git-svn-id: http://svn.tuebingen.mpg.de/ag-raetsch/projects/QPalma@8652 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 = 250
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 == 1000:
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, DNA, max_intron_size, read_size, splice_thresh):
264
265 def signum(a):
266 if a>0:
267 return 1
268 elif a<0:
269 return -1
270 else:
271 return 0
272
273 proximal_acc = []
274 for idx in xrange(max_intron_size, max_intron_size+read_size):
275 if currentAcc[idx]>= splice_thresh:
276 proximal_acc.append((idx,currentAcc[idx]))
277
278 proximal_acc.sort(lambda x,y: signum(x[1]-y[1]))
279 proximal_acc=proximal_acc[-2:]
280
281 distal_acc = []
282 for idx in xrange(max_intron_size+read_size, len(currentAcc)):
283 if currentAcc[idx]>= splice_thresh:
284 distal_acc.append((idx, currentAcc[idx], DNA[idx:idx+read_size]))
285
286 #distal_acc.sort(lambda x,y: signum(x[1]-y[1]))
287 #distal_acc=distal_acc[-2:]
288
289
290 proximal_don = []
291 for idx in xrange(max_intron_size, max_intron_size+read_size):
292 if currentDon[idx] >= splice_thresh:
293 proximal_don.append((idx, currentDon[idx]))
294
295 proximal_don.sort(lambda x,y: signum(x[1]-y[1]))
296 proximal_don=proximal_don[-2:]
297
298 distal_don = []
299 for idx in xrange(max_intron_size, max_intron_size+read_size):
300 if currentDon[idx] >= splice_thresh:
301 distal_don.append((idx, currentDon[idx], DNA[idx-read_size:idx]))
302
303 #distal_don.sort(lambda x,y: signum(x[1]-y[1]))
304 #distal_don=distal_don[-2:]
305
306 return proximal_acc,proximal_don,distal_acc,distal_don
307
308 def calcAlternativeAlignments(self,location):
309 """
310 Given an alignment proposed by Vmatch this function calculates possible
311 alternative alignments taking into account for example matched
312 donor/acceptor positions.
313 """
314
315 run = self.run
316 splice_thresh = 0.01
317 max_intron_size = 2000
318
319 id = location['id']
320 chr = location['chr']
321 pos = location['pos']
322 strand = location['strand']
323 original_est = location['seq']
324 quality = location['prb']
325 cal_prb = location['cal_prb']
326
327 est = unbracket_est(original_est)
328 effective_len = len(est)
329
330 genomicSeq_start = pos - max_intron_size
331 genomicSeq_stop = pos + max_intron_size + len(est)
332
333 start = cpu()
334 currentDNASeq, currentAcc, currentDon = get_seq_and_scores(chr,strand,genomicSeq_start,genomicSeq_stop,run['dna_flat_files'])
335 stop = cpu()
336 self.get_time += stop-start
337 dna = currentDNASeq
338
339 proximal_don,proximal_acc,distal_don,distal_acc = self.findHighestScoringSpliceSites(currentAcc,currentDon, max_intron_size)
340
341 #sort_acc=[ elem for elem in enumerate(currentAcc) ]
342 #sort_acc.sort(lambda x,y: signum(x[1]-y[1]) )
343
344 #print alt_don
345 #print alt_acc
346
347 alternativeScores = []
348
349 # inlined
350 h = self.h
351 d = self.d
352 a = self.a
353 mmatrix = self.mmatrix
354 qualityPlifs = self.qualityPlifs
355 # inlined
356
357 # compute dummy scores
358 #IntronScore = calculatePlif(h, [math.fabs(max_acc_pos-30)])[0]
359 #dummyAcceptorScore = calculatePlif(a, [max_acc_score])[0]
360 IntronScore = calculatePlif(h, [self.intron_size])[0] - 0.5
361 dummyAcceptorScore = calculatePlif(a, [0.25])[0]
362 dummyDonorScore = calculatePlif(d, [0.25])[0]
363
364 _start = cpu()
365 for (don_pos,don_score) in alt_don:
366 # remove mismatching positions in the second exon
367 original_est_cut=''
368
369 est_ptr=0
370 dna_ptr=0
371 ptr=0
372 while ptr<len(original_est):
373
374 if original_est[ptr]=='[':
375 dnaletter=original_est[ptr+1]
376 estletter=original_est[ptr+2]
377 if dna_ptr < don_pos:
378 original_est_cut+=original_est[ptr:ptr+4]
379 else:
380 #original_est_cut+=estletter # EST letter
381 original_est_cut+=dnaletter # DNA letter
382 ptr+=4
383 else:
384 dnaletter=original_est[ptr]
385 estletter=dnaletter
386
387 original_est_cut+=estletter # EST letter
388 ptr+=1
389
390 if estletter=='-':
391 dna_ptr+=1
392 elif dnaletter=='-':
393 est_ptr+=1
394 else:
395 dna_ptr+=1
396 est_ptr+=1
397
398 assert(dna_ptr<=len(dna))
399 assert(est_ptr<=len(est))
400
401 #print "Donor"
402 DonorScore = calculatePlif(d, [don_score])[0]
403 #print DonorScore,don_score,don_pos
404
405 score = computeSpliceAlignScoreWithQuality(original_est_cut, quality, qualityPlifs, run, self.currentPhi)
406 score += dummyAcceptorScore + IntronScore + DonorScore
407
408 #print 'diff %f,%f,%f' % ((trueWeight.T * self.currentPhi)[0,0] - score,(trueWeight.T * self.currentPhi)[0,0], score)
409 alternativeScores.append(score)
410
411 _stop = cpu()
412 self.alternativeScoresTime += _stop-_start
413
414 _start = cpu()
415 for (acc_pos,acc_score) in alt_acc:
416 # remove mismatching positions in the second exon
417 original_est_cut=''
418
419 est_ptr=0
420 dna_ptr=0
421 ptr=0
422 while ptr<len(original_est):
423
424 if original_est[ptr]=='[':
425 dnaletter=original_est[ptr+1]
426 estletter=original_est[ptr+2]
427 if est_ptr>=acc_pos:
428 original_est_cut+=original_est[ptr:ptr+4]
429 else:
430 original_est_cut+=estletter # EST letter
431 ptr+=4
432 else:
433 dnaletter=original_est[ptr]
434 estletter=dnaletter
435
436 original_est_cut+=estletter # EST letter
437 ptr+=1
438
439 if estletter=='-':
440 dna_ptr+=1
441 elif dnaletter=='-':
442 est_ptr+=1
443 else:
444 dna_ptr+=1
445 est_ptr+=1
446
447 assert(dna_ptr<=len(dna))
448 assert(est_ptr<=len(est))
449
450 #print original_est,original_est_cut
451
452 AcceptorScore = calculatePlif(d, [acc_score])[0]
453 #print "Acceptor"
454 #print AcceptorScore,acc_score,acc_pos
455
456 #if acc_score<0.1:
457 # print currentAcc[0:50]
458 # print currentDon[0:50]
459
460 score = computeSpliceAlignScoreWithQuality(original_est_cut, quality, qualityPlifs, run, self.currentPhi)
461 score += AcceptorScore + IntronScore + dummyDonorScore
462
463 #print 'diff %f,%f,%f' % ((trueWeight.T * self.currentPhi)[0,0] - score,(trueWeight.T * self.currentPhi)[0,0], score)
464 alternativeScores.append(score)
465
466 _stop = cpu()
467 self.alternativeScoresTime += _stop-_start
468
469 return alternativeScores
470
471
472 def calcAlignmentScore(self,alignment):
473 """
474 Given an alignment (dna,exons,est) and the current parameter for QPalma
475 this function calculates the dot product of the feature representation of
476 the alignment and the parameter vector i.e the alignment score.
477 """
478
479 start = cpu()
480 run = self.run
481
482 # Lets start calculation
483 dna, exons, est, original_est, quality, acc_supp, don_supp = alignment
484
485 score = computeSpliceAlignScoreWithQuality(original_est, quality, self.qualityPlifs, run, self.currentPhi)
486
487 stop = cpu()
488 self.calcAlignmentScoreTime += stop-start
489
490 return score
491
492
493 def cpu():
494 return (resource.getrusage(resource.RUSAGE_SELF).ru_utime+\
495 resource.getrusage(resource.RUSAGE_SELF).ru_stime)
496
497
498 if __name__ == '__main__':
499 #run_fname = sys.argv[1]
500 #data_fname = sys.argv[2]
501 #param_filename = sys.argv[3]
502
503 dir = '/fml/ag-raetsch/home/fabio/tmp/QPalma_test/run_+_quality_+_splicesignals_+_intron_len'
504 jp = os.path.join
505
506 run_fname = jp(dir,'run_object.pickle')
507 #data_fname = '/fml/ag-raetsch/share/projects/qpalma/solexa/current_data/map.vm_unspliced_1k'
508
509 data_fname = '/fml/ag-raetsch/share/projects/qpalma/solexa/pipeline_data/map.vm_2k'
510 #data_fname = '/fml/ag-raetsch/share/projects/qpalma/solexa/pipeline_data/map.vm_100'
511
512 param_fname = jp(dir,'param_500.pickle')
513
514 ph1 = PipelineHeuristic(run_fname,data_fname,param_fname)
515
516 start = cpu()
517 ph1.filter()
518 stop = cpu()
519
520 print 'total time elapsed: %f' % (stop-start)
521 print 'time spend for get seq: %f' % ph1.get_time
522 print 'time spend for calcAlignmentScoreTime: %f' % ph1.calcAlignmentScoreTime
523 print 'time spend for alternativeScoresTime: %f' % ph1.alternativeScoresTime
524 print 'time spend for count time: %f' % ph1.count_time
525 print 'time spend for init time: %f' % ph1.init_time
526 print 'time spend for read_parsing time: %f' % ph1.read_parsing
527 print 'time spend for main_loop time: %f' % ph1.main_loop
528 print 'time spend for splice_site_time time: %f' % ph1.splice_site_time
529
530 print 'time spend for computeSpliceAlignWithQualityTime time: %f'% ph1.computeSpliceAlignWithQualityTime
531 print 'time spend for computeSpliceWeightsTime time: %f'% ph1.computeSpliceWeightsTime
532 print 'time spend for DotProdTime time: %f'% ph1.DotProdTime
533 print 'time spend forarray_stuff time: %f'% ph1.array_stuff
534 #import cProfile
535 #cProfile.run('ph1.filter()')
536
537 #import hotshot
538 #p = hotshot.Profile('profile.log')
539 #p.runcall(ph1.filter)