|
0
|
1 # Copyright (c) 2006, The Regents of the University of California, through
|
|
|
2 # Lawrence Berkeley National Laboratory (subject to receipt of any required
|
|
|
3 # approvals from the U.S. Dept. of Energy). All rights reserved.
|
|
|
4
|
|
|
5 # This software is distributed under the new BSD Open Source License.
|
|
|
6 # <http://www.opensource.org/licenses/bsd-license.html>
|
|
|
7 #
|
|
|
8 # Redistribution and use in source and binary forms, with or without
|
|
|
9 # modification, are permitted provided that the following conditions are met:
|
|
|
10 #
|
|
|
11 # (1) Redistributions of source code must retain the above copyright notice,
|
|
|
12 # this list of conditions and the following disclaimer.
|
|
|
13 #
|
|
|
14 # (2) Redistributions in binary form must reproduce the above copyright
|
|
|
15 # notice, this list of conditions and the following disclaimer in the
|
|
|
16 # documentation and or other materials provided with the distribution.
|
|
|
17 #
|
|
|
18 # (3) Neither the name of the University of California, Lawrence Berkeley
|
|
|
19 # National Laboratory, U.S. Dept. of Energy nor the names of its contributors
|
|
|
20 # may be used to endorse or promote products derived from this software
|
|
|
21 # without specific prior written permission.
|
|
|
22 #
|
|
|
23 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
|
24 # AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
|
25 # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
|
26 # ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
|
|
27 # LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
|
28 # CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
|
29 # SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
|
30 # INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
|
|
31 # CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
|
|
32 # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
|
|
33 # POSSIBILITY OF SUCH DAMAGE.
|
|
|
34
|
|
|
35 """
|
|
|
36 Standard information used in computational biology.
|
|
|
37
|
|
|
38
|
|
|
39 To convert a property dictionary to a list :
|
|
|
40 >>> comp = [ amino_acid_composition[k] for k in amino_acid_letters]
|
|
|
41
|
|
|
42
|
|
|
43 Resources: (Various standard data files.)
|
|
|
44
|
|
|
45
|
|
|
46 BLOSUM Scoring Matrices
|
|
|
47 Source: ftp://ftp.ncbi.nih.gov/repository/blocks/unix/blosum
|
|
|
48 These are all new blast style with 1/3 bit scaling
|
|
|
49 - blosum35
|
|
|
50 - blosum45
|
|
|
51 - blosum62
|
|
|
52 - blosum40
|
|
|
53 - blosum50
|
|
|
54 - blosum80
|
|
|
55 - blosum100
|
|
|
56
|
|
|
57 Other subsitution scoring matrices:
|
|
|
58 - dist20_comp
|
|
|
59 - pam250
|
|
|
60 - pam120
|
|
|
61
|
|
|
62
|
|
|
63 Status: Beta (Data needs to be proof checked.)
|
|
|
64 """
|
|
|
65 # TODO: add this datafile?
|
|
|
66 # Description of database cross references :
|
|
|
67 # - dbxref.txt (http://www.expasy.org/cgi-bin/lists?dbxref.txt)
|
|
|
68
|
|
|
69
|
|
|
70 # FIXME: Move documentation of data to docstring above. docstrings
|
|
|
71 # after variables don't work.
|
|
|
72
|
|
|
73
|
|
|
74 # The ExPasy ProtScale tool is a great source of amino acid properties.
|
|
|
75 # http://au.expasy.org/cgi-bin/protscale.pl
|
|
|
76
|
|
|
77 from StringIO import StringIO
|
|
|
78 from corebio._future import resource_string, resource_stream,resource_filename
|
|
|
79 from corebio import utils
|
|
|
80
|
|
|
81 # Explictly list set of available data resources. We want to be able to access
|
|
|
82 # these resources in, for example, a webapp, without inadvertently allowing
|
|
|
83 # unrestricted read access to the local file system.
|
|
|
84
|
|
|
85 resource_names = [
|
|
|
86 'blosum35',
|
|
|
87 'blosum45',
|
|
|
88 'blosum62',
|
|
|
89 'blosum40',
|
|
|
90 'blosum50',
|
|
|
91 'blosum80',
|
|
|
92 'blosum100',
|
|
|
93 'dist20_comp',
|
|
|
94 'pam250',
|
|
|
95 'pam120',
|
|
|
96 ]
|
|
|
97
|
|
|
98 _resource_filenames = {
|
|
|
99 'blosum35': 'data/blosum35.mat',
|
|
|
100 'blosum45': 'data/blosum45.mat',
|
|
|
101 'blosum62': 'data/blosum62.mat',
|
|
|
102 'blosum40': 'data/blosum40.mat',
|
|
|
103 'blosum50': 'data/blosum50.mat',
|
|
|
104 'blosum80': 'data/blosum80.mat',
|
|
|
105 'blosum100': 'data/blosum100.mat',
|
|
|
106 'dist20_comp': 'data/dist20_comp.mat',
|
|
|
107 'pam250': 'data/pam250.mat',
|
|
|
108 'pam120': 'data/pam120.mat',
|
|
|
109 }
|
|
|
110
|
|
|
111 # TODO: Subsitution matrix parser, SeqMatrix.read
|
|
|
112 _resource_parsers = {}
|
|
|
113
|
|
|
114 def data_string( name ):
|
|
|
115 fn = _resource_filenames[name]
|
|
|
116 return resource_string(__name__, fn , __file__)
|
|
|
117
|
|
|
118 def data_stream( name ):
|
|
|
119 fn = _resource_filenames[name]
|
|
|
120 return resource_stream(__name__, fn , __file__)
|
|
|
121
|
|
|
122 def data_filename( name ):
|
|
|
123 fn = _resource_filenames[name]
|
|
|
124 return resource_filename(__name__, fn, __file__)
|
|
|
125
|
|
|
126 def data_object( name, parser = None) :
|
|
|
127 if parser is None :
|
|
|
128 if name in _resource_parsers :
|
|
|
129 parser = _resource_parsers[name]
|
|
|
130 else :
|
|
|
131 parser = str
|
|
|
132 return parser( data_stream(name) )
|
|
|
133
|
|
|
134
|
|
|
135 amino_acid_letters = "ACDEFGHIKLMNPQRSTVWY"
|
|
|
136 """Standard codes for the 20 canonical amino acids, in alphabetic order."""
|
|
|
137
|
|
|
138 amino_acid_alternative_letters = "ARNDCQEGHILKMFPSTWYV"
|
|
|
139 """Amino acid one letter codes, alphabetic by three letter codes."""
|
|
|
140
|
|
|
141 amino_acid_extended_letters = "ACDEFGHIKLMNOPQRSTUVWYBJZX*-"
|
|
|
142
|
|
|
143
|
|
|
144 dna_letters = "GATC"
|
|
|
145 dna_extended_letters = "GATCRYWSMKHBVDN"
|
|
|
146
|
|
|
147 rna_letters = "GAUC"
|
|
|
148 rna_extended_letters = "GAUCRYWSMKHBVDN"
|
|
|
149
|
|
|
150
|
|
|
151 dna_ambiguity = {
|
|
|
152 "A": "A",
|
|
|
153 "C": "C",
|
|
|
154 "G": "G",
|
|
|
155 "T": "T",
|
|
|
156 "M": "AC",
|
|
|
157 "R": "AG",
|
|
|
158 "W": "AT",
|
|
|
159 "S": "CG",
|
|
|
160 "Y": "CT",
|
|
|
161 "K": "GT",
|
|
|
162 "V": "ACG",
|
|
|
163 "H": "ACT",
|
|
|
164 "D": "AGT",
|
|
|
165 "B": "CGT",
|
|
|
166 "X": "GATC",
|
|
|
167 "N": "GATC",
|
|
|
168 }
|
|
|
169
|
|
|
170 rna_ambiguity = {
|
|
|
171 "A": "A",
|
|
|
172 "C": "C",
|
|
|
173 "G": "G",
|
|
|
174 "U": "U",
|
|
|
175 "M": "AC",
|
|
|
176 "R": "AG",
|
|
|
177 "W": "AU",
|
|
|
178 "S": "CG",
|
|
|
179 "Y": "CU",
|
|
|
180 "K": "GU",
|
|
|
181 "V": "ACG",
|
|
|
182 "H": "ACU",
|
|
|
183 "D": "AGU",
|
|
|
184 "B": "CGU",
|
|
|
185 "X": "GAUC",
|
|
|
186 "N": "GAUC",
|
|
|
187 }
|
|
|
188
|
|
|
189 amino_acid_ambiguity = {
|
|
|
190 "A": "A",
|
|
|
191 "B": "ND",
|
|
|
192 "C": "C",
|
|
|
193 "D": "D",
|
|
|
194 "E": "E",
|
|
|
195 "F": "F",
|
|
|
196 "G": "G",
|
|
|
197 "H": "H",
|
|
|
198 "I": "I",
|
|
|
199 "K": "K",
|
|
|
200 "L": "L",
|
|
|
201 "M": "M",
|
|
|
202 "N": "N",
|
|
|
203 "P": "P",
|
|
|
204 "Q": "Q",
|
|
|
205 "R": "R",
|
|
|
206 "S": "S",
|
|
|
207 "T": "T",
|
|
|
208 "V": "V",
|
|
|
209 "W": "W",
|
|
|
210 "X": "ACDEFGHIKLMNPQRSTVWY",
|
|
|
211 "Y": "Y",
|
|
|
212 "Z": "QE",
|
|
|
213 "J": "IL",
|
|
|
214 'U': 'U',
|
|
|
215 'O': 'O',
|
|
|
216 }
|
|
|
217
|
|
|
218
|
|
|
219 # Monomer isotopically averaged molecular mass
|
|
|
220 # Data Checked GEC Nov 2006
|
|
|
221 amino_acid_mass = {
|
|
|
222 "A": 89.09,
|
|
|
223 "B" : 132.66, # Averaged proportional to amino_acid_composition
|
|
|
224 "C": 121.16,
|
|
|
225 "D": 133.10,
|
|
|
226 "E": 147.13,
|
|
|
227 "F": 165.19,
|
|
|
228 "G": 75.07,
|
|
|
229 "H": 155.16,
|
|
|
230 "I": 131.18,
|
|
|
231 "J": 131.18,
|
|
|
232 "K": 146.19,
|
|
|
233 "L": 131.18,
|
|
|
234 "M": 149.21,
|
|
|
235 "N": 132.12,
|
|
|
236 # "O" : ???, # TODO
|
|
|
237 "P": 115.13,
|
|
|
238 "Q": 146.15,
|
|
|
239 "R": 174.20,
|
|
|
240 "S": 105.09,
|
|
|
241 "T": 119.12,
|
|
|
242 "U" : 168.05,
|
|
|
243 "V": 117.15,
|
|
|
244 "W": 204.23,
|
|
|
245 "X" : 129.15, # Averaged proportional to amino_acid_composition
|
|
|
246 "Y": 181.19,
|
|
|
247 "Z" : 146.76, # Averaged proportional to amino_acid_composition
|
|
|
248 }
|
|
|
249
|
|
|
250 dna_mass = {
|
|
|
251 "A": 347.,
|
|
|
252 "C": 323.,
|
|
|
253 "G": 363.,
|
|
|
254 "T": 322.,
|
|
|
255 }
|
|
|
256
|
|
|
257 rna_mass = {
|
|
|
258 "A": 363.,
|
|
|
259 "C": 319.,
|
|
|
260 "G": 379.,
|
|
|
261 "U": 340.,
|
|
|
262 }
|
|
|
263
|
|
|
264 one_to_three = {
|
|
|
265 'A':'Ala', 'B':'Asx', 'C':'Cys', 'D':'Asp',
|
|
|
266 'E':'Glu', 'F':'Phe', 'G':'Gly', 'H':'His',
|
|
|
267 'I':'Ile', 'K':'Lys', 'L':'Leu', 'M':'Met',
|
|
|
268 'N':'Asn', 'P':'Pro', 'Q':'Gln', 'R':'Arg',
|
|
|
269 'S':'Ser', 'T':'Thr', 'V':'Val', 'W':'Trp',
|
|
|
270 'Y':'Tyr', 'Z':'Glx', 'X':'Xaa',
|
|
|
271 'U':'Sec', 'J':'Xle', 'O':'Pyl'
|
|
|
272 }
|
|
|
273 """ Map between standard 1 letter amino acid codes and standard three letter codes.
|
|
|
274
|
|
|
275 Ref: http://www.ebi.ac.uk/RESID/faq.html
|
|
|
276 """
|
|
|
277
|
|
|
278 standard_three_to_one = utils.invert_dict(one_to_three)
|
|
|
279 """ Map between standard three letter amino acid codes and standard one letter codes.
|
|
|
280
|
|
|
281 Ref: http://www.ebi.ac.uk/RESID/faq.html
|
|
|
282 """
|
|
|
283
|
|
|
284
|
|
|
285 extended_three_to_one= {
|
|
|
286 '2as':'D', '3ah':'H', '5hp':'E', 'Acl':'R', 'Agm':'R', 'Aib':'A', 'Ala':'A', 'Alm':'A', 'Alo':'T', 'Aly':'K', 'Arg':'R', 'Arm':'R', 'Asa':'D', 'Asb':'D', 'Ask':'D', 'Asl':'D', 'Asn':'N', 'Asp':'D', 'Asq':'D', 'Asx':'B', 'Aya':'A', 'Bcs':'C', 'Bhd':'D', 'Bmt':'T', 'Bnn':'A', 'Buc':'C', 'Bug':'L', 'C5c':'C', 'C6c':'C', 'Ccs':'C', 'Cea':'C', 'Cgu':'E', 'Chg':'A', 'Cle':'L', 'Cme':'C', 'Csd':'A', 'Cso':'C', 'Csp':'C', 'Css':'C', 'Csw':'C', 'Csx':'C', 'Cxm':'M', 'Cy1':'C', 'Cy3':'C', 'Cyg':'C', 'Cym':'C', 'Cyq':'C', 'Cys':'C', 'Dah':'F', 'Dal':'A', 'Dar':'R', 'Das':'D', 'Dcy':'C', 'Dgl':'E', 'Dgn':'Q', 'Dha':'A', 'Dhi':'H', 'Dil':'I', 'Div':'V', 'Dle':'L', 'Dly':'K', 'Dnp':'A', 'Dpn':'F', 'Dpr':'P', 'Dsn':'S', 'Dsp':'D', 'Dth':'T', 'Dtr':'W', 'Dty':'Y', 'Dva':'V', 'Efc':'C', 'Fla':'A', 'Fme':'M', 'Ggl':'E', 'Gl3':'G', 'Gln':'Q', 'Glu':'E', 'Glx':'Z', 'Gly':'G', 'Glz':'G', 'Gma':'E', 'Gsc':'G', 'Hac':'A', 'Har':'R', 'Hic':'H', 'Hip':'H', 'His':'H', 'Hmr':'R', 'Hpq':'F', 'Htr':'W', 'Hyp':'P', 'Iil':'I', 'Ile':'I', 'Iyr':'Y', 'Kcx':'K', 'Leu':'L', 'Llp':'K', 'Lly':'K', 'Ltr':'W', 'Lym':'K', 'Lys':'K', 'Lyz':'K', 'Maa':'A', 'Men':'N', 'Met':'M', 'Mhs':'H', 'Mis':'S', 'Mle':'L', 'Mpq':'G', 'Msa':'G', 'Mse':'M', 'Mva':'V', 'Nem':'H', 'Nep':'H', 'Nle':'L', 'Nln':'L', 'Nlp':'L', 'Nmc':'G', 'Oas':'S', 'Ocs':'C', 'Omt':'M', 'Paq':'Y', 'Pca':'E', 'Pec':'C', 'Phe':'F', 'Phi':'F', 'Phl':'F', 'Pr3':'C', 'Pro':'P', 'Prr':'A', 'Ptr':'Y', 'Pyl':'O', 'Sac':'S', 'Sar':'G', 'Sch':'C', 'Scs':'C', 'Scy':'C', 'Sec':'U', 'Sel':'U', 'Sep':'S', 'Ser':'S', 'Set':'S', 'Shc':'C', 'Shr':'K', 'Smc':'C', 'Soc':'C', 'Sty':'Y', 'Sva':'S', 'Ter':'*', 'Thr':'T', 'Tih':'A', 'Tpl':'W', 'Tpo':'T', 'Tpq':'A', 'Trg':'K', 'Tro':'W', 'Trp':'W', 'Tyb':'Y', 'Tyq':'Y', 'Tyr':'Y', 'Tys':'Y', 'Tyy':'Y', 'Unk':'X', 'Val':'V', 'Xaa':'X', 'Xer':'X', 'Xle':'J'}
|
|
|
287
|
|
|
288 """ Map between three letter amino acid codes and standard one letter codes.
|
|
|
289 This map contains many nonstandard three letter codes, used, for example, to specify chemically modified amino acids in PDB files.
|
|
|
290
|
|
|
291 Ref: http://astral.berkeley.edu/
|
|
|
292 Ref: http://www.ebi.ac.uk/RESID/faq.html
|
|
|
293 """
|
|
|
294 # Initial table is from the ASTRAL RAF release notes.
|
|
|
295 # added UNK
|
|
|
296 # Extra IUPAC: Xle, Xaa, Sec, Pyl
|
|
|
297 # The following have been seen in biopython code.
|
|
|
298 # Ter : '*' Termination
|
|
|
299 # Sel : 'U' A typo for Sec, selenocysteine?
|
|
|
300 # Xer : 'X' Another alternative for unknown?
|
|
|
301
|
|
|
302
|
|
|
303 amino_acid_names = {
|
|
|
304 'A' : 'alanine',
|
|
|
305 'M' : 'methionine',
|
|
|
306 'C' : 'cysteine',
|
|
|
307 'N' : 'asparagine',
|
|
|
308 'D' : 'aspartic acid',
|
|
|
309 'P' : 'proline',
|
|
|
310 'E' : 'glutamic acid',
|
|
|
311 'Q' : 'glutamine',
|
|
|
312 'F' : 'phenylalanine',
|
|
|
313 'R' : 'arginine',
|
|
|
314 'G' : 'glycine',
|
|
|
315 'S' : 'serine',
|
|
|
316 'H' : 'histidine',
|
|
|
317 'T' : 'threonine',
|
|
|
318 'I' : 'isoleucine',
|
|
|
319 'V' : 'valine',
|
|
|
320 'K' : 'lysine',
|
|
|
321 'W' : 'tryptophan',
|
|
|
322 'L' : 'leucine',
|
|
|
323 'Y' : 'tyrosine',
|
|
|
324 'B' : 'aspartic acid or asparagine',
|
|
|
325 'J' : 'leucine or isoleucine',
|
|
|
326 'X' : 'unknown',
|
|
|
327 'Z' : 'glutamic acid or glutamine',
|
|
|
328 'U' : 'selenocysteine',
|
|
|
329 'O' : 'pyrrolysine',
|
|
|
330 '*' : 'translation stop',
|
|
|
331 '-' : 'gap'
|
|
|
332 }
|
|
|
333
|
|
|
334 amino_acid_composition = dict(
|
|
|
335 A = .082, R = .057, N = .044, D = .053, C = .017,
|
|
|
336 Q = .040, E = .062, G = .072, H = .022, I = .052,
|
|
|
337 L = .090, K = .057, M = .024, F =.039, P = .051,
|
|
|
338 S = .069, T = .058, W = .013, Y= .032, V =.066 )
|
|
|
339
|
|
|
340 """
|
|
|
341 Overall amino acid composition of proteins.
|
|
|
342 Ref: McCaldon P., Argos P. Proteins 4:99-122 (1988).
|
|
|
343 """
|
|
|
344 # FIXME : Proof these values
|
|
|
345
|
|
|
346 kyte_doolittle_hydrophobicity = dict(
|
|
|
347 A=1.8, R=-4.5, N=-3.5, D=-3.5, C=2.5,
|
|
|
348 Q=-3.5, E=-3.5, G=-0.4, H=-3.2, I=4.5,
|
|
|
349 L=3.8, K=-3.9, M=1.9, F=2.8, P=-1.6,
|
|
|
350 S=-0.8, T=-0.7, W=-0.9, Y=-1.3, V=4.2 )
|
|
|
351 """
|
|
|
352 Kyte-Doolittle hydrophobicity scale.
|
|
|
353 Ref: Kyte J., Doolittle R.F. J. Mol. Biol. 157:105-132 (1982)
|
|
|
354 """
|
|
|
355 # FIXME : Proof these values
|
|
|
356
|
|
|
357
|
|
|
358 nucleotide_names = {
|
|
|
359 'A' : 'Adenosine',
|
|
|
360 'C' : 'Cytidine',
|
|
|
361 'G' : 'Guanine',
|
|
|
362 'T' : 'Thymidine',
|
|
|
363 'U' : 'Uracil',
|
|
|
364 'R' : 'G A (puRine)',
|
|
|
365 'Y' : 'T C (pYrimidine)',
|
|
|
366 'K' : 'G T (Ketone)',
|
|
|
367 'M' : 'A C (aMino group)',
|
|
|
368 'S' : 'G C (Strong interaction)',
|
|
|
369 'W' : 'A T (Weak interaction)',
|
|
|
370 'B' : 'G T C (not A) (B comes after A)',
|
|
|
371 'D' : 'G A T (not C) (D comes after C)',
|
|
|
372 'H' : 'A C T (not G) (H comes after G)',
|
|
|
373 'V' : 'G C A (not T, not U) (V comes after U)',
|
|
|
374 'N' : 'A G C T (aNy)',
|
|
|
375 '-' : 'gap',
|
|
|
376 }
|
|
|
377
|
|
|
378
|
|
|
379
|
|
|
380
|
|
|
381
|
|
|
382
|
|
|
383
|
|
|
384
|
|
|
385 |
