Source Code for Module Bio.ExPASy.Enzyme

  1  # Copyright 1999 by Jeffrey Chang.  All rights reserved. 
  2  # Copyright 2009 by Michiel de Hoon.  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  """ 
  8  This module provides code to work with the enzyme.dat file from 
  9  Enzyme. 
 10  http://www.expasy.ch/enzyme/ 
 11   
 12  Tested with the release of 03-Mar-2009. 
 13   
 14  Functions: 
 15  read       Reads a file containing one ENZYME entry 
 16  parse      Reads a file containing multiple ENZYME entries 
 17   
 18  Classes: 
 19  Record     Holds ENZYME data. 
 20   
 21  """ 
 22   
 23   
 24 -def parse(handle): 
 25      """Parse ENZYME records. 
 26   
 27      This function is for parsing ENZYME files containing multiple 
 28      records. 
 29   
 30      handle   - handle to the file.""" 
 31   
 32      while True: 
 33          record = __read(handle) 
 34          if not record: 
 35              break 
 36          yield record 
 37   
 38   
 39 -def read(handle): 
 40      """Read one ENZYME record. 
 41   
 42      This function is for parsing ENZYME files containing 
 43      exactly one record. 
 44   
 45      handle   - handle to the file.""" 
 46   
 47      record = __read(handle) 
 48      # We should have reached the end of the record by now 
 49      remainder = handle.read() 
 50      if remainder: 
 51          raise ValueError("More than one ENZYME record found") 
 52      return record 
 53   
 54   
 55 -class Record(dict): 
 56      """\ 
 57  Holds information from an ExPASy ENZYME record as a Python dictionary. 
 58   
 59  Each record contains the following keys: 
 60      ID: EC number 
 61      DE: Recommended name 
 62      AN: Alternative names (if any) 
 63      CA: Catalytic activity 
 64      CF: Cofactors (if any) 
 65      PR: Pointers to the Prosite documentation entrie(s) that 
 66          correspond to the enzyme (if any) 
 67      DR: Pointers to the Swiss-Prot protein sequence entrie(s) 
 68          that correspond to the enzyme (if any) 
 69      CC: Comments 
 70  """ 
 71   
 72 -    def __init__(self): 
 73          dict.__init__(self) 
 74          self["ID"] = '' 
 75          self["DE"] = '' 
 76          self["AN"] = [] 
 77          self["CA"] = '' 
 78          self["CF"] = '' 
 79          self["CC"] = []   # one comment per line 
 80          self["PR"] = [] 
 81          self["DR"] = [] 
 82   
 83 -    def __repr__(self): 
 84          if self["ID"]: 
 85              if self["DE"]: 
 86                  return "%s (%s, %s)" % (self.__class__.__name__, 
 87                                          self["ID"], self["DE"]) 
 88              else: 
 89                  return "%s (%s)" % (self.__class__.__name__, 
 90                                         self["ID"]) 
 91          else: 
 92              return "%s ( )" % (self.__class__.__name__) 
 93   
 94 -    def __str__(self): 
 95          output = "ID: " + self["ID"] 
 96          output += " DE: " + self["DE"] 
 97          output += " AN: " + repr(self["AN"]) 
 98          output += " CA: '" + self["CA"] + "'" 
 99          output += " CF: " + self["CF"] 
100          output += " CC: " + repr(self["CC"]) 
101          output += " PR: " + repr(self["PR"]) 
102          output += " DR: %d Records" % len(self["DR"]) 
103          return output 
104   
105  # Everything below is private 
106   
107   
108 -def __read(handle): 
109      record = None 
110      for line in handle: 
111          key, value = line[:2], line[5:].rstrip() 
112          if key=="ID": 
113              record = Record() 
114              record["ID"] = value 
115          elif key=="DE": 
116              record["DE"]+=value 
117          elif key=="AN": 
118              if record["AN"] and not record["AN"][-1].endswith("."): 
119                  record["AN"][-1] += " " + value 
120              else: 
121                  record["AN"].append(value) 
122          elif key=="CA": 
123              record["CA"] += value 
124          elif key=="DR": 
125              pair_data = value.rstrip(";").split(';') 
126              for pair in pair_data: 
127                  t1, t2 = pair.split(',') 
128                  row = [t1.strip(), t2.strip()] 
129                  record["DR"].append(row) 
130          elif key=="CF": 
131              if record["CF"]: 
132                  record["CF"] += " " + value 
133              else: 
134                  record["CF"] = value 
135          elif key=="PR": 
136              assert value.startswith("PROSITE; ") 
137              value = value[9:].rstrip(";") 
138              record["PR"].append(value) 
139          elif key=='CC': 
140              if value.startswith("-!- "): 
141                  record["CC"].append(value[4:]) 
142              elif value.startswith("    ") and record["CC"]: 
143                  record["CC"][-1] += value[3:] 
144              # copyright notice is silently skipped 
145          elif key=="//": 
146              if record: 
147                  return record 
148              else: # This was the copyright notice 
149                  continue 
150      if record: 
151          raise ValueError("Unexpected end of stream") 
152