addarg_out()
parser.add_argument(
"--actions",
nargs='*',
help=("set of actions:args to perform, "
"note these are done in order as listed"))
parser.add_argument("--labels",
action="store_true",
help="use sample labels instead of indices")
parser.add_argument("--test",
help="manually input a line for testing")
parser.add_argument("--test-nchar",
"--textnchar",
type=int,
help="total number of samples for test string")
parser.add_argument(
"--more-help",
"--morehelp",
action="store_true",
help="prints full module list and descriptions")
parser.addarg_linebuffer()
parser.add_argument("--verbose",
action="store_true",
help="report every line (for debugging)")
parser.addarg_overwrite()
return parser
