Class: Dataset

Inherits:
Object
  • Object
show all
Defined in:
lib/gene_assembler/dataset.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(type) ⇒ Dataset

Carga un objeto blast para generar los objetos contig que inician esta clase



5
6
7
8
9
10
 
# File 'lib/gene_assembler/dataset.rb', line 5

def initialize(type) #Carga un objeto blast para generar los objetos contig que inician esta clase
  @type=type #Definido pero no se usa
  @contigs=[]
  @clusters=[]
  @references_hash=''
end

Instance Attribute Details

#clusters ⇒ Object

Returns the value of attribute clusters.



4
5
6
 
# File 'lib/gene_assembler/dataset.rb', line 4

def clusters
  @clusters
end

#contigs ⇒ Object

Returns the value of attribute contigs.



4
5
6
 
# File 'lib/gene_assembler/dataset.rb', line 4

def contigs
  @contigs
end

#references_hash ⇒ Object

Returns the value of attribute references_hash.



4
5
6
 
# File 'lib/gene_assembler/dataset.rb', line 4

def references_hash
  @references_hash
end

#type ⇒ Object

Returns the value of attribute type.



4
5
6
 
# File 'lib/gene_assembler/dataset.rb', line 4

def type
  @type
end

Instance Method Details

#add_contig(name) ⇒ Object 



12
13
14
15
16
 
# File 'lib/gene_assembler/dataset.rb', line 12

def add_contig(name)
  c=Contig.new(name)
  @contigs << c
  return c
end

#align_contigs(contig_base) ⇒ Object 



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
 
# File 'lib/gene_assembler/dataset.rb', line 388

def align_contigs(contig_base)
limit=0
   las_contig=nil
if !contig_base.nil?
  limit=-1
  last_contig=contig_base
end
## Alineamiento de los contig entre si o contra una referencia
add=0
align=TRUE
each_contig_with_index do |contig,i|
  if i>limit 
    #Calcular desplazamiento de un contig respecto al anterior en el gff
    overlap_exon_with_last,ex=contig.compare(last_contig)
    if overlap_exon_with_last==-1
      if contig_base.nil?
         add+=last_contig.length
      else
        align=FALSE
      end
    else
       overlap_exon_current,ex=last_contig.compare(contig)
       add+=coord_prot(last_contig.hsp_at(overlap_exon_with_last),contig.hsp_at(overlap_exon_current))
       if !contig_base.nil?
         align=TRUE
       end
    end
  end 

  #Modificacion de contigs
  if align || contig_base.nil? # Modificar si no existe referencia o el contig a alineado contra la referencia
    contig.modified_coordenates(add)
    contig.length+=add
  end
  if !contig_base.nil?
    last_contig=contig_base
        add=0 #Resetear desplazamiento en caso de usarse una referencia
  else
    last_contig=contig
  end
end   
end

#attrib_recover(dataset) ⇒ Object

Reponer atributos en el Dataset del exonerate que se han perdido en el proceso (exonerate no los tiene), se recuperan del blast



103
104
105
106
107
108
109
110
111
112
113
114
115
116
 
# File 'lib/gene_assembler/dataset.rb', line 103

def attrib_recover(dataset) #Reponer atributos en el Dataset del exonerate que se han perdido en el proceso (exonerate no los tiene), se recuperan del blast
  each_contig{|self_contig|
  dataset.each_contig{|dataset_contig|
    if self_contig.name==dataset_contig.name
      self_contig.length=dataset_contig.length
      self_contig.seq=dataset_contig.seq
      self_contig.each_hit{|hit|
        hit.s_length=dataset_contig.first_hit.s_length
      }
      break  
    end
  }
}
end

#clear_clusters ⇒ Object 



344
345
346
 
# File 'lib/gene_assembler/dataset.rb', line 344

def clear_clusters
  @clusters=[]
end

#clr_contigs ⇒ Object

Vacia @contigs



76
77
78
 
# File 'lib/gene_assembler/dataset.rb', line 76

def clr_contigs # Vacia @contigs
  @contigs=[]
end

#cluster_count ⇒ Object 



98
99
100
101
 
# File 'lib/gene_assembler/dataset.rb', line 98

def cluster_count
  count=@clusters.length
  return count
end

#clustering ⇒ Object

Compara el subject_id entre todos los contig y agrupa en un array aquellos con mismo s_i. Cada array se guarda en el array ‘clusters’



124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
 
# File 'lib/gene_assembler/dataset.rb', line 124

def clustering # Compara el subject_id  entre todos los contig y agrupa en un array aquellos con mismo s_i. Cada array se guarda en el array 'clusters'
  finished_clusters=[]
  each_contig{|contig|
    clust=[]
    if finished_clusters.include?(contig.first_hit.name)
      next
    end
    each_contig{|contig2|
      if contig.first_hit.name==contig2.first_hit.name
        clust << contig2
        contig2=nil
      end
    }
    finished_clusters << contig.first_hit.name
    if !clust.empty?
      @clusters << clust
    end  
  }
end

#clusters_empty? ⇒ Boolean 



80
81
82
83
84
85
86
87
88
89
90
91
 
# File 'lib/gene_assembler/dataset.rb', line 80

def clusters_empty?
  empty=TRUE
  i=0
  each_cluster{|cl|
    i+=1
    if i>0
      empty=FALSE
      break
    end
  }
  return empty
end

#contig_count ⇒ Object 



93
94
95
96
 
# File 'lib/gene_assembler/dataset.rb', line 93

def contig_count
  count=@contigs.length
  return count
end

#correct_hsp_contigs(blast_coor_type) ⇒ Object 



118
119
120
121
122
 
# File 'lib/gene_assembler/dataset.rb', line 118

def correct_hsp_contigs(blast_coor_type)
  each_contig {|contig|
    contig.correct_hsps(blast_coor_type)  
  }
end

#correct_left_side_contigs(contig_base) ⇒ Object 



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
 
# File 'lib/gene_assembler/dataset.rb', line 357

def correct_left_side_contigs(contig_base)
  last_contig=nil
  limit=0
  correct=0
  ## Alineamiento de los contig entre si para calcular desplazamiento
  if !contig_base.nil?
    limit=-1
    last_contig=contig_base
  end
  each_contig_with_index do |contig,i| # Calculo del desplazamiento necesario para corregir indices negativos en el gff
     if i>limit 
       overlap_exon_with_last,ex=contig.compare(last_contig)
       if overlap_exon_with_last>-1
        overlap_exon_current,ex=last_contig.compare(contig)
           diference=coord_prot(last_contig.hsp_at(overlap_exon_with_last),contig.hsp_at(overlap_exon_current))        
           if diference<correct
           correct=diference
           end
       end
    end 
    
    if !contig_base.nil?
      last_contig=contig_base
    else
      last_contig=contig
    end 
  end
  correct*=-1
  return correct
end

#delete_cluster(cluster) ⇒ Object 



38
39
40
 
# File 'lib/gene_assembler/dataset.rb', line 38

def delete_cluster(cluster)
  @clusters.delete(cluster) 
end

#delete_cluster_at(ind) ⇒ Object 



42
43
44
 
# File 'lib/gene_assembler/dataset.rb', line 42

def delete_cluster_at(ind)
  @clusters.delete_at(ind) 
end

#each_cluster ⇒ Object 



59
60
61
62
63
 
# File 'lib/gene_assembler/dataset.rb', line 59

def each_cluster
  @clusters.each do |cluster|
    yield cluster
  end
end

#each_cluster_with_index ⇒ Object 



65
66
67
68
69
 
# File 'lib/gene_assembler/dataset.rb', line 65

def each_cluster_with_index
  @clusters.each_with_index do |cluster,i|
    yield cluster,i
  end
end

#each_contig ⇒ Object

iterador



47
48
49
50
51
 
# File 'lib/gene_assembler/dataset.rb', line 47

def each_contig
  @contigs.each do |contig|
    yield contig
  end
end

#each_contig_with_index ⇒ Object 



53
54
55
56
57
 
# File 'lib/gene_assembler/dataset.rb', line 53

def each_contig_with_index
  @contigs.each_with_index do |contig,i|
    yield contig,i
  end
end

#fasta(fasta_file) ⇒ Object

Crea un archivo fasta a partir de @contigs



208
209
210
211
212
213
214
215
 
# File 'lib/gene_assembler/dataset.rb', line 208

def fasta(fasta_file) #Crea un archivo fasta a partir de @contigs
  temp=File.open(fasta_file, 'w')
    each_contig{|contig|
    temp.print ">#{contig.name}\n"
    temp.puts contig.seq
  }
  temp.close
end

#filtering ⇒ Object

Bateria de filtros



164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
 
# File 'lib/gene_assembler/dataset.rb', line 164

def filtering #Bateria de filtros
  putative_contigs=[]
  uni_hsp=[]
each_contig{ |contig|
  if contig.mixed?
    next
  elsif contig.is_one_hsp? #Apartamos contigs uni-hsp
    uni_hsp << contig
    next
  elsif contig.is_gapped?
    next
  elsif contig.is_truncated?
    next
  elsif contig.hsp_minor_than?(15) #En nt
    next
  else putative_contigs << contig
    if $verbose
      puts "#{contig.first_hit.name}\t#{contig.name}"
    end
  end
}
@contigs=putative_contigs
return uni_hsp
end

#filtering_clust ⇒ Object

Bateria de filtros q se aplica sobre @clusters. tb muestra informacion



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
 
# File 'lib/gene_assembler/dataset.rb', line 217

def filtering_clust # Bateria de filtros q se aplica sobre @clusters. tb muestra informacion
  gene_clusters=[]
  uni_hsp=[]
each_cluster{|clust|
  if $verbose
    puts "\n********************CLUSTER*************************\n"
  end
  putative_ex=[]
  trash_ex=[]
  clust.each do |contig|
    temp=[]
    if contig.mixed?
      temp << "#{contig.first_hit.name}\t#{contig.name}"
      trash_ex << temp
    elsif contig.is_truncated?
      temp << "#{contig.first_hit.name}\t#{contig.name}"
      trash_ex << temp
    elsif contig.is_one_hsp?
      temp << "#{contig.first_hit.name}\t#{contig.name}"
      trash_ex << temp
      uni_hsp << contig#Se guardan los contig uni-hsp, para procesado posterior
    elsif contig.is_gapped?
      temp << "#{contig.first_hit.name}\t#{contig.name}"
      trash_ex << temp
    else putative_ex << contig
    end
  end
  if $verbose
    putative_ex.each do |contig|
    puts "#{contig.first_hit.name}\t#{contig.name}\t\t\tsc:#{contig.first_hit.first_hsp.score}" #el score de cada hsp es el mismo, por lo que realmente pertenece al alineamiento entero
    end
    puts ',,,,,,,,,,,,,REJECTED,,,,,,,,,,,,,'
    trash_ex.each do |contig|
      puts contig
    end
    puts "\n= = = = = = = = = =MAP= = = = = = = = = = = =\n"
    putative_ex.each do |contig|
      contig.draw
    end
  end
  gene_clusters << putative_ex 
}
@clusters=gene_clusters
return uni_hsp
end

#generate_file_5_prime(file, fasta) ⇒ Object 



510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
 
# File 'lib/gene_assembler/dataset.rb', line 510

def generate_file_5_prime(file, fasta)
  prime5_file = File.open(file, 'w')
  fasta_file = File.open(fasta, 'w')
  each_cluster{ |cluster|
    if !cluster.nil? && !cluster.empty?
      gene_name = cluster.first.first_hit.name
      cluster.each do |contig|
        if contig.first_hit.first_hsp.s_beg <= 10
          prime5_end = contig.first_hit.first_hsp.q_beg
          prime5_file.puts "#{gene_name}\t#{contig.name}\t#{prime5_end}"
          seq = contig.seq[0..prime5_end]
          if !seq.nil?
            fasta_file.puts "#{gene_name}\n#{seq}"
          end
        end
      end
    end
  }
  prime5_file.close
  fasta_file.close
end

#info_clusters ⇒ Object

Muestra informacion sobre @Clusters, muestra contig, la proteina a la q pertenece y un diagrama del alineamiento en aa



144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
# File 'lib/gene_assembler/dataset.rb', line 144

def info_clusters # Muestra informacion sobre @Clusters, muestra contig, la proteina a la q pertenece y un diagrama del alineamiento en aa
  if $verbose
  each_cluster{|cl|
      puts '............................'
      cl.each do |c|
        puts "#{c.first_hit.name}\t#{c.name}"
      end
      puts "............................"
  }

  each_cluster{|clust|
    puts "\n********************MAP*************************\n"
    clust.each do |contig|
      contig.draw
    end
  }
puts "\n"
end
end

#load_references(references_file) ⇒ Object

Carga en @references_hash todas las referencias en forma de objetos contig



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
 
# File 'lib/gene_assembler/dataset.rb', line 274

def load_references(references_file) # Carga en @references_hash todas las referencias en forma de objetos contig
  hash={}
  if File.exists?(references_file)
  File.open(references_file, 'r').each do |line|
    fields=line.split
    contig_name=fields[0]
    if !fields[1].nil?
      structures=fields[1].split('|')
      all_models=[]
      structures.each do |structure|
        contig=Contig.new(contig_name)
        contig.add_hit(contig_name, 0, 1,:nt)
        if structure.nil?
          break
        end
        hsps=structure.split(';')
        s_end=0
        nt_add=0
        hsps.each do |hsp|
          coords=hsp.split('-')
          q_beg=coords[0].to_i
          q_end=coords[1].to_i
          s_beg=s_end+1
          exon_length=q_end-q_beg+nt_add
          s_end=s_end+(exon_length/3)
          nt_add=exon_length.modulo(3)
          contig.first_hit.add_hsp(q_beg, q_end, s_beg, s_end, 0, 0, 0, 0)
        end
        contig.length=contig.first_hit.last_hsp.q_end
        all_models << contig
      end
      hash[contig_name]=all_models
     end
  end
 end
  @references_hash=hash
end

#load_seq(hash) ⇒ Object

Carga secuencias en @contigs



189
190
191
192
193
194
 
# File 'lib/gene_assembler/dataset.rb', line 189

def load_seq(hash) #Carga secuencias en @contigs
  each_contig{|contig|
      contig.seq=hash[contig.name]
      contig.seq.upcase!
  }
end

#missing_cluster_transfer(dataset) ⇒ Object

Busca que clusters estan vacios e intenta llenarlos con clusters de dataset



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
 
# File 'lib/gene_assembler/dataset.rb', line 312

def missing_cluster_transfer(dataset) #Busca que clusters estan vacios e intenta llenarlos con clusters de dataset
  add=[]
  delete=[]
  if clusters_empty?
    dataset.each_cluster{ |clust|
      transfer_cluster(clust)
    }
    dataset.clear_clusters
  else   
  dataset.each_cluster_with_index{|uni_cluster,ind|
    is_cluster=FALSE
    each_cluster{|cluster| #Se mira si existe cluster uni-hsp en cluster 
      if uni_cluster.first.first_hit.name==cluster.first.first_hit.name
        is_cluster=TRUE
        break
      end
    }
    if !is_cluster #Caso de q no exista cluster, se transfiere cluster uni-hsp
      add << uni_cluster
      delete << ind
    end  
  }
  add.each do |clust|
    transfer_cluster(clust.dup)
  end
delete.sort!
  delete.reverse_each do |ind|
    dataset.delete_cluster_at(ind)
  end
  end
end

#missing_contigs_transfer(dataset) ⇒ Object

dataset is uni_hsp. Se buscan contigs q no alineen con los de self



474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
 
# File 'lib/gene_assembler/dataset.rb', line 474

def missing_contigs_transfer(dataset) #dataset is uni_hsp. Se buscan contigs q no alineen con los de self
  contigs_cluster=[]
  self.each_cluster_with_index{|self_cluster,s|
    dataset.each_cluster{|dataset_cluster|
  if dataset_cluster.nil? ||dataset_cluster.empty?
    next
  end
      if self_cluster.first.first_hit.name==dataset_cluster.first.first_hit.name #Mismo cluster
        dataset_cluster.each do |dataset_contig|
          align=FALSE
          self_cluster.each do |self_contig|
            position,n_exones=dataset_contig.compare(self_contig)
            if position>-1
              align=TRUE
              break
            end
          end
          if !align
            contigs_cluster << dataset_contig
          end
        end
        
        contigs_cluster.each do |contig|
          self.transfer_contig_to_cluster(contig,s)
    dataset_cluster.delete(contig)
        end
        contigs_cluster=[]
      end  
    }
  }
end

#multiple_align_contigs(array_contig_base, mod_contig_base = FALSE) ⇒ Object 



431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
 
# File 'lib/gene_assembler/dataset.rb', line 431

def multiple_align_contigs(array_contig_base,mod_contig_base=FALSE)
  correct=0
  array_contig_base.each do |contig_base|
local_correct=correct_left_side_contigs(contig_base)
if local_correct>correct
  correct=local_correct
end
self.align_contigs(contig_base,mod_contig_base)
  end
  # Correcion del modelo en base al desplazamiento general calculado para cada fragmento teniendo en cuenta el desplazamiento local realizado
  array_contig_base.each do |contig|
if correct>0
  contig.modified_coordenates(correct)
  contig.length+=correct
end
  end
  self.each_contig {|contig|
if correct>0
  contig.modified_coordenates(correct)
  contig.length+=correct
end
  }
  
  return correct
end

#n_contigs? ⇒ Boolean 



71
72
73
74
 
# File 'lib/gene_assembler/dataset.rb', line 71

def n_contigs?
  n=@contigs.length
  return n
end

#parse_stops ⇒ Object 



202
203
204
205
206
 
# File 'lib/gene_assembler/dataset.rb', line 202

def parse_stops
  each_contig{|contig|
    contig.stop_codon_search
  }
end

#rev_comp ⇒ Object

Realiza la secuencia reverso complementaria en @contigs y @uni_hsp



196
197
198
199
200
 
# File 'lib/gene_assembler/dataset.rb', line 196

def rev_comp #Realiza la secuencia reverso complementaria en @contigs y @uni_hsp
  each_contig{|contig|
    contig.rev_comp_if_hit
  }
end

#score_correction(factor) ⇒ Object

Suma al atributo score la operacion nº intrones*factor



348
349
350
351
352
353
354
355
 
# File 'lib/gene_assembler/dataset.rb', line 348

def score_correction(factor) #Suma al atributo score la operacion nº intrones*factor
  each_contig{|contig|
    n_intron=contig.n_intron
    contig.first_hit.each_hsp{|hsp|
      hsp.score+=factor*n_intron
    }
  }
end

#sort_cluster(cluster) ⇒ Object

Ordena los elementos de cluster(contigs) en base a su posicion en el subject



270
271
272
 
# File 'lib/gene_assembler/dataset.rb', line 270

def sort_cluster(cluster)#Ordena los elementos de cluster(contigs) en base a su posicion en el subject
  cluster.sort!{|e1,e2| e1.first_hit.first_hsp.s_beg<=>e2.first_hit.first_hsp.s_beg}
end

#sort_cont_clust ⇒ Object

Ordenar contigs dentro de @clusters de menor a mayor en base a su primer hsp



263
264
265
266
267
268
 
# File 'lib/gene_assembler/dataset.rb', line 263

def sort_cont_clust #Ordenar contigs dentro de @clusters de menor a mayor en base a su primer hsp
  each_cluster{|cluster| 
  cluster=sort_cluster(cluster)
}
  #@clusters=sort_clusters(@clusters)
end

#transfer_cluster(cluster) ⇒ Object 



34
35
36
 
# File 'lib/gene_assembler/dataset.rb', line 34

def transfer_cluster(cluster)
  @clusters << cluster
end

#transfer_contig_to_cluster(contig, n_cluster) ⇒ Object 



506
507
508
 
# File 'lib/gene_assembler/dataset.rb', line 506

def transfer_contig_to_cluster(contig,n_cluster)
  @clusters[n_cluster] << contig
end

#transfer_contigs(add_contigs, limit = 0) ⇒ Object 



18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
 
# File 'lib/gene_assembler/dataset.rb', line 18

def transfer_contigs(add_contigs,limit=0)
  if limit==0
  @contigs << add_contigs
  @contigs.flatten!
else
 if add_contigs.class.to_s=='Array'
  add_contigs.each_with_index do |contig,i|
    if i==limit
      break
    end
    @contigs << contig
  end
 end
end         
end

#transfer_n_contigs_def_hit_type(dataset, cluster, new_hit_type, limit) ⇒ Object 



457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
 
# File 'lib/gene_assembler/dataset.rb', line 457

def transfer_n_contigs_def_hit_type(dataset,cluster,new_hit_type,limit)
  if !cluster.empty?||!cluster.nil?
    dataset.each_cluster{|dat_cluster| 
      if dat_cluster.empty?||dat_cluster.nil?
        next
      end          
      if dat_cluster.first.first_hit.name==cluster.first.first_hit.name # Se busca en los clusters unihsp aquel q pertenece al gen q se esta trabajando
        dat_cluster.each do |contig|
          contig.first_hit.type='pseudogene'
        end
        transfer_contigs(dat_cluster,limit)
      end  

    }
  end    
end