Bio.Enzyme

1 # Copyright 1999 by Jeffrey Chang. 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 6 """Module to work with enzyme.dat file (DEPRECATED). 7 8 This module provides code to work with the enzyme.dat file from 9 Enzyme (OBSOLETE as of Biopython version 1.50). 10 http://www.expasy.ch/enzyme/ 11 12 The functionality of Bio.Enzyme has moved to Bio.ExPASy.ExPASy; 13 please use that module instead of Bio.Enzyme. Bio.Enzyme is now 14 deprecated and will be removed in a future release of Biopython. 15 """ 16 17 import warnings 18 import Bio 19 warnings.warn("Bio.Enzyme is deprecated, and will be removed in a"\ 20 " future release of Biopython. Most of the functionality " 21 " is now provided by Bio.ExPASy.Enzyme. If you want to " 22 " continue to use Bio.Enzyme, please get in contact " 23 " via the mailing lists to avoid its permanent removal from"\ 24 " Biopython.", Bio.BiopythonDeprecationWarning) 25 26 from Bio import File 27 from Bio.ParserSupport import * 28

29 -class _Scanner:

30 """Scans Enzyme data (PRIVATE). 31 32 Tested with: 33 Release 33 34 """ 35

36 - def feed(self, handle, consumer):

37 """feed(self, handle, consumer) 38 39 Feed in Enzyme data for scanning. handle is a file-like object 40 that contains keyword information. consumer is a Consumer 41 object that will receive events as the report is scanned. 42 43 """ 44 if isinstance(handle, File.UndoHandle): 45 uhandle = handle 46 else: 47 uhandle = File.UndoHandle(handle) 48 49 while not is_blank_line(uhandle.peekline()): # Am I done yet? 50 self._scan_record(uhandle, consumer)

51

52 - def _scan_record(self, uhandle, consumer):

53 # The first record is just copyright information embedded in 54 # comments. Check to see if I'm at the first record. If so, 55 # then just scan the comments and the terminator. 56 consumer.start_record() 57 line = uhandle.peekline() 58 if line[:2] == 'CC': 59 self._scan_cc(uhandle, consumer) 60 self._scan_terminator(uhandle, consumer) 61 else: 62 for fn in self._scan_fns: 63 fn(self, uhandle, consumer) 64 consumer.end_record()

65

66 - def _scan_line(self, line_type, uhandle, event_fn, 67 exactly_one=None, one_or_more=None, any_number=None, 68 up_to_one=None):

69 # Callers must set exactly one of exactly_one, one_or_more, or 70 # any_number to a true value. I do not explicitly check to 71 # make sure this function is called correctly. 72 73 # This does not guarantee any parameter safety, but I 74 # like the readability. The other strategy I tried was have 75 # parameters min_lines, max_lines. 76 77 if exactly_one or one_or_more: 78 read_and_call(uhandle, event_fn, start=line_type) 79 if one_or_more or any_number: 80 while 1: 81 if not attempt_read_and_call(uhandle, event_fn, 82 start=line_type): 83 break 84 if up_to_one: 85 attempt_read_and_call(uhandle, event_fn, start=line_type)

86

87 - def _scan_id(self, uhandle, consumer):

88 self._scan_line('ID', uhandle, consumer.identification, exactly_one=1)

89

90 - def _scan_de(self, uhandle, consumer):

91 self._scan_line('DE', uhandle, consumer.description, one_or_more=1)

92

93 - def _scan_an(self, uhandle, consumer):

94 self._scan_line('AN', uhandle, consumer.alternate_name, any_number=1)

95

96 - def _scan_ca(self, uhandle, consumer):

97 self._scan_line('CA', uhandle, consumer.catalytic_activity, 98 any_number=1)

99

100 - def _scan_cf(self, uhandle, consumer):

101 self._scan_line('CF', uhandle, consumer.cofactor, any_number=1)

102

103 - def _scan_cc(self, uhandle, consumer):

104 self._scan_line('CC', uhandle, consumer.comment, any_number=1)

105

106 - def _scan_di(self, uhandle, consumer):

107 self._scan_line('DI', uhandle, consumer.disease, any_number=1)

108

109 - def _scan_pr(self, uhandle, consumer):

110 self._scan_line('PR', uhandle, consumer.prosite_reference, 111 any_number=1)

112

113 - def _scan_dr(self, uhandle, consumer):

114 self._scan_line('DR', uhandle, consumer.databank_reference, 115 any_number=1)

116

117 - def _scan_terminator(self, uhandle, consumer):

118 self._scan_line('//', uhandle, consumer.terminator, exactly_one=1)

119 120 _scan_fns = [ 121 _scan_id, 122 _scan_de, 123 _scan_an, 124 _scan_ca, 125 _scan_cf, 126 _scan_cc, 127 _scan_di, 128 _scan_pr, 129 _scan_dr, 130 _scan_terminator 131 ]

132 -class DataRecord:

133 - def __init__(self,tr_code='',sw_code=''):

134 self.tr_code = tr_code 135 self.sw_code = sw_code

136

137 - def __str__(self):

138 return self.tr_code + ", " + self.sw_code

139

140 -class EnzymeRecord:

141 - def __init__(self):

142 self.ID = '' 143 self.DE = [] 144 self.AN = [] 145 self.CA = '' 146 self.CF = [] 147 self.CC = [] # one comment per line 148 self.DI = [] 149 self.PR = [] 150 self.DR = []

151

152 - def __repr__(self):

153 if self.ID: 154 if self.DE: 155 return "%s (%s, %s)" % (self.__class__.__name__, 156 self.ID, self.DE[0]) 157 else: 158 return "%s (%s)" % (self.__class__.__name__, 159 self.ID) 160 else: 161 return "%s ( )" % (self.__class__.__name__)

162

163 - def __str__(self):

164 output = "ID: " + self.ID 165 output += " DE: " + repr(self.DE) 166 output += " AN: " + repr(self.AN) 167 output += " CA: '" + self.CA + "'" 168 output += " CF: " + repr(self.CF) 169 output += " CC: " + repr(self.CC) 170 output += " DI: " + repr(self.DI) 171 output += " PR: " + repr(self.PR) 172 output += " DR: %d Records" % len(self.DR) 173 174 return output

175

176 -class RecordParser(AbstractParser):

177 - def __init__(self):

178 self._scanner = _Scanner() 179 self._consumer = _RecordConsumer()

180

181 - def parse(self, handle):

182 if isinstance(handle, File.UndoHandle): 183 uhandle = handle 184 else: 185 uhandle = File.UndoHandle(handle) 186 self._scanner.feed(uhandle, self._consumer) 187 return self._consumer.enzyme_record

188

189 -class Iterator:

190 - def __init__(self, handle, parser=None):

191 self._uhandle = File.UndoHandle(handle)

192

193 - def next(self):

194 self._parser = RecordParser() 195 lines = [] 196 while True: 197 line = self._uhandle.readline() 198 if not line: break 199 if line[:2] == '//': 200 break 201 lines.append(line) 202 if not lines: 203 return None 204 lines.append('//') 205 data = ''.join(lines) 206 if self._parser is not None: 207 return self._parser.parse(File.StringHandle(data)) 208 return data

209

210 - def __iter__(self):

211 return iter(self.next, None)

212

213 -class _RecordConsumer(AbstractConsumer):

214 - def __init__(self):

215 self.enzyme_record = EnzymeRecord()

216 - def identification(self, id_info):

217 self.enzyme_record.ID = id_info.split()[1]

218 - def description(self,de_info):

219 self.enzyme_record.DE.append(de_info[2:].strip())

220 - def alternate_name(self,an_info):

221 self.enzyme_record.AN.append(an_info[2:].strip())

222 - def catalytic_activity(self, ca_info):

223 self.enzyme_record.CA = ''.join([self.enzyme_record.CA, ca_info[2:].strip()])

224 - def cofactor(self, cf_info):

225 self.enzyme_record.CF.append(cf_info[2:].strip())

226 - def comment(self, cc_info):

227 cc = cc_info[2:].strip() 228 if cc.startswith("-!-"): 229 self.enzyme_record.CC.append(cc[len("-!-"):].strip()) 230 else: 231 # The header is all CC, but doesn't start with -!- 232 if self.enzyme_record.CC: 233 pre_cc = self.enzyme_record.CC.pop() 234 else: 235 pre_cc = "" 236 new_cc = pre_cc + " " + cc 237 self.enzyme_record.CC.append(new_cc)

238 - def disease(self, di_info):

239 self.enzyme_record.DI.append(di_info[2:].strip())

240

241 - def prosite_reference(self,pr_info):

242 self.enzyme_record.PR.append(pr_info.split(';')[1].strip())

243

244 - def databank_reference(self,dr_info):

245 good_data = dr_info[2:].strip() 246 pair_data = good_data.split(';') 247 for pair in pair_data: 248 if not pair: continue 249 data_record = DataRecord() 250 t1, t2 = pair.split(',') 251 data_record.tr_code, data_record.sw_code = \ 252 t1.strip(), t2.strip() 253 self.enzyme_record.DR.append(data_record)

254

255 - def terminator(self,schwarzenegger):

256 pass # Hasta la Vista, baby!

257

Source Code for Package Bio.Enzyme