Spaces:
No application file
No application file
File size: 10,544 Bytes
b7731cd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 |
# Copyright 2009 by Cymon J. Cox. All rights reserved.
#
# This file is part of the Biopython distribution and governed by your
# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
# Please see the LICENSE file that should have been included as part of this
# package.
"""Command line wrapper for the multiple alignment program PRANK."""
from Bio.Application import _Option, _Switch, AbstractCommandline
class PrankCommandline(AbstractCommandline):
"""Command line wrapper for the multiple alignment program PRANK.
http://www.ebi.ac.uk/goldman-srv/prank/prank/
Notes
-----
Last checked against version: 081202
References
----------
Loytynoja, A. and Goldman, N. 2005. An algorithm for progressive
multiple alignment of sequences with insertions. Proceedings of
the National Academy of Sciences, 102: 10557--10562.
Loytynoja, A. and Goldman, N. 2008. Phylogeny-aware gap placement
prevents errors in sequence alignment and evolutionary analysis.
Science, 320: 1632.
Examples
--------
To align a FASTA file (unaligned.fasta) with the output in aligned
FASTA format with the output filename starting with "aligned" (you
can't pick the filename explicitly), no tree output and no XML output,
use:
>>> from Bio.Align.Applications import PrankCommandline
>>> prank_cline = PrankCommandline(d="unaligned.fasta",
... o="aligned", # prefix only!
... f=8, # FASTA output
... notree=True, noxml=True)
>>> print(prank_cline)
prank -d=unaligned.fasta -o=aligned -f=8 -noxml -notree
You would typically run the command line with prank_cline() or via
the Python subprocess module, as described in the Biopython tutorial.
"""
def __init__(self, cmd="prank", **kwargs):
"""Initialize the class."""
OUTPUT_FORMAT_VALUES = list(range(1, 18))
self.parameters = [
# ################# input/output parameters: ##################
# -d=sequence_file
_Option(["-d", "d"], "Input filename", filename=True, is_required=True),
# -t=tree_file [default: no tree, generate approximate NJ tree]
_Option(["-t", "t"], "Input guide tree filename", filename=True),
# -tree="tree_string" [tree in newick format; in double quotes]
_Option(["-tree", "tree"], "Input guide tree as Newick string"),
# -m=model_file [default: HKY2/WAG]
_Option(
["-m", "m"], "User-defined alignment model filename. Default: HKY2/WAG"
),
# -o=output_file [default: 'output']
_Option(
["-o", "o"],
"Output filenames prefix. Default: 'output'\n "
"Will write: output.?.fas (depending on requested "
"format), output.?.xml and output.?.dnd",
filename=True,
),
# -f=output_format [default: 8]
_Option(
["-f", "f"],
"Output alignment format. Default: 8 FASTA\n"
"Option are:\n"
"1. IG/Stanford 8. Pearson/Fasta\n"
"2. GenBank/GB 11. Phylip3.2\n"
"3. NBRF 12. Phylip\n"
"4. EMBL 14. PIR/CODATA\n"
"6. DNAStrider 15. MSF\n"
"7. Fitch 17. PAUP/NEXUS",
checker_function=lambda x: x in OUTPUT_FORMAT_VALUES,
),
_Switch(
["-noxml", "noxml"],
"Do not output XML files (PRANK versions earlier than v.120626)",
),
_Switch(
["-notree", "notree"],
"Do not output dnd tree files (PRANK versions earlier than v.120626)",
),
_Switch(
["-showxml", "showxml"], "Output XML files (PRANK v.120626 and later)"
),
_Switch(
["-showtree", "showtree"],
"Output dnd tree files (PRANK v.120626 and later)",
),
_Switch(["-shortnames", "shortnames"], "Truncate names at first space"),
_Switch(["-quiet", "quiet"], "Reduce verbosity"),
# ###################### model parameters: ######################
# +F [force insertions to be always skipped]
# -F [equivalent]
_Switch(
["-F", "+F", "F"], "Force insertions to be always skipped: same as +F"
),
# -dots [show insertion gaps as dots]
_Switch(["-dots", "dots"], "Show insertion gaps as dots"),
# -gaprate=# [gap opening rate; default: dna 0.025 / prot 0.0025]
_Option(
["-gaprate", "gaprate"],
"Gap opening rate. Default: dna 0.025 prot 0.0025",
checker_function=lambda x: isinstance(x, float),
),
# -gapext=# [gap extension probability; default: dna 0.5 / prot 0.5]
_Option(
["-gapext", "gapext"],
"Gap extension probability. Default: dna 0.5 / prot 0.5",
checker_function=lambda x: isinstance(x, float),
),
# -dnafreqs=#,#,#,# [ACGT; default: empirical]
_Option(
["-dnafreqs", "dnafreqs"],
"DNA frequencies - 'A,C,G,T'. eg '25,25,25,25' as a quote "
"surrounded string value. Default: empirical",
checker_function=lambda x: isinstance(x, bytes),
),
# -kappa=# [ts/tv rate ratio; default:2]
_Option(
["-kappa", "kappa"],
"Transition/transversion ratio. Default: 2",
checker_function=lambda x: isinstance(x, int),
),
# -rho=# [pur/pyr rate ratio; default:1]
_Option(
["-rho", "rho"],
"Purine/pyrimidine ratio. Default: 1",
checker_function=lambda x: isinstance(x, int),
),
# -codon [for DNA: use empirical codon model]
_Switch(["-codon", "codon"], "Codon aware alignment or not"),
# -termgap [penalise terminal gaps normally]
_Switch(["-termgap", "termgap"], "Penalise terminal gaps normally"),
# ############### other parameters: ################################
# -nopost [do not compute posterior support; default: compute]
_Switch(
["-nopost", "nopost"],
"Do not compute posterior support. Default: compute",
),
# -pwdist=# [expected pairwise distance for computing guidetree;
# default: dna 0.25 / prot 0.5]
_Option(
["-pwdist", "pwdist"],
"Expected pairwise distance for computing guidetree. "
"Default: dna 0.25 / prot 0.5",
checker_function=lambda x: isinstance(x, float),
),
_Switch(
["-once", "once"], "Run only once. Default: twice if no guidetree given"
),
_Switch(["-twice", "twice"], "Always run twice"),
_Switch(["-skipins", "skipins"], "Skip insertions in posterior support"),
_Switch(
["-uselogs", "uselogs"],
"Slower but should work for a greater number of sequences",
),
_Switch(["-writeanc", "writeanc"], "Output ancestral sequences"),
_Switch(
["-printnodes", "printnodes"], "Output each node; mostly for debugging"
),
# -matresize=# [matrix resizing multiplier]
# Doesn't specify type but Float and Int work
_Option(
["-matresize", "matresize"],
"Matrix resizing multiplier",
checker_function=lambda x: (isinstance(x, float) or isinstance(x, int)),
),
# -matinitsize=# [matrix initial size multiplier]
# Doesn't specify type but Float and Int work
_Option(
["-matinitsize", "matinitsize"],
"Matrix initial size multiplier",
checker_function=lambda x: (isinstance(x, float) or isinstance(x, int)),
),
_Switch(["-longseq", "longseq"], "Save space in pairwise alignments"),
_Switch(["-pwgenomic", "pwgenomic"], "Do pairwise alignment, no guidetree"),
# -pwgenomicdist=# [distance for pairwise alignment; default: 0.3]
_Option(
["-pwgenomicdist", "pwgenomicdist"],
"Distance for pairwise alignment. Default: 0.3",
checker_function=lambda x: isinstance(x, float),
),
# -scalebranches=# [scale branch lengths; default: dna 1 / prot 2]
_Option(
["-scalebranches", "scalebranches"],
"Scale branch lengths. Default: dna 1 / prot 2",
checker_function=lambda x: isinstance(x, int),
),
# -fixedbranches=# [use fixed branch lengths]
# Assume looking for a float
_Option(
["-fixedbranches", "fixedbranches"],
"Use fixed branch lengths of input value",
checker_function=lambda x: isinstance(x, float),
),
# -maxbranches=# [set maximum branch length]
# Assume looking for a float
_Option(
["-maxbranches", "maxbranches"],
"Use maximum branch lengths of input value",
checker_function=lambda x: isinstance(x, float),
),
# -realbranches [disable branch length truncation]
_Switch(
["-realbranches", "realbranches"], "Disable branch length truncation"
),
_Switch(["-translate", "translate"], "Translate to protein"),
_Switch(
["-mttranslate", "mttranslate"], "Translate to protein using mt table"
),
# ##################### other: ####################
_Switch(
["-convert", "convert"],
"Convert input alignment to new format. Do not perform alignment",
),
]
AbstractCommandline.__init__(self, cmd, **kwargs)
if __name__ == "__main__":
from Bio._utils import run_doctest
run_doctest()
|