Source Code for Module Bio.Align.Applications._TCoffee

  1  # Copyright 2009 by Cymon J. Cox and Brad Chapman. 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 TCOFFEE. 
  6  """ 
  7   
  8  __docformat__ = "epytext en"  # Don't just use plain text in epydoc API pages! 
  9   
 10  from Bio.Application import _Option, _Switch, AbstractCommandline 
 11   
 12   
 13 -class TCoffeeCommandline(AbstractCommandline): 
 14      """Commandline object for the TCoffee alignment program. 
 15   
 16      http://www.tcoffee.org/Projects_home_page/t_coffee_home_page.html 
 17   
 18      The T-Coffee command line tool has a lot of switches and options. 
 19      This wrapper implements a VERY limited number of options - if you 
 20      would like to help improve it please get in touch. 
 21   
 22      Example: 
 23   
 24      To align a FASTA file (unaligned.fasta) with the output in ClustalW 
 25      format (file aligned.aln), and otherwise default settings, use: 
 26   
 27      >>> from Bio.Align.Applications import TCoffeeCommandline 
 28      >>> tcoffee_cline = TCoffeeCommandline(infile="unaligned.fasta", 
 29      ...                                    output="clustalw", 
 30      ...                                    outfile="aligned.aln") 
 31      >>> print tcoffee_cline 
 32      t_coffee -output clustalw -infile unaligned.fasta -outfile aligned.aln 
 33   
 34      You would typically run the command line with tcoffee_cline() or via 
 35      the Python subprocess module, as described in the Biopython tutorial. 
 36   
 37      Citation: 
 38   
 39      T-Coffee: A novel method for multiple sequence alignments. 
 40      Notredame, Higgins, Heringa, JMB,302(205-217) 2000 
 41   
 42      Last checked against: Version_6.92 
 43      """ 
 44      SEQ_TYPES = ["dna","protein","dna_protein"] 
 45   
 46 -    def __init__(self, cmd="t_coffee", **kwargs): 
 47          self.parameters = [ 
 48             _Option(["-output", "output"], 
 49                     """Specify the output type. 
 50                     One (or more separated by a comma) of: 
 51                     'clustalw_aln', 'clustalw', 'gcg', 'msf_aln', 
 52                     'pir_aln', 'fasta_aln', 'phylip', 'pir_seq', 'fasta_seq' 
 53   
 54                     Note that of these Biopython's AlignIO module will only 
 55                     read clustalw, pir, and fasta. 
 56                     """,  # TODO - Can we read the PHYLIP output? 
 57                     equate=False), 
 58             _Option(["-infile", "infile"], 
 59                     "Specify the input file.", 
 60                     filename=True, 
 61                     is_required=True, 
 62                     equate=False), 
 63             #Indicates the name of the alignment output by t_coffee. If the 
 64             #default is used, the alignment is named <your sequences>.aln 
 65             _Option(["-outfile", "outfile"], 
 66                     "Specify the output file. Default: <your sequences>.aln", 
 67                     filename=True, 
 68                     equate=False), 
 69             _Switch(["-convert", "convert"], 
 70                     "Specify you want to perform a file conversion"), 
 71             _Option(["-type", "type"], 
 72                     "Specify the type of sequence being aligned", 
 73                     checker_function=lambda x: x in self.SEQ_TYPES, 
 74                     equate=False), 
 75             _Option(["-outorder", "outorder"], 
 76                     "Specify the order of sequence to output" 
 77                     "Either 'input', 'aligned' or <filename> of " 
 78                     "Fasta file with sequence order", 
 79                     equate=False), 
 80             _Option(["-matrix", "matrix"], 
 81                     "Specify the filename of the substitution matrix to use." 
 82                     "Default: blosum62mt", 
 83                     equate=False), 
 84             _Option(["-gapopen", "gapopen"], 
 85                     "Indicates the penalty applied for opening a gap " 
 86                     "(negative integer)", 
 87                     checker_function=lambda x: isinstance(x, int), 
 88                     equate=False), 
 89             _Option(["-gapext", "gapext"], 
 90                     "Indicates the penalty applied for extending a " 
 91                     "gap. (negative integer)", 
 92                     checker_function=lambda x: isinstance(x, int), 
 93                     equate=False), 
 94             _Switch(["-quiet", "quiet"], 
 95                     "Turn off log output"), 
 96             _Option(["-mode", "mode"], 
 97                     "Specifies a special mode: genome, quickaln, dali, 3dcoffee", 
 98                     equate=False), 
 99             ] 
100          AbstractCommandline.__init__(self, cmd, **kwargs) 
101   
102   
103 -def _test(): 
104      """Run the module's doctests (PRIVATE).""" 
105      print "Running modules doctests..." 
106      import doctest 
107      doctest.testmod() 
108      print "Done" 
109   
110  if __name__ == "__main__": 
111      _test() 
112