Source Code for Module Bio.Align.Applications._Dialign

  1  # Copyright 2009 by Cymon J. Cox.  All rights reserved. 
  2  # This code is part of the Biopython distribution and governed by its 
  3  # license.  Please see the LICENSE file that should have been included 
  4  # as part of this package. 
  5  """Command line wrapper for the multiple alignment program DIALIGN2-2. 
  6  """ 
  7   
  8  __docformat__ = "epytext en"  # Don't just use plain text in epydoc API pages! 
  9   
 10  from Bio.Application import _Option, _Argument, _Switch, AbstractCommandline 
 11   
 12   
 13 -class DialignCommandline(AbstractCommandline): 
 14      """Command line wrapper for the multiple alignment program DIALIGN2-2. 
 15   
 16      http://bibiserv.techfak.uni-bielefeld.de/dialign/welcome.html 
 17   
 18      Example: 
 19   
 20      To align a FASTA file (unaligned.fasta) with the output files names 
 21      aligned.* including a FASTA output file (aligned.fa), use: 
 22   
 23      >>> from Bio.Align.Applications import DialignCommandline 
 24      >>> dialign_cline = DialignCommandline(input="unaligned.fasta", 
 25      ...                                    fn="aligned", fa=True) 
 26      >>> print dialign_cline 
 27      dialign2-2 -fa -fn aligned unaligned.fasta 
 28   
 29      You would typically run the command line with dialign_cline() or via 
 30      the Python subprocess module, as described in the Biopython tutorial. 
 31   
 32      Citation: 
 33   
 34      B. Morgenstern (2004). DIALIGN: Multiple DNA and Protein Sequence 
 35      Alignment at BiBiServ. Nucleic Acids Research 32, W33-W36. 
 36   
 37      Last checked against version: 2.2 
 38      """ 
 39 -    def __init__(self, cmd="dialign2-2", **kwargs): 
 40          self.program_name = cmd 
 41          self.parameters = \ 
 42              [ 
 43              _Switch(["-afc", "afc"], 
 44                      "Creates additional output file '*.afc' " 
 45                      "containing data of all fragments considered " 
 46                      "for alignment WARNING: this file can be HUGE !"), 
 47              _Switch(["-afc_v", "afc_v"], 
 48                      "Like '-afc' but verbose: fragments are explicitly " 
 49                      "printed. WARNING: this file can be EVEN BIGGER !"), 
 50              _Switch(["-anc", "anc"], 
 51                      "Anchored alignment. Requires a file <seq_file>.anc " 
 52                      "containing anchor points."), 
 53              _Switch(["-cs", "cs"], 
 54                      "If segments are translated, not only the `Watson " 
 55                      "strand' but also the `Crick strand' is looked at."), 
 56              _Switch(["-cw", "cw"], 
 57                      "Additional output file in CLUSTAL W format."), 
 58              _Switch(["-ds", "ds"], 
 59                      "`dna alignment speed up' - non-translated nucleic acid " 
 60                      "fragments are taken into account only if they start " 
 61                      "with at least two matches. Speeds up DNA alignment at " 
 62                      "the expense of sensitivity."), 
 63              _Switch(["-fa", "fa"], 
 64                      "Additional output file in FASTA format."), 
 65              _Switch(["-ff", "ff"], 
 66                      "Creates file *.frg containing information about all " 
 67                      "fragments that are part of the respective optimal " 
 68                      "pairwise alignmnets plus information about " 
 69                      "consistency in the multiple alignment"), 
 70              _Option(["-fn", "fn"], 
 71                      "Output files are named <out_file>.<extension>.", 
 72                      equate=False), 
 73              _Switch(["-fop", "fop"], 
 74                      "Creates file *.fop containing coordinates of all " 
 75                      "fragments that are part of the respective pairwise alignments."), 
 76              _Switch(["-fsm", "fsm"], 
 77                      "Creates file *.fsm containing coordinates of all " 
 78                      "fragments that are part of the final alignment"), 
 79              _Switch(["-iw", "iw"], 
 80                      "Overlap weights switched off (by default, overlap " 
 81                      "weights are used if up to 35 sequences are aligned). " 
 82                      "This option speeds up the alignment but may lead " 
 83                      "to reduced alignment quality."), 
 84              _Switch(["-lgs", "lgs"], 
 85                      "`long genomic sequences' - combines the following " 
 86                      "options: -ma, -thr 2, -lmax 30, -smin 8, -nta, -ff, " 
 87                      "-fop, -ff, -cs, -ds, -pst "), 
 88              _Switch(["-lgs_t", "lgs_t"], 
 89                      "Like '-lgs' but with all segment pairs assessed " 
 90                      "at the peptide level (rather than 'mixed alignments' " 
 91                      "as with the '-lgs' option). Therefore faster than " 
 92                      "-lgs but not very sensitive for non-coding regions."), 
 93              _Option(["-lmax", "lmax"], 
 94                      "Maximum fragment length = x  (default: x = 40 or " 
 95                      "x = 120 for `translated' fragments). Shorter x " 
 96                      "speeds up the program but may affect alignment quality.", 
 97                      checker_function=lambda x: isinstance(x, int), 
 98                      equate=False), 
 99              _Switch(["-lo", "lo"], 
100                      "(Long Output) Additional file *.log with information " 
101                      "about fragments selected for pairwise alignment and " 
102                      "about consistency in multi-alignment proceedure."), 
103              _Switch(["-ma", "ma"], 
104                      "`mixed alignments' consisting of P-fragments and " 
105                      "N-fragments if nucleic acid sequences are aligned."), 
106              _Switch(["-mask", "mask"], 
107                      "Residues not belonging to selected fragments are " 
108                      "replaced by `*' characters in output alignment " 
109                      "(rather than being printed in lower-case characters)"), 
110              _Switch(["-mat", "mat"], 
111                      "Creates file *mat with substitution counts derived " 
112                      "from the fragments that have been selected for alignment."), 
113              _Switch(["-mat_thr", "mat_thr"], 
114                      "Like '-mat' but only fragments with weight score " 
115                      "> t are considered"), 
116              _Switch(["-max_link", "max_link"], 
117                      "'maximum linkage' clustering used to construct " 
118                      "sequence tree (instead of UPGMA)."), 
119              _Switch(["-min_link", "min_link"], 
120                      "'minimum linkage' clustering used."), 
121              _Option(["-mot", "mot"], 
122                      "'motif' option.", 
123                      equate=False), 
124              _Switch(["-msf", "msf"], 
125                      "Separate output file in MSF format."), 
126              _Switch(["-n", "n"], 
127                      "Input sequences are nucleic acid sequences. " 
128                      "No translation of fragments."), 
129              _Switch(["-nt", "nt"], 
130                      "Input sequences are nucleic acid sequences and " 
131                      "`nucleic acid segments' are translated to `peptide " 
132                      "segments'."), 
133              _Switch(["-nta", "nta"], 
134                      "`no textual alignment' - textual alignment suppressed. " 
135                      "This option makes sense if other output files are of " 
136                      "intrest -- e.g. the fragment files created with -ff, " 
137                      "-fop, -fsm or -lo."), 
138              _Switch(["-o", "o"], 
139                      "Fast version, resulting alignments may be slightly " 
140                      "different."), 
141              _Switch(["-ow", "ow"], 
142                      "Overlap weights enforced (By default, overlap weights " 
143                      "are used only if up to 35 sequences are aligned since " 
144                      "calculating overlap weights is time consuming)."), 
145              _Switch(["-pst", "pst"], 
146                      "'print status'. Creates and updates a file *.sta with " 
147                      "information about the current status of the program " 
148                      "run.  This option is recommended if large data sets " 
149                      "are aligned since it allows the user to estimate the " 
150                      "remaining running time."), 
151              _Switch(["-smin", "smin"], 
152                      "Minimum similarity value for first residue pair " 
153                      "(or codon pair) in fragments. Speeds up protein " 
154                      "alignment or alignment of translated DNA fragments " 
155                      "at the expense of sensitivity."), 
156              _Option(["-stars", "stars"], 
157                      "Maximum number of `*' characters indicating degree " 
158                      "of local similarity among sequences. By default, no " 
159                      "stars are used but numbers between 0 and 9, instead.", 
160                      checker_function = lambda x: x in range(0,10), 
161                      equate=False), 
162              _Switch(["-stdo", "stdo"], 
163                      "Results written to standard output."), 
164              _Switch(["-ta", "ta"], 
165                      "Standard textual alignment printed (overrides " 
166                      "suppression of textual alignments in special " 
167                      "options, e.g. -lgs)"), 
168              _Option(["-thr", "thr"], 
169                      "Threshold T = x.", 
170                      checker_function = lambda x: isinstance(x, int), 
171                      equate=False), 
172              _Switch(["-xfr", "xfr"], 
173                      "'exclude fragments' - list of fragments can be " 
174                      "specified that are NOT considered for pairwise alignment"), 
175              _Argument(["input"], 
176                        "Input file name. Must be FASTA format", 
177                        filename=True, 
178                        is_required=True), 
179              ] 
180          AbstractCommandline.__init__(self, cmd, **kwargs) 
181   
182   
183 -def _test(): 
184      """Run the module's doctests (PRIVATE).""" 
185      print "Running modules doctests..." 
186      import doctest 
187      doctest.testmod() 
188      print "Done" 
189   
190  if __name__ == "__main__": 
191      _test() 
192