Snippets

Dénes Türei Looking up phosphopeptide fragments in UniProt sequences

Created by Dénes Türei last modified
  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
#!/usr/bin/env python

# Denes Turei 2019
# turei.denes@gmail.com


import importlib as imp
import os
import re
import csv
import collections

import pypath.homology
import pypath.session_mod
import pypath.ptm
import pypath.mapping
import pypath.progress


FragmentMatch = collections.namedtuple(
    'FragmentMatch',
    [
        'isoform',
        'uniprot_offset',
        'fragment',
        'databases',
        'enzymes',
    ],
)
FragmentMatch.__new__.__defaults__ = (None,) * 2


class SeqLookup(pypath.session_mod.Logger):
    """
    Looks up phosphopeptide sequence fragments in UniProt sequences.
    Determines the offset of the phosphosites.
    """
    
    
    reptm = re.compile(
        r'(\d+)x'
        r'(\w+) '
        r'\[([-;\w/]+)\]'
    )
    reptmsite = re.compile(
        r'([A-Z/]+)'
        r'(?:([0-9]+))?'
    )
    mod_types = {
        'Phospho': 'phosphorylation',
        'Oxidation': 'oxidation',
        'Carbamidomethyl': 'carbamidomethylation',
    }
    
    
    def __init__(
            self,
            seq_fragments_file = None,
            ncbi_tax_id = 10090,
            output_path = None,
            **kwargs
        ):
        
        self.seq_fragments_file = seq_fragments_file
        self.ncbi_tax_id = ncbi_tax_id
        self.output_path = output_path
        
        self._set_ptmdb_pickle()
        
        pypath.session_mod.Logger.__init__(self, name = 'seq-lookup')
    
    
    def reload(self):

        modname = self.__class__.__module__
        mod = __import__(modname, fromlist = [modname.split('.')[0]])
        imp.reload(mod)
        new = getattr(mod, self.__class__.__name__)
        setattr(self, '__class__', new)
    
    
    def main(self):
        
        self.load()
        self.read()
        self.lookup()
        self.results_table()
        self.export()
        
        self._log('Finished.')
    
    
    def load(self):
        
        self.load_sequences()
        self.load_ptms()
    
    
    def load_sequences(self):
        
        self._log('Loading sequences for the entire proteome from UniProt.')
        
        self.seq = pypath.homology.SequenceContainer()
        self.seq.load_seq(taxon = self.ncbi_tax_id)
    
    
    def load_ptms(self):
        
        self._log('Loading known PTM sites.')
        
        ptm_args = {
            'ncbi_tax_id': self.ncbi_tax_id,
            'pickle_file': (
                self.ptmdb_pickle
                    if os.path.exists(self.ptmdb_pickle) else
                None
            ),
        }
        
        self.ptmdb = pypath.ptm.PtmAggregator(**ptm_args)
        
        self.save_ptmdb()
    
    
    def save_ptmdb(self, overwrite = False):
        
        if not os.path.exists(self.ptmdb_pickle) or overwrite:
            
            self.ptmdb.save_to_pickle(pickle_file = self.ptmdb_pickle)
    
    
    def _set_ptmdb_pickle(self):
        
        self.ptmdb_pickle = os.path.join(
            'data',
            'ptmdb__%s.pickle' % self.ncbi_tax_id,
        )
    
    
    def read(self):
        
        self._log(
            'Reading sequence fragments from `%s`.' % self.seq_fragments_file
        )
        
        with open(self.seq_fragments_file, 'r') as fp:
            
            self.seq_frag_raw = list(csv.DictReader(fp))
        
        self.preprocess_fragments()
    
    
    def preprocess_fragments(self):
        
        PtmRecord = collections.namedtuple(
            'PtmRecord',
            [
                'idx',
                'uniprot',
                'typ',
                'residue',
                'offset',
                'times',
                'data',
            ],
        )
        
        self.fragments = []
        
        prg = pypath.progress.Progress(
            len(self.seq_frag_raw),
            'Preprocessing sequence fragments',
            1,
        )
        
        for i, rec in enumerate(self.seq_frag_raw):
            
            prg.step()
            
            all_features = self.reptm.findall(rec['mod'])
            
            for times, typ, mod in all_features:
                
                for mod in mod.split(';'):
                    
                    residues, offset = self.reptmsite.match(mod).groups()
                    
                    for residue in residues.split('/'):
                        
                        for uniprot in pypath.mapping.map_name(
                            rec['ProtAcc'],
                            'uniprot',
                            'uniprot',
                            ncbi_tax_id = self.ncbi_tax_id,
                        ):
                            
                            typ = (
                                self.mod_types[typ]
                                    if typ in self.mod_types else
                                typ
                            )
                            
                            self.fragments.append(
                                PtmRecord(
                                    idx = i,
                                    uniprot = uniprot,
                                    typ = typ,
                                    residue = residue,
                                    offset = int(offset) if offset else None,
                                    times = times,
                                    data = rec,
                                )
                            )
        
        prg.terminate()
    
    
    def lookup(self):
        
        self._log('Looking up sequence fragments.')
        
        self.lookup_result = []
        
        prg = pypath.progress.Progress(
            len(self.fragments),
            'Looking up sequence fragments',
            1,
        )
        
        for frag in self.fragments:
            
            prg.step()
            
            self.lookup_result.extend(self.lookup_frag(frag))
        
        prg.terminate()
    
    
    def lookup_frag(self, frag):
        
        lookup_result = []
        
        seq = self.seq.get_seq(frag.uniprot, taxon = self.ncbi_tax_id)
        
        if not seq:
            
            self._log(
                'Could not find sequence '
                'in UniProt: `%s`.' % frag.uniprot
            )
            return [FragmentMatch(None, None, frag)]
        
        seq_found = False
        residue_found = False
        
        for iso, offset in seq.findall(frag.data['peptide_seq']):
            
            seq_found = True
            
            if frag.offset is not None:
                
                uniprot_offsets = (offset + frag.offset,)
                
            else:
                
                uniprot_offsets = [
                    offset + res_offset
                    for res_offset in self.substr_find_all(
                        frag.data['peptide_seq'],
                        frag.residue,
                    )
                ]
            
            for uniprot_offset in uniprot_offsets:
                
                residue_found = True
                
                this_ptm = pypath.intera.Ptm(
                    protein = frag.uniprot,
                    isoform = iso,
                    typ = frag.typ,
                    residue = pypath.intera.Residue(
                        identifier = frag.uniprot,
                        name = frag.residue,
                        number = uniprot_offset,
                    )
                )
                
                databases, enzymes = (
                    (
                        ';'.join(sorted(self.ptmdb.ptms[this_ptm].sources)),
                        ';'.join(sorted(self.ptmdb.ptm_to_enzyme[this_ptm])),
                    )
                        if this_ptm in self.ptmdb.ptms else
                    (None, None)
                )
                
                lookup_result.append(
                    FragmentMatch(
                        isoform = iso,
                        uniprot_offset = uniprot_offset,
                        fragment = frag,
                        databases = databases,
                        enzymes = enzymes,
                    )
                )
        
        if not seq_found:
            
            self._log(
                'Could not find sequence `%s` '
                'in any isoform of UniProt `%s`.' % (
                    frag.data['peptide_seq'],
                    frag.uniprot,
                )
            )
            lookup_result = [FragmentMatch(None, None, frag)]
        
        elif not residue_found and frag.residue != 'N':
            
            self._log(
                'Could not find residue `%s` in '
                'sequence fragment `%s` (UniProt: %s).' % (
                    frag.residue,
                    frag.data['peptide_seq'],
                    frag.uniprot,
                )
            )
            lookup_result = [FragmentMatch(None, None, frag)]
        
        return lookup_result
    
    
    @staticmethod
    def substr_find_all(string, sub):
        
        offset = 0
        
        while True:
            
            offset = string.find(sub, offset)
            
            if offset == -1:
                
                break
            
            yield offset
            
            offset += 1
    
    
    def results_table(self):
        
        ResultRecord = collections.namedtuple(
            'ResultRecord',
            [
                'uniprot',
                'isoform',
                'residue',
                'offset',
                'modification',
                'times',
                'original_id',
                'original_uniprot',
                'peptide_seq',
                'peptide_seq_offset',
                'modifications_raw',
                'gene',
                'p_value',
                'q_value',
                'diff',
                'stat',
                'databases',
                'enzymes',
            ]
        )
        
        self.result = []
        
        for rec in self.lookup_result:
            
            self.result.append(
                ResultRecord(
                    uniprot = rec.fragment.uniprot,
                    isoform = rec.isoform,
                    residue = rec.fragment.residue,
                    offset = rec.uniprot_offset,
                    modification = rec.fragment.typ,
                    times = rec.fragment.times,
                    original_id = rec.fragment.idx,
                    original_uniprot = rec.fragment.data['ProtAcc'],
                    peptide_seq = rec.fragment.data['peptide_seq'],
                    peptide_seq_offset = rec.fragment.offset,
                    modifications_raw = rec.fragment.data['mod'],
                    gene = rec.fragment.data['gene'],
                    p_value = rec.fragment.data['p-value'],
                    q_value = rec.fragment.data['q-value'],
                    diff = rec.fragment.data['diff'],
                    stat = rec.fragment.data['stat'],
                    databases = rec.databases,
                    enzymes = rec.enzymes,
                )
            )
    
    
    def export(self):
        
        self.output_path = (
            self.output_path or
            '%s.uniprot.csv' % self.seq_fragments_file
        )
        
        self._log('Exporting results to `%s`.' % self.output_path)
        
        with open(self.output_path, 'w') as fp:
            
            writer = csv.writer(
                fp,
                delimiter = ',',
                quotechar = '"',
                quoting = csv.QUOTE_MINIMAL,
            )
            
            writer.writerow(self.result[0]._fields)
            
            for row in self.result:
                
                writer.writerow(row)


if __name__ == '__main__':
    
    input_files = [
        ('data', 'Ursula_D140vsWT_original.csv'),
        ('data', 'Ursula_E98VvsWT_original.csv'),
    ]
    ncbi_tax_id = 10090
    
    for input_file in input_files:
        
        seq_fragments_file = os.path.join(*input_file)
        
        sl = SeqLookup(
            seq_fragments_file = seq_fragments_file,
            ncbi_tax_id = ncbi_tax_id,
        )
        
        sl.main()
    
    sl._log('Script exiting.')

Comments (1)

  1. Linda Melson
HTTPS SSH

You can clone a snippet to your computer for local editing. Learn more.