git-svn-id: http://svn.tuebingen.mpg.de/ag-raetsch/projects/QPalma@8638 e1793c9e...
[qpalma.git] / scripts / PipelineHeuristic.py
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 import cPickle
5 import sys
6 import pdb
7 import os
8 import os.path
9 import math
10 import resource
11
12 from qpalma.DataProc import *
13 from qpalma.computeSpliceWeights import *
14 from qpalma.set_param_palma import *
15 from qpalma.computeSpliceAlignWithQuality import *
16 from qpalma.penalty_lookup_new import *
17 from qpalma.compute_donacc import *
18 from qpalma.TrainingParam import Param
19 from qpalma.Plif import Plf
20
21 from qpalma.tools.splicesites import getDonAccScores
22 from qpalma.Configuration import *
23
24 from compile_dataset import getSpliceScores, get_seq_and_scores
25
26 from numpy.matlib import mat,zeros,ones,inf
27 from numpy import inf,mean
28
29 from qpalma.parsers import PipelineReadParser
30
31
32 def unbracket_est(est):
33 new_est = ''
34 e = 0
35
36 while True:
37 if e >= len(est):
38 break
39
40 if est[e] == '[':
41 new_est += est[e+2]
42 e += 4
43 else:
44 new_est += est[e]
45 e += 1
46
47 return "".join(new_est).lower()
48
49
50 class PipelineHeuristic:
51 """
52 This class wraps the filter which decides whether an alignment found by
53 vmatch is spliced an should be then newly aligned using QPalma or not.
54 """
55
56 def __init__(self,run_fname,data_fname,param_fname):
57 """
58 We need a run object holding information about the nr. of support points
59 etc.
60 """
61
62 run = cPickle.load(open(run_fname))
63 self.run = run
64
65 start = cpu()
66
67 self.data_fname = data_fname
68
69 self.param = cPickle.load(open(param_fname))
70
71 # Set the parameters such as limits penalties for the Plifs
72 [h,d,a,mmatrix,qualityPlifs] = set_param_palma(self.param,True,run)
73
74 self.h = h
75 self.d = d
76 self.a = a
77 self.mmatrix = mmatrix
78 self.qualityPlifs = qualityPlifs
79
80 # when we look for alternative alignments with introns this value is the
81 # mean of intron size
82 self.intron_size = 90
83
84 self.read_size = 36
85
86 self.original_reads = {}
87
88 for line in open('/fml/ag-raetsch/share/projects/qpalma/solexa/allReads.pipeline'):
89 line = line.strip()
90 id,seq,q1,q2,q3 = line.split()
91 id = int(id)
92 self.original_reads[id] = seq
93
94 lengthSP = run['numLengthSuppPoints']
95 donSP = run['numDonSuppPoints']
96 accSP = run['numAccSuppPoints']
97 mmatrixSP = run['matchmatrixRows']*run['matchmatrixCols']
98 numq = run['numQualSuppPoints']
99 totalQualSP = run['totalQualSuppPoints']
100
101 currentPhi = zeros((run['numFeatures'],1))
102 currentPhi[0:lengthSP] = mat(h.penalties[:]).reshape(lengthSP,1)
103 currentPhi[lengthSP:lengthSP+donSP] = mat(d.penalties[:]).reshape(donSP,1)
104 currentPhi[lengthSP+donSP:lengthSP+donSP+accSP] = mat(a.penalties[:]).reshape(accSP,1)
105 currentPhi[lengthSP+donSP+accSP:lengthSP+donSP+accSP+mmatrixSP] = mmatrix[:]
106
107 totalQualityPenalties = self.param[-totalQualSP:]
108 currentPhi[lengthSP+donSP+accSP+mmatrixSP:] = totalQualityPenalties[:]
109 self.currentPhi = currentPhi
110
111 # we want to identify spliced reads
112 # so true pos are spliced reads that are predicted "spliced"
113 self.true_pos = 0
114
115 # as false positives we count all reads that are not spliced but predicted
116 # as "spliced"
117 self.false_pos = 0
118
119 self.true_neg = 0
120 self.false_neg = 0
121
122 # total time spend for get seq and scores
123 self.get_time = 0.0
124 self.calcAlignmentScoreTime = 0.0
125 self.alternativeScoresTime = 0.0
126
127 self.count_time = 0.0
128 self.read_parsing = 0.0
129 self.main_loop = 0.0
130 self.splice_site_time = 0.0
131 self.computeSpliceAlignWithQualityTime = 0.0
132 self.computeSpliceWeightsTime = 0.0
133 self.DotProdTime = 0.0
134 self.array_stuff = 0.0
135 stop = cpu()
136
137 self.init_time = stop-start
138
139 def filter(self):
140 """
141 This method...
142 """
143 run = self.run
144
145 start = cpu()
146
147 rrp = PipelineReadParser(self.data_fname)
148 all_remapped_reads = rrp.parse()
149
150 stop = cpu()
151
152 self.read_parsing = stop-start
153
154 ctr = 0
155 unspliced_ctr = 0
156 spliced_ctr = 0
157
158 print 'Starting filtering...'
159 _start = cpu()
160
161 for readId,currentReadLocations in all_remapped_reads.items():
162 for location in currentReadLocations[:1]:
163
164 id = location['id']
165 chr = location['chr']
166 pos = location['pos']
167 strand = location['strand']
168 mismatch = location['mismatches']
169 length = location['length']
170 off = location['offset']
171 seq = location['seq']
172 prb = location['prb']
173 cal_prb = location['cal_prb']
174 chastity = location['chastity']
175
176 id = int(id)
177
178 if strand == '-':
179 continue
180
181 if ctr == 100:
182 break
183
184 #if pos > 10000000:
185 # continue
186
187 unb_seq = unbracket_est(seq)
188 effective_len = len(unb_seq)
189
190 genomicSeq_start = pos
191 genomicSeq_stop = pos+effective_len-1
192
193 start = cpu()
194 #print genomicSeq_start,genomicSeq_stop
195 currentDNASeq, currentAcc, currentDon = get_seq_and_scores(chr,strand,genomicSeq_start,genomicSeq_stop,run['dna_flat_files'])
196 stop = cpu()
197 self.get_time += stop-start
198
199 dna = currentDNASeq
200 exons = zeros((2,1))
201 exons[0,0] = 0
202 exons[1,0] = effective_len
203 est = unb_seq
204 original_est = seq
205 quality = prb
206
207 #pdb.set_trace()
208
209 currentVMatchAlignment = dna, exons, est, original_est, quality,\
210 currentAcc, currentDon
211 vMatchScore = self.calcAlignmentScore(currentVMatchAlignment)
212
213 alternativeAlignmentScores = self.calcAlternativeAlignments(location)
214
215 start = cpu()
216 # found no alternatives
217 if alternativeAlignmentScores == []:
218 continue
219
220 maxAlternativeAlignmentScore = max(alternativeAlignmentScores)
221 #print 'vMatchScore/alternativeScore: %f %f ' % (vMatchScore,maxAlternativeAlignmentScore)
222 #print 'all candidates %s' % str(alternativeAlignmentScores)
223
224 new_id = id - 1000000300000
225
226 unspliced = False
227 # unspliced
228 if new_id > 0:
229 unspliced = True
230
231 # Seems that according to our learned parameters VMatch found a good
232 # alignment of the current read
233 if maxAlternativeAlignmentScore < vMatchScore:
234 unspliced_ctr += 1
235
236 if unspliced:
237 self.true_neg += 1
238 else:
239 self.false_neg += 1
240
241 # We found an alternative alignment considering splice sites that scores
242 # higher than the VMatch alignment
243 else:
244 spliced_ctr += 1
245
246 if unspliced:
247 self.false_pos += 1
248 else:
249 self.true_pos += 1
250
251 ctr += 1
252 stop = cpu()
253 self.count_time = stop-start
254
255 _stop = cpu()
256 self.main_loop = _stop-_start
257
258 print 'Unspliced/Splice: %d %d'%(unspliced_ctr,spliced_ctr)
259 print 'True pos / false pos : %d %d'%(self.true_pos,self.false_pos)
260 print 'True neg / false neg : %d %d'%(self.true_neg,self.false_neg)
261
262
263 def findHighestScoringSpliceSites(self,currentAcc,currentDon):
264
265 acc = []
266 for idx,score in enumerate(currentAcc):
267 if score > -inf:
268 acc.append((idx,score))
269 if idx>self.read_size:
270 break
271
272 acc.sort(lambda x,y: x[0]-y[0])
273 acc=acc[-2:]
274
275 don = []
276 for idx,score in enumerate(currentDon):
277 if score > -inf:
278 don.append((idx,score))
279 if idx>self.read_size:
280 break
281
282 don.sort(lambda x,y: x[0]-y[0])
283 don=don[-2:]
284
285 return don,acc
286
287
288 def calcAlternativeAlignments(self,location):
289 """
290 Given an alignment proposed by Vmatch this function calculates possible
291 alternative alignments taking into account for example matched
292 donor/acceptor positions.
293 """
294
295 run = self.run
296
297 id = location['id']
298 chr = location['chr']
299 pos = location['pos']
300 strand = location['strand']
301 original_est = location['seq']
302 quality = location['prb']
303 cal_prb = location['cal_prb']
304
305 est = unbracket_est(original_est)
306 effective_len = len(est)
307
308 genomicSeq_start = pos
309 genomicSeq_stop = pos+self.intron_size*2+self.read_size*2
310
311 start = cpu()
312 currentDNASeq, currentAcc, currentDon = get_seq_and_scores(chr,strand,genomicSeq_start,genomicSeq_stop,run['dna_flat_files'])
313 stop = cpu()
314 self.get_time += stop-start
315 dna = currentDNASeq
316
317 alt_don,alt_acc = self.findHighestScoringSpliceSites(currentAcc,currentDon)
318 print alt_don
319 print alt_acc
320
321 alternativeScores = []
322
323 # inlined
324 h = self.h
325 d = self.d
326 a = self.a
327 mmatrix = self.mmatrix
328 qualityPlifs = self.qualityPlifs
329 # inlined
330
331 # compute dummy scores
332 IntronScore = calculatePlif(h, [self.intron_size+1])[0]
333 dummyAcceptorScore = calculatePlif(a, [0.25])[0]
334 dummyDonorScore = calculatePlif(d, [0.25])[0]
335
336 _start = cpu()
337 for (don_pos,don_score) in alt_don:
338 # remove mismatching positions in the second exon
339 original_est_cut=''
340
341 est_ptr=0
342 dna_ptr=0
343 ptr=0
344 while ptr<len(original_est):
345
346 if original_est[ptr]=='[':
347 dnaletter=original_est[ptr+1]
348 estletter=original_est[ptr+2]
349 if dna_ptr < don_pos:
350 original_est_cut+=original_est[ptr:ptr+4]
351 else:
352 original_est_cut+=estletter # EST letter
353 ptr+=4
354 else:
355 dnaletter=original_est[ptr]
356 estletter=dnaletter
357
358 original_est_cut+=estletter # EST letter
359 ptr+=1
360
361 if estletter=='-':
362 dna_ptr+=1
363 elif dnaletter=='-':
364 est_ptr+=1
365 else:
366 dna_ptr+=1
367 est_ptr+=1
368
369 assert(dna_ptr<=len(dna))
370 assert(est_ptr<=len(est))
371
372 print "Donor"
373 DonorScore = calculatePlif(d, [don_score])[0]
374 print DonorScore,don_score,don_pos
375
376 score = computeSpliceAlignScoreWithQuality(original_est_cut, quality, qualityPlifs, run, self.currentPhi)
377 score += dummyAcceptorScore + IntronScore + DonorScore
378
379 #print 'diff %f,%f,%f' % ((trueWeight.T * self.currentPhi)[0,0] - score,(trueWeight.T * self.currentPhi)[0,0], score)
380 alternativeScores.append(score)
381
382 _stop = cpu()
383 self.alternativeScoresTime += _stop-_start
384
385 _start = cpu()
386 for (acc_pos,acc_score) in alt_acc:
387 # remove mismatching positions in the second exon
388 original_est_cut=''
389
390 est_ptr=0
391 dna_ptr=0
392 ptr=0
393 while ptr<len(original_est):
394
395 if original_est[ptr]=='[':
396 dnaletter=original_est[ptr+1]
397 estletter=original_est[ptr+2]
398 if est_ptr>=acc_pos:
399 original_est_cut+=original_est[ptr:ptr+4]
400 else:
401 original_est_cut+=estletter # EST letter
402 ptr+=4
403 else:
404 dnaletter=original_est[ptr]
405 estletter=dnaletter
406
407 original_est_cut+=estletter # EST letter
408 ptr+=1
409
410 if estletter=='-':
411 dna_ptr+=1
412 elif dnaletter=='-':
413 est_ptr+=1
414 else:
415 dna_ptr+=1
416 est_ptr+=1
417
418 assert(dna_ptr<=len(dna))
419 assert(est_ptr<=len(est))
420
421 #print original_est,original_est_cut
422
423 AcceptorScore = calculatePlif(d, [acc_score])[0]
424 print "Acceptor"
425 print AcceptorScore,acc_score,acc_pos
426
427 if acc_score<0.1:
428 print currentAcc[0:50]
429 print currentDon[0:50]
430
431 score = computeSpliceAlignScoreWithQuality(original_est_cut, quality, qualityPlifs, run, self.currentPhi)
432 score += AcceptorScore + IntronScore + dummyDonorScore
433
434 #print 'diff %f,%f,%f' % ((trueWeight.T * self.currentPhi)[0,0] - score,(trueWeight.T * self.currentPhi)[0,0], score)
435 alternativeScores.append(score)
436
437 _stop = cpu()
438 self.alternativeScoresTime += _stop-_start
439
440 return alternativeScores
441
442
443 def calcAlignmentScore(self,alignment):
444 """
445 Given an alignment (dna,exons,est) and the current parameter for QPalma
446 this function calculates the dot product of the feature representation of
447 the alignment and the parameter vector i.e the alignment score.
448 """
449
450 start = cpu()
451 run = self.run
452
453 # Lets start calculation
454 dna, exons, est, original_est, quality, acc_supp, don_supp = alignment
455
456 score = computeSpliceAlignScoreWithQuality(original_est, quality, self.qualityPlifs, run, self.currentPhi)
457
458 stop = cpu()
459 self.calcAlignmentScoreTime += stop-start
460
461 return score
462
463
464 def cpu():
465 return (resource.getrusage(resource.RUSAGE_SELF).ru_utime+\
466 resource.getrusage(resource.RUSAGE_SELF).ru_stime)
467
468
469 if __name__ == '__main__':
470 #run_fname = sys.argv[1]
471 #data_fname = sys.argv[2]
472 #param_filename = sys.argv[3]
473
474 dir = '/fml/ag-raetsch/home/fabio/tmp/QPalma_test/run_+_quality_+_splicesignals_+_intron_len'
475 jp = os.path.join
476
477 run_fname = jp(dir,'run_object.pickle')
478 #data_fname = '/fml/ag-raetsch/share/projects/qpalma/solexa/current_data/map.vm_unspliced_flag'
479
480 data_fname = '/fml/ag-raetsch/share/projects/qpalma/solexa/pipeline_data/map.vm_2k'
481 #data_fname = '/fml/ag-raetsch/share/projects/qpalma/solexa/pipeline_data/map.vm_100'
482
483 param_fname = jp(dir,'param_500.pickle')
484
485 ph1 = PipelineHeuristic(run_fname,data_fname,param_fname)
486
487 start = cpu()
488 ph1.filter()
489 stop = cpu()
490
491 print 'total time elapsed: %f' % (stop-start)
492 print 'time spend for get seq: %f' % ph1.get_time
493 print 'time spend for calcAlignmentScoreTime: %f' % ph1.calcAlignmentScoreTime
494 print 'time spend for alternativeScoresTime: %f' % ph1.alternativeScoresTime
495 print 'time spend for count time: %f' % ph1.count_time
496 print 'time spend for init time: %f' % ph1.init_time
497 print 'time spend for read_parsing time: %f' % ph1.read_parsing
498 print 'time spend for main_loop time: %f' % ph1.main_loop
499 print 'time spend for splice_site_time time: %f' % ph1.splice_site_time
500
501 print 'time spend for computeSpliceAlignWithQualityTime time: %f'% ph1.computeSpliceAlignWithQualityTime
502 print 'time spend for computeSpliceWeightsTime time: %f'% ph1.computeSpliceWeightsTime
503 print 'time spend for DotProdTime time: %f'% ph1.DotProdTime
504 print 'time spend forarray_stuff time: %f'% ph1.array_stuff
505 #import cProfile
506 #cProfile.run('ph1.filter()')
507
508 #import hotshot
509 #p = hotshot.Profile('profile.log')
510 #p.runcall(ph1.filter)