Source Code for Module Bio.motifs.mast

  1  # Copyright 2008 by Bartek Wilczynski. 
  2  # Adapted from Bio.MEME.Parser by Jason A. Hackney.  All rights reserved. 
  3  # This code is part of the Biopython distribution and governed by its 
  4  # license.  Please see the LICENSE file that should have been included 
  5  # as part of this package. 
  6   
  7  from Bio.Alphabet import IUPAC 
  8  from Bio.motifs import meme 
  9   
 10   
 11 -class Record(list): 
 12      """The class for holding the results from a MAST run. 
 13   
 14      A mast.Record holds data about matches between motifs and sequences. 
 15      The motifs held by the Record are objects of the class meme.Motif. 
 16   
 17      The mast.Record class inherits from list, so you can access individual 
 18      motifs in the record by their index. Alternatively, you can find a motif 
 19      by its name: 
 20   
 21      >>> f = open("mast.output.txt") 
 22      >>> from Bio import motifs 
 23      >>> record = motifs.parse(f, 'MAST') 
 24      >>> motif = record[0] 
 25      >>> print motif.name 
 26      1 
 27      >>> motif = record['1'] 
 28      >>> print motif.name 
 29      1 
 30      """ 
 31   
 32 -    def __init__(self): 
 33          self.sequences = [] 
 34          self.version = "" 
 35          self.database = "" 
 36          self.diagrams = {} 
 37          self.alphabet = None 
 38   
 39 -    def __getitem__(self, key): 
 40          if isinstance(key, str): 
 41              for motif in self: 
 42                  if motif.name==key: 
 43                      return motif 
 44          else: 
 45              return list.__getitem__(self, key) 
 46   
 47   
 48 -def read(handle): 
 49      """read(handle)""" 
 50      record = Record() 
 51      __read_version(record, handle) 
 52      __read_database_and_motifs(record, handle) 
 53      __read_section_i(record, handle) 
 54      __read_section_ii(record, handle) 
 55      __read_section_iii(record, handle) 
 56      return record 
 57   
 58   
 59  # Everything below is private 
 60   
 61   
 62 -def __read_version(record, handle): 
 63      for line in handle: 
 64          if "MAST version" in line: 
 65              break 
 66      else: 
 67          raise ValueError("Improper input file. Does not begin with a line with 'MAST version'") 
 68      record.version = line.strip().split()[2] 
 69   
 70   
 71 -def __read_database_and_motifs(record, handle): 
 72      for line in handle: 
 73          if line.startswith('DATABASE AND MOTIFS'): 
 74              break 
 75      line = handle.next() 
 76      if not line.startswith('****'): 
 77          raise ValueError("Line does not start with '****':\n%s" % line) 
 78      line = handle.next() 
 79      if not 'DATABASE' in line: 
 80          raise ValueError("Line does not contain 'DATABASE':\n%s" % line) 
 81      words = line.strip().split() 
 82      record.database = words[1] 
 83      if words[2] == '(nucleotide)': 
 84          record.alphabet = IUPAC.unambiguous_dna 
 85      elif words[2] == '(peptide)': 
 86          record.alphabet = IUPAC.protein 
 87      for line in handle: 
 88          if 'MOTIF WIDTH' in line: 
 89              break 
 90      line = handle.next() 
 91      if not '----' in line: 
 92          raise ValueError("Line does not contain '----':\n%s" % line) 
 93      for line in handle: 
 94          if not line.strip(): 
 95              break 
 96          words = line.strip().split() 
 97          motif = meme.Motif(record.alphabet) 
 98          motif.name = words[0] 
 99          motif.length = int(words[1]) 
100          # words[2] contains the best possible match 
101          record.append(motif) 
102   
103   
104 -def __read_section_i(record, handle): 
105      for line in handle: 
106          if line.startswith('SECTION I:'): 
107              break 
108      for line in handle: 
109          if line.startswith('SEQUENCE NAME'): 
110              break 
111      line = handle.next() 
112      if not line.startswith('---'): 
113          raise ValueError("Line does not start with '---':\n%s" % line) 
114      for line in handle: 
115          if not line.strip(): 
116              break 
117          else: 
118              sequence, description_evalue_length = line.split(None, 1) 
119              record.sequences.append(sequence) 
120      line = handle.next() 
121      if not line.startswith('****'): 
122          raise ValueError("Line does not start with '****':\n%s" % line) 
123   
124   
125 -def __read_section_ii(record, handle): 
126      for line in handle: 
127          if line.startswith('SECTION II:'): 
128              break 
129      for line in handle: 
130          if line.startswith('SEQUENCE NAME'): 
131              break 
132      line = handle.next() 
133      if not line.startswith('---'): 
134          raise ValueError("Line does not start with '---':\n%s" % line) 
135      for line in handle: 
136          if not line.strip(): 
137              break 
138          elif line.startswith(" "): 
139              diagram = line.strip() 
140              record.diagrams[sequence] += diagram 
141          else: 
142              sequence, pvalue, diagram = line.split() 
143              record.diagrams[sequence] = diagram 
144      line = handle.next() 
145      if not line.startswith('****'): 
146          raise ValueError("Line does not start with '****':\n%s" % line) 
147   
148   
149 -def __read_section_iii(record, handle): 
150      for line in handle: 
151          if line.startswith('SECTION III:'): 
152              break 
153      for line in handle: 
154          if line.startswith('****'): 
155              break 
156      for line in handle: 
157          if line.startswith('*****'): 
158              break 
159      for line in handle: 
160          if line.strip(): 
161              break 
162