Source Code for Module Bio.Align.Applications._Probcons

  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 PROBCONS. 
  6  """ 
  7   
  8  __docformat__ = "epytext en"  # Don't just use plain text in epydoc API pages! 
  9   
 10  from Bio.Application import _Option, _Switch, _Argument, AbstractCommandline 
 11   
 12   
 13 -class ProbconsCommandline(AbstractCommandline): 
 14      """Command line wrapper for the multiple alignment program PROBCONS. 
 15   
 16      http://probcons.stanford.edu/ 
 17   
 18      Example: 
 19   
 20      To align a FASTA file (unaligned.fasta) with the output in ClustalW 
 21      format, and otherwise default settings, use: 
 22   
 23      >>> from Bio.Align.Applications import ProbconsCommandline 
 24      >>> probcons_cline = ProbconsCommandline(input="unaligned.fasta", 
 25      ...                                      clustalw=True) 
 26      >>> print probcons_cline 
 27      probcons -clustalw unaligned.fasta 
 28   
 29      You would typically run the command line with probcons_cline() or via 
 30      the Python subprocess module, as described in the Biopython tutorial. 
 31      Note that PROBCONS will write the alignment to stdout, which you may 
 32      want to save to a file and then parse, e.g.:: 
 33   
 34          stdout, stderr = probcons_cline() 
 35          handle = open("aligned.aln", "w") 
 36          handle.write(stdout) 
 37          handle.close() 
 38          from Bio import AlignIO 
 39          align = AlignIO.read("aligned.fasta", "clustalw") 
 40   
 41      Alternatively, to parse the output with AlignIO directly you can 
 42      use StringIO to turn the string into a handle:: 
 43   
 44          stdout, stderr = probcons_cline() 
 45          from StringIO import StringIO 
 46          from Bio import AlignIO 
 47          align = AlignIO.read(StringIO(stdout), "clustalw") 
 48   
 49      Citations: 
 50   
 51      Do, C.B., Mahabhashyam, M.S.P., Brudno, M., and Batzoglou, S. 2005. 
 52      PROBCONS: Probabilistic Consistency-based Multiple Sequence Alignment. 
 53      Genome Research 15: 330-340. 
 54   
 55      Last checked against version: 1.12 
 56      """ 
 57 -    def __init__(self, cmd="probcons", **kwargs): 
 58          self.parameters = \ 
 59              [ 
 60              #Note that some options cannot be assigned via properties using the 
 61              #original documented option (because hyphens are not valid for names in 
 62              #python), e.g cmdline.pre-training = 3 will not work 
 63              #In these cases the shortened option name should be used 
 64              #cmdline.pre = 3 
 65              _Switch(["-clustalw", "clustalw"], 
 66                      "Use CLUSTALW output format instead of MFA"), 
 67              _Option(["-c", "c", "--consistency", "consistency" ], 
 68                      "Use 0 <= REPS <= 5 (default: 2) passes of consistency transformation", 
 69                      checker_function=lambda x: x in range(0,6), 
 70                      equate=False), 
 71              _Option(["-ir", "--iterative-refinement", "iterative-refinement", "ir"], 
 72                      "Use 0 <= REPS <= 1000 (default: 100) passes of " 
 73                      "iterative-refinement", 
 74                      checker_function=lambda x: x in range(0,1001), 
 75                      equate=False), 
 76              _Option(["-pre", "--pre-training", "pre-training", "pre"], 
 77                      "Use 0 <= REPS <= 20 (default: 0) rounds of pretraining", 
 78                      checker_function=lambda x: x in range(0,21), 
 79                      equate=False), 
 80              _Switch(["-pairs", "pairs"], 
 81                      "Generate all-pairs pairwise alignments"), 
 82              _Switch(["-viterbi", "viterbi"], 
 83                      "Use Viterbi algorithm to generate all pairs " 
 84                      "(automatically enables -pairs)"), 
 85              _Switch(["-verbose", "verbose"], 
 86                      "Report progress while aligning (default: off)"), 
 87              _Option(["-annot", "annot"], 
 88                      "Write annotation for multiple alignment to FILENAME", 
 89                      equate=False), 
 90              _Option(["-t", "t", "--train", "train"], 
 91                      "Compute EM transition probabilities, store in FILENAME " 
 92                      "(default: no training)", 
 93                      equate=False), 
 94              _Switch(["-e", "e", "--emissions", "emissions"], 
 95                      "Also reestimate emission probabilities (default: off)"), 
 96              _Option(["-p", "p", "--paramfile", "paramfile"], 
 97                      "Read parameters from FILENAME", 
 98                      equate=False), 
 99              _Switch(["-a", "--alignment-order", "alignment-order", "a"], 
100                      "Print sequences in alignment order rather than input " 
101                      "order (default: off)"), 
102              #Input file name 
103              _Argument(["input"], 
104                        "Input file name. Must be multiple FASTA alignment "+ 
105                        "(MFA) format", 
106                        filename=True, 
107                        is_required=True), 
108              ] 
109          AbstractCommandline.__init__(self, cmd, **kwargs) 
110   
111   
112 -def _test(): 
113      """Run the module's doctests (PRIVATE).""" 
114      print "Running modules doctests..." 
115      import doctest 
116      doctest.testmod() 
117      print "Done" 
118   
119  if __name__ == "__main__": 
120      _test() 
121