File size: 10,012 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
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
# Copyright 2011 by Andreas Wilm. All rights reserved.
# Based on ClustalW wrapper copyright 2009 by Cymon J. Cox.
#
# 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 Clustal Omega."""


from Bio.Application import _Option, _Switch, AbstractCommandline


class ClustalOmegaCommandline(AbstractCommandline):
    """Command line wrapper for clustal omega.

    http://www.clustal.org/omega

    Notes
    -----
    Last checked against version: 1.2.0

    References
    ----------
    Sievers F, Wilm A, Dineen DG, Gibson TJ, Karplus K, Li W, Lopez R,
    McWilliam H, Remmert M, Söding J, Thompson JD, Higgins DG (2011).
    Fast, scalable generation of high-quality protein multiple
    sequence alignments using Clustal Omega.
    Molecular Systems Biology 7:539 https://doi.org/10.1038/msb.2011.75

    Examples
    --------
    >>> from Bio.Align.Applications import ClustalOmegaCommandline
    >>> in_file = "unaligned.fasta"
    >>> out_file = "aligned.fasta"
    >>> clustalomega_cline = ClustalOmegaCommandline(infile=in_file, outfile=out_file, verbose=True, auto=True)
    >>> print(clustalomega_cline)
    clustalo -i unaligned.fasta -o aligned.fasta --auto -v

    You would typically run the command line with clustalomega_cline() or via
    the Python subprocess module, as described in the Biopython tutorial.

    """

    def __init__(self, cmd="clustalo", **kwargs):
        """Initialize the class."""
        # order parameters in the same order as clustalo --help
        self.parameters = [
            # Sequence Input
            _Option(
                ["-i", "--in", "--infile", "infile"],
                "Multiple sequence input file",
                filename=True,
                equate=False,
            ),
            _Option(
                ["--hmm-in", "HMM input", "hmm_input"],
                "HMM input files",
                filename=True,
                equate=False,
            ),
            _Switch(["--dealign", "dealign"], "Dealign input sequences"),
            _Option(
                ["--profile1", "--p1", "profile1"],
                "Pre-aligned multiple sequence file (aligned columns will be kept fix).",
                filename=True,
                equate=False,
            ),
            _Option(
                ["--profile2", "--p2", "profile2"],
                "Pre-aligned multiple sequence file (aligned columns will be kept fix).",
                filename=True,
                equate=False,
            ),
            _Option(
                ["-t", "--seqtype", "seqtype"],
                "{Protein, RNA, DNA} Force a sequence type (default: auto).",
                equate=False,
                checker_function=lambda x: x
                in ["protein", "rna", "dna", "Protein", "RNA", "DNA", "PROTEIN"],
            ),
            _Switch(
                ["--is-profile", "isprofile"],
                "disable check if profile, force profile (default no)",
            ),
            _Option(
                ["--infmt", "infmt"],
                """Forced sequence input file format (default: auto)

                    Allowed values: a2m, fa[sta], clu[stal], msf, phy[lip], selex, st[ockholm], vie[nna]
                    """,
                equate=False,
                checker_function=lambda x: x
                in [
                    "a2m",
                    "fa",
                    "fasta",
                    "clu",
                    "clustal",
                    "msf",
                    "phy",
                    "phylip",
                    "selex",
                    "st",
                    "stockholm",
                    "vie",
                    "vienna",
                ],
            ),
            # Clustering
            _Option(
                ["--distmat-in", "distmat_in"],
                "Pairwise distance matrix input file (skips distance computation).",
                filename=True,
                equate=False,
            ),
            _Option(
                ["--distmat-out", "distmat_out"],
                "Pairwise distance matrix output file.",
                filename=True,
                equate=False,
            ),
            _Option(
                ["--guidetree-in", "guidetree_in"],
                "Guide tree input file (skips distance computation and guide-tree clustering step).",
                filename=True,
                equate=False,
            ),
            _Option(
                ["--guidetree-out", "guidetree_out"],
                "Guide tree output file.",
                filename=True,
                equate=False,
            ),
            _Switch(
                ["--full", "distmat_full"],
                "Use full distance matrix for guide-tree calculation (slow; mBed is default)",
            ),
            _Switch(
                ["--full-iter", "distmat_full_iter"],
                "Use full distance matrix for guide-tree calculation during iteration (mBed is default)",
            ),
            _Option(
                ["--cluster-size", "clustersize"],
                "soft maximum of sequences in sub-clusters",
                checker_function=lambda x: isinstance(x, int),
            ),
            _Option(
                ["--clustering-out", "clusteringout"],
                "Clustering output file",
                filename=True,
            ),
            _Switch(
                ["--use-kimura", "usekimura"],
                "use Kimura distance correction for aligned sequences (default no)",
            ),
            _Switch(
                ["--percent-id", "percentid"],
                "convert distances into percent identities (default no)",
            ),
            # Alignment Output
            _Option(
                ["-o", "--out", "--outfile", "outfile"],
                "Multiple sequence alignment output file (default: stdout).",
                filename=True,
                equate=False,
            ),
            _Option(
                ["--outfmt", "outfmt"],
                "MSA output file format:"
                " a2m=fa[sta],clu[stal],msf,phy[lip],selex,st[ockholm],vie[nna]"
                " (default: fasta).",
                equate=False,
                checker_function=lambda x: x
                in [
                    "a2m",
                    "fa",
                    "fasta",
                    "clu",
                    "clustal",
                    "msf",
                    "phy",
                    "phylip",
                    "selex",
                    "st",
                    "stockholm",
                    "vie",
                    "vienna",
                ],
            ),
            _Switch(
                ["--residuenumber", "--resno", "residuenumber"],
                "in Clustal format print residue numbers (default no)",
            ),
            _Option(
                ["--wrap", "wrap"],
                "number of residues before line-wrap in output",
                checker_function=lambda x: isinstance(x, int),
            ),
            _Option(
                ["--output-order", "outputorder"],
                "MSA output order like in input/guide-tree",
                checker_function=lambda x: x in ["input-order", "tree-order"],
            ),
            # Iteration
            _Option(
                ["--iterations", "--iter", "iterations"],
                "Number of (combined guide-tree/HMM) iterations",
                equate=False,
                checker_function=lambda x: isinstance(x, int),
            ),
            _Option(
                ["--max-guidetree-iterations", "max_guidetree_iterations"],
                "Maximum number of guidetree iterations",
                equate=False,
                checker_function=lambda x: isinstance(x, int),
            ),
            _Option(
                ["--max-hmm-iterations", "max_hmm_iterations"],
                "Maximum number of HMM iterations",
                equate=False,
                checker_function=lambda x: isinstance(x, int),
            ),
            # Limits (will exit early, if exceeded):
            _Option(
                ["--maxnumseq", "maxnumseq"],
                "Maximum allowed number of sequences",
                equate=False,
                checker_function=lambda x: isinstance(x, int),
            ),
            _Option(
                ["--maxseqlen", "maxseqlen"],
                "Maximum allowed sequence length",
                equate=False,
                checker_function=lambda x: isinstance(x, int),
            ),
            # Miscellaneous:
            _Switch(
                ["--auto", "auto"],
                "Set options automatically (might overwrite some of your options)",
            ),
            _Option(
                ["--threads", "threads"],
                "Number of processors to use",
                equate=False,
                checker_function=lambda x: isinstance(x, int),
            ),
            _Option(
                ["-l", "--log", "log"],
                "Log all non-essential output to this file.",
                filename=True,
                equate=False,
            ),
            _Switch(["-h", "--help", "help"], "Print help and exit."),
            _Switch(["-v", "--verbose", "verbose"], "Verbose output"),
            _Switch(["--version", "version"], "Print version information and exit"),
            _Switch(
                ["--long-version", "long_version"],
                "Print long version information and exit",
            ),
            _Switch(["--force", "force"], "Force file overwriting."),
        ]
        AbstractCommandline.__init__(self, cmd, **kwargs)


if __name__ == "__main__":
    from Bio._utils import run_doctest

    run_doctest()