Bio.KEGG.Enzyme

1 # Copyright 2001 by Tarjei Mikkelsen. All rights reserved. 2 # Copyright 2007 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 KEGG Enzyme database. 9 10 Functions: 11 parse - Returns an iterator giving Record objects. 12 13 Classes: 14 Record -- Holds the information from a KEGG Enzyme record. 15 """ 16 17 from Bio.KEGG import _write_kegg 18 from Bio.KEGG import _wrap_kegg 19 20 21 # Set up line wrapping rules (see Bio.KEGG._wrap_kegg) 22 rxn_wrap = [0, "", 23 (" + ","",1,1), 24 (" = ","",1,1), 25 (" ","$",1,1), 26 ("-","$",1,1)] 27 name_wrap = [0, "", 28 (" ","$",1,1), 29 ("-","$",1,1)] 30 id_wrap = lambda indent : [indent, "", 31 (" ","",1,0)] 32 struct_wrap = lambda indent : [indent, "", 33 (" ","",1,1)] 34 35

36 -class Record(object):

37 """Holds info from a KEGG Enzyme record. 38 39 Members: 40 entry The EC number (withou the 'EC '). 41 name A list of the enzyme names. 42 classname A list of the classification terms. 43 sysname The systematic name of the enzyme. 44 reaction A list of the reaction description strings. 45 substrate A list of the substrates. 46 product A list of the products. 47 inhibitor A list of the inhibitors. 48 cofactor A list of the cofactors. 49 effector A list of the effectors. 50 comment A list of the comment strings. 51 pathway A list of 3-tuples: (database, id, pathway) 52 genes A list of 2-tuples: (organism, list of gene ids) 53 disease A list of 3-tuples: (database, id, disease) 54 structures A list of 2-tuples: (database, list of struct ids) 55 dblinks A list of 2-tuples: (database, list of db ids) 56 """

57 - def __init__(self):

58 """__init___(self) 59 60 Create a new Record. 61 """ 62 self.entry = "" 63 self.name = [] 64 self.classname = [] 65 self.sysname = [] 66 self.reaction = [] 67 self.substrate = [] 68 self.product = [] 69 self.inhibitor = [] 70 self.cofactor = [] 71 self.effector = [] 72 self.comment = [] 73 self.pathway = [] 74 self.genes = [] 75 self.disease = [] 76 self.structures = [] 77 self.dblinks = []

78

79 - def __str__(self):

80 """__str__(self) 81 82 Returns a string representation of this Record. 83 """ 84 return self._entry() + \ 85 self._name() + \ 86 self._classname() + \ 87 self._sysname() + \ 88 self._reaction() + \ 89 self._substrate() + \ 90 self._product() + \ 91 self._inhibitor() + \ 92 self._cofactor() + \ 93 self._effector() + \ 94 self._comment() + \ 95 self._pathway() + \ 96 self._genes() + \ 97 self._disease() + \ 98 self._structures() + \ 99 self._dblinks() + \ 100 "///"

101

102 - def _entry(self):

103 return _write_kegg("ENTRY", 104 ["EC " + self.entry])

105

106 - def _name(self):

107 return _write_kegg("NAME", 108 [_wrap_kegg(l, wrap_rule = name_wrap) 109 for l in self.name])

110

111 - def _classname(self):

112 return _write_kegg("CLASS", 113 self.classname)

114

115 - def _sysname(self):

116 return _write_kegg("SYSNAME", 117 [_wrap_kegg(l, wrap_rule = name_wrap) 118 for l in self.sysname])

119

120 - def _reaction(self):

121 return _write_kegg("REACTION", 122 [_wrap_kegg(l, wrap_rule = rxn_wrap) 123 for l in self.reaction])

124

125 - def _substrate(self):

126 return _write_kegg("SUBSTRATE", 127 [_wrap_kegg(l, wrap_rule = name_wrap) 128 for l in self.substrate])

129

130 - def _product(self):

131 return _write_kegg("PRODUCT", 132 [_wrap_kegg(l, wrap_rule = name_wrap) 133 for l in self.product])

134

135 - def _inhibitor(self):

136 return _write_kegg("INHIBITOR", 137 [_wrap_kegg(l, wrap_rule = name_wrap) 138 for l in self.inhibitor])

139

140 - def _cofactor(self):

141 return _write_kegg("COFACTOR", 142 [_wrap_kegg(l, wrap_rule = name_wrap) 143 for l in self.cofactor])

144

145 - def _effector(self):

146 return _write_kegg("EFFECTOR", 147 [_wrap_kegg(l, wrap_rule = name_wrap) 148 for l in self.effector])

149

150 - def _comment(self):

151 return _write_kegg("COMMENT", 152 [_wrap_kegg(l, wrap_rule = id_wrap(0)) 153 for l in self.comment])

154

155 - def _pathway(self):

156 s = [] 157 for entry in self.pathway: 158 s.append(entry[0] + ": " + entry[1] + " " + entry[2]) 159 return _write_kegg("PATHWAY", 160 [_wrap_kegg(l, wrap_rule = id_wrap(16)) 161 for l in s])

162

163 - def _genes(self):

164 s = [] 165 for entry in self.genes: 166 s.append(entry[0] + ": " + " ".join(entry[1])) 167 return _write_kegg("GENES", 168 [_wrap_kegg(l, wrap_rule = id_wrap(5)) 169 for l in s])

170

171 - def _disease(self):

172 s = [] 173 for entry in self.disease: 174 s.append(entry[0] + ": " + entry[1] + " " + entry[2]) 175 return _write_kegg("DISEASE", 176 [_wrap_kegg(l, wrap_rule = id_wrap(13)) 177 for l in s])

178

179 - def _structures(self):

180 s = [] 181 for entry in self.structures: 182 s.append(entry[0] + ": " + " ".join(entry[1]) + " ") 183 return _write_kegg("STRUCTURES", 184 [_wrap_kegg(l, wrap_rule = struct_wrap(5)) 185 for l in s])

186

187 - def _dblinks(self):

188 # This is a bit of a cheat that won't work if enzyme entries 189 # have more than one link id per db id. For now, that's not 190 # the case - storing links ids in a list is only to make 191 # this class similar to the Compound.Record class. 192 s = [] 193 for entry in self.dblinks: 194 s.append(entry[0] + ": " + " ".join(entry[1])) 195 return _write_kegg("DBLINKS", s)

196 197

198 -def parse(handle):

199 """Parse a KEGG Enzyme file, returning Record objects. 200 201 This is an iterator function, typically used in a for loop. For 202 example, using one of the example KEGG files in the Biopython 203 test suite, 204 205 >>> handle = open("KEGG/enzyme.sample") 206 >>> for record in parse(handle): 207 ... print record.entry, record.name[0] 208 ... 209 1.1.1.1 Alcohol dehydrogenase 210 1.1.1.62 Estradiol 17beta-dehydrogenase 211 1.1.1.68 Transferred to EC 1.7.99.5 212 1.6.5.3 NADH dehydrogenase (ubiquinone) 213 1.14.13.28 3,9-Dihydroxypterocarpan 6a-monooxygenase 214 2.4.1.68 Glycoprotein 6-alpha-L-fucosyltransferase 215 3.1.1.6 Acetylesterase 216 2.7.2.1 Acetate kinase 217 """ 218 record = Record() 219 for line in handle: 220 if line[:3]=="///": 221 yield record 222 record = Record() 223 continue 224 if line[:12]!=" ": 225 keyword = line[:12] 226 data = line[12:].strip() 227 if keyword=="ENTRY ": 228 words = data.split() 229 record.entry = words[1] 230 elif keyword=="CLASS ": 231 record.classname.append(data) 232 elif keyword=="COFACTOR ": 233 record.cofactor.append(data) 234 elif keyword=="COMMENT ": 235 record.comment.append(data) 236 elif keyword=="DBLINKS ": 237 if ":" in data: 238 key, values = data.split(":") 239 values = values.split() 240 row = (key, values) 241 record.dblinks.append(row) 242 else: 243 row = record.dblinks[-1] 244 key, values = row 245 values.extend(data.split()) 246 row = key, values 247 record.dblinks[-1] = row 248 elif keyword=="DISEASE ": 249 if ":" in data: 250 database, data = data.split(":") 251 number, name = data.split(None, 1) 252 row = (database, number, name) 253 record.disease.append(row) 254 else: 255 row = record.disease[-1] 256 database, number, name = row 257 name = name + " " + data 258 row = database, number, name 259 record.disease[-1] = row 260 elif keyword=="EFFECTOR ": 261 record.effector.append(data.strip(";")) 262 elif keyword=="GENES ": 263 if data[3:5]==': ': 264 key, values = data.split(":",1) 265 values = [value.split("(")[0] for value in values.split()] 266 row = (key, values) 267 record.genes.append(row) 268 else: 269 row = record.genes[-1] 270 key, values = row 271 for value in data.split(): 272 value = value.split("(")[0] 273 values.append(value) 274 row = key, values 275 record.genes[-1] = row 276 elif keyword=="INHIBITOR ": 277 record.inhibitor.append(data.strip(";")) 278 elif keyword=="NAME ": 279 record.name.append(data.strip(";")) 280 elif keyword=="PATHWAY ": 281 if data[:5]=='PATH:': 282 _, map_num, name = data.split(None,2) 283 pathway = ('PATH', map_num, name) 284 record.pathway.append(pathway) 285 else: 286 ec_num, name = data.split(None,1) 287 pathway = 'PATH', ec_num, name 288 record.pathway.append(pathway) 289 elif keyword=="PRODUCT ": 290 record.product.append(data.strip(";")) 291 elif keyword=="REACTION ": 292 record.reaction.append(data.strip(";")) 293 elif keyword=="STRUCTURES ": 294 if data[:4]=='PDB:': 295 database = data[:3] 296 accessions = data[4:].split() 297 row = (database, accessions) 298 record.structures.append(row) 299 else: 300 row = record.structures[-1] 301 database, accessions = row 302 accessions.extend(data.split()) 303 row = (database, accessions) 304 record.structures[-1] = row 305 elif keyword=="SUBSTRATE ": 306 record.substrate.append(data.strip(";")) 307 elif keyword=="SYSNAME ": 308 record.sysname.append(data.strip(";"))

309 310 311 if __name__ == "__main__": 312 from Bio._utils import run_doctest 313 run_doctest() 314

Source Code for Package Bio.KEGG.Enzyme