Source Code for Package Bio.Motif

  1  # Copyright 2003-2009 by Bartek Wilczynski.  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  """Tools for sequence motif analysis (OBSOLETE, see Bio.motifs instead). 
  6   
  7  This module (Bio.Motif) is now obsolete, and will be deprecated and 
  8  removed in a future release of release of Biopython. Please use the 
  9  new module Bio.motifs instead. 
 10   
 11  This contains the core Motif class containing various I/O methods as 
 12  well as methods for motif comparisons and motif searching in sequences. 
 13  It also inlcudes functionality for parsing AlignACE and MEME programs. 
 14  """ 
 15   
 16  import warnings 
 17  warnings.warn("The module Bio.Motif is now obsolete, and will be" 
 18                "deprecated and removed in a future release of" 
 19                "release of Biopython. As a replacement for Bio.Motif," 
 20                "please use the new module Bio.motifs instead. Please" 
 21                "be aware that though the functionality of Bio.Motif" 
 22                "is retained (and extended) in Bio.motifs, usage may" 
 23                "be different.", 
 24                PendingDeprecationWarning) 
 25   
 26   
 27  from Bio.Motif._Motif import Motif 
 28  from Bio.Motif.Parsers.AlignAce import read as _AlignAce_read 
 29  from Bio.Motif.Parsers.MEME import read as _MEME_read 
 30  from Bio.Motif.Thresholds import ScoreDistribution 
 31   
 32  _parsers={"AlignAce" : _AlignAce_read, 
 33            "MEME" : _MEME_read, 
 34            } 
 35   
 36 -def _from_pfm(handle): 
 37      return Motif()._from_jaspar_pfm(handle) 
 38   
 39 -def _from_sites(handle): 
 40      return Motif()._from_jaspar_sites(handle) 
 41   
 42  _readers={"jaspar-pfm": _from_pfm, 
 43            "jaspar-sites": _from_sites 
 44            } 
 45   
 46   
 47             
 48 -def parse(handle,format): 
 49      """Parses an output file of motif finding programs. 
 50   
 51      Currently supported formats: 
 52       - AlignAce 
 53       - MEME 
 54   
 55      You can also use single-motif formats, although the Bio.Motif.read() 
 56      function is simpler to use in this situation. 
 57       - jaspar-pfm 
 58       - jaspar-sites 
 59   
 60      For example: 
 61   
 62      >>> from Bio import Motif 
 63      >>> for motif in Motif.parse(open("Motif/alignace.out"),"AlignAce"): 
 64      ...     print motif.consensus() 
 65      TCTACGATTGAG 
 66      CTGCACCTAGCTACGAGTGAG 
 67      GTGCCCTAAGCATACTAGGCG 
 68      GCCACTAGCAGAGCAGGGGGC 
 69      CGACTCAGAGGTT 
 70      CCACGCTAAGAGAAGTGCCGGAG 
 71      GCACGTCCCTGAGCA 
 72      GTCCATCGCAAAGCGTGGGGC 
 73      GAGATCAGAGGGCCG 
 74      TGGACGCGGGG 
 75      GACCAGAGCCTCGCATGGGGG 
 76      AGCGCGCGTG 
 77      GCCGGTTGCTGTTCATTAGG 
 78      ACCGACGGCAGCTAAAAGGG 
 79      GACGCCGGGGAT 
 80      CGACTCGCGCTTACAAGG 
 81      """ 
 82      try: 
 83          parser=_parsers[format] 
 84           
 85      except KeyError: 
 86          try: #not a true parser, try reader formats 
 87              reader=_readers[format] 
 88          except: 
 89              raise ValueError("Wrong parser format") 
 90          else: #we have a proper reader  
 91              yield reader(handle) 
 92      else: # we have a proper reader 
 93          for m in parser(handle).motifs: 
 94              yield m 
 95   
 96 -def read(handle,format): 
 97      """Reads a motif from a handle using a specified file-format. 
 98   
 99      This supports the same formats as Bio.Motif.parse(), but 
100      only for files containing exactly one record.  For example, 
101      reading a pfm file: 
102   
103      >>> from Bio import Motif 
104      >>> motif = Motif.read(open("Motif/SRF.pfm"),"jaspar-pfm") 
105      >>> motif.consensus() 
106      Seq('GCCCATATATGG', IUPACUnambiguousDNA()) 
107   
108      Or a single-motif MEME file, 
109   
110      >>> from Bio import Motif 
111      >>> motif =  Motif.read(open("Motif/meme.out"),"MEME") 
112      >>> motif.consensus() 
113      Seq('CTCAATCGTA', IUPACUnambiguousDNA()) 
114   
115      If the handle contains no records, or more than one record, 
116      an exception is raised: 
117   
118      >>> from Bio import Motif 
119      >>> motif = Motif.read(open("Motif/alignace.out"),"AlignAce") 
120      Traceback (most recent call last): 
121          ... 
122      ValueError: More than one motif found in handle 
123   
124      If however you want the first record from a file containing 
125      multiple records this function would raise an exception (as 
126      shown in the example above).  Instead use: 
127   
128      >>> from Bio import Motif 
129      >>> motif = Motif.parse(open("Motif/alignace.out"),"AlignAce").next() 
130      >>> motif.consensus() 
131      Seq('TCTACGATTGAG', IUPACUnambiguousDNA()) 
132   
133      Use the Bio.Motif.parse(handle, format) function if you want 
134      to read multiple records from the handle. 
135      """ 
136      iterator = parse(handle, format) 
137      try: 
138          first = iterator.next() 
139      except StopIteration: 
140          first = None 
141      if first is None: 
142          raise ValueError("No motifs found in handle") 
143      try: 
144          second = iterator.next() 
145      except StopIteration: 
146          second = None 
147      if second is not None: 
148          raise ValueError("More than one motif found in handle") 
149      return first 
150   
151   
152 -def _test(): 
153      """Run the Bio.Motif module's doctests. 
154   
155      This will try and locate the unit tests directory, and run the doctests 
156      from there in order that the relative paths used in the examples work. 
157      """ 
158      import doctest 
159      import os 
160      if os.path.isdir(os.path.join("..","..","Tests")): 
161          print "Runing doctests..." 
162          cur_dir = os.path.abspath(os.curdir) 
163          os.chdir(os.path.join("..","..","Tests")) 
164          doctest.testmod() 
165          os.chdir(cur_dir) 
166          del cur_dir 
167          print "Done" 
168   
169  if __name__ == "__main__": 
170      #Run the doctests 
171      _test() 
172