Newer
Older
Copyright 2023 INRAE, Université de Tours
requests at: sebastien.leclercq@inrae.fr
This file is part of GenoFig.
GenoFig is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License
as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
Genofig is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty
of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
A copy of the GNU General Public License is available in the COPYING file. If not, see <https://www.gnu.org/licenses/>
This script may use some code adapted from Easyfig v2.1.1 written by Mitchell Sullivan and licensed under GNU GPLv3 (http://mjsull.github.io/Easyfig/files.html - Legacy versions)
'''
# Gtk modules
from gi.repository import Gtk,GObject
# BioPython modules
from Bio import SeqIO
from Bio.SeqFeature import FeatureLocation
import re
import copy
import tempfile
# Parse the Input File (Fasta or Genbank) to extract and store information
#--------------------------------------------------------------------------
def parseSeqFile(filename,outtype):
ftype=filename[filename.rfind('.')+1:]
parsed=None
# Detect the format from the file extension
if re.match(r'fa|fna',ftype):
parsed = SeqIO.parse(filename, "fasta")
if re.match(r'gb|genbank',ftype):
parsed = SeqIO.parse(filename, "genbank")
# Try to detect the format without an obvious file extension
Sebastien leclercq
committed
if parsed == None:
filein = open(filename)
line=filein.read(10)
if line.startswith('>'):
parsed = SeqIO.parse(filename, "fasta")
if line.startswith('LOCUS'):
parsed = SeqIO.parse(filename, "genbank")
Sebastien leclercq
committed
filein.close()
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
# return a list of seqentries, with a postreatment on their accession.
if outtype == "L":
filelist= []
for seqentry in parsed:
filelist.append([getSeqname(seqentry),seqentry])
return filelist
# return a dictionary of seqEntries, matching to their accesssion in the input (have to be unique)
if outtype == "D":
filelist= {}
for seqentry in parsed:
filelist[getSeqname(seqentry)] = seqentry
return filelist
# Get the sequence ACCESSION ID
#--------------------------------------------------------------------------
def getSeqname(record):
componame = record.name.split("|")
# Depends if its a fasta or a genbank
if len(componame) > 3:
shortname= componame[3].split(".")[0]
elif len(componame) > 2:
shortname= componame[1].split(".")[0] + componame[2]
else:
shortname=componame[0]
return shortname
################################################################################################
#
# This is a custom class to insert colored buttons (with icons only) into the sequence and feature table
#
#######################################################text#########################################
class CellRendererButton( Gtk.CellRendererPixbuf ):
__gproperties__ = { "callable": ( GObject.TYPE_PYOBJECT,
"callable property",
"callable property",
GObject.PARAM_READWRITE ) }
_button_width = 2
_button_height = 1
def __init__( self ):
# self.__GObject_init__()
Gtk.CellRendererPixbuf.__init__( self )
self.set_property( "xalign", 0.5 )
self.set_property( "mode", Gtk.CellRendererMode.ACTIVATABLE )
self.set_property('cell-background-set' , True)
self.activatable = True
self.callable = None
self.table = None
def do_get_property( self, pspec ):
if pspec.name == "callable":
return self.callable
else:
raise AttributeError( "Unknown property %s" % pspec.name )
def do_set_property( self, pspec, value ):
if pspec.name == "callable":
if callable( value ):
self.callable = value
else:
raise TypeError( "callable property must be callable!" )
else:
raise AttributeError( "Unknown property %s" % pspec.name )
def do_get_size( self, wid, cell_area ):
xpad = self.get_property( "xpad" )
ypad = self.get_property( "ypad" )
if not cell_area:
x, y = 0, 0
w = 2 * xpad + self._button_width
h = 2 * ypad + self._button_height
else:
w = 2 * xpad + cell_area.width
h = 2 * ypad + cell_area.height
xalign = self.get_property( "xalign" )
yalign = self.get_property( "yalign" )
x = max( 0, xalign * ( cell_area.width - w ) )
y = max( 0, yalign * ( cell_area.height - h ) )
return ( x, y, w, h )
def do_render( self, window, wid, bg_area, cell_area, flags ):
if not window:
return
flags = flags & Gtk.CellRendererState.SELECTED
Gtk.CellRendererPixbuf.do_render( self, window, wid, bg_area,
cell_area, flags )
def do_activate( self, event, wid, path, bg_area, cell_area, flags ):
cb = self.get_property( "callable" )
if cb != None :
cb (path)
return True
def set_color(self,colRGBA):
self.set_property("cell-background-rgba",colRGBA)
# _CellRendererButton
################################################################################################
#
# This is a custom ListStore class which exclude the first line from the drag and drop
#
################################################################################################
class ListStoreDnd(Gtk.ListStore):
def __init__(*args):
Gtk.ListStore.__init__(*args)
# To forbid movements of the [two] first rows
def do_row_draggable(self,path):
if str(path) == '0' :
return False
else:
return True
# Avoid drag and drop before the [two] first row
def do_row_drop_possible(self, dest, selection_data):
if ':' in str(dest) or str(dest) == '0':
return False
else:
return True
def saveinfasta(self):
Ffile = tempfile.NamedTemporaryFile(mode='w',delete=False)
viewedNames={} # to avoid multiple copies of the same sequence being blasted
for s in self.return_seqEntries():
if not s.bname in viewedNames.keys():
Ffile.write(">" + s.bname + "\n" + str(s.record.seq) + "\n")
viewedNames[s.bname]=1
return Ffile.name
# Transform the ListStore as a list of SeqEntries, more convenient to be handled in the Drawing script
def return_seqEntries(self):
seqs = []
# Skip the first row which is the general sequence information
S = self.get_iter_first()
S = self.iter_next(S)
while S != None:
entry = SeqEntry(self.get_value(S,3),self.get_value(S,5).bname,self.get_value(S,5).record)
entry.gp['file'] = self.get_value(S,5).file # get the original file path for save/reload purpose
entry.gp['sel'] = int(self.get_value(S,6))
entry.gp['height'] = self.get_value(S,7)
entry.gp['lwidth'] = self.get_value(S,8)
entry.gp['inspace'] = self.get_value(S,9)
entry.gp['lcol'] = self.get_value(S,12)
entry.gp['spos'] = self.get_value(S,13)
entry.gp['sxpos'] = self.get_value(S,11)
entry.gp['min'] = self.get_value(S,14)
entry.gp['max'] = self.get_value(S,15)
entry.gp['rev'] = self.get_value(S,16)
entry.gp['slabsel'] = self.get_value(S,17)
entry.gp['slabid'] = self.get_value(S,18)
entry.gp['slabpos'] = self.get_value(S,19)
entry.gp['slaboffset'] = self.get_value(S,30)
entry.gp['slabcol'] = self.get_value(S,21)
entry.gp['slabsize'] = self.get_value(S,22)
entry.gp['slabbold'] = self.get_value(S,32)
entry.gp['slabital'] = self.get_value(S,33)
entry.gp['flabsel'] = self.get_value(S,23)
entry.gp['flabval'] = self.get_value(S,24)
entry.gp['flabpos'] = self.get_value(S,25)
entry.gp['flabcol'] = self.get_value(S,27)
entry.gp['flabsize'] = self.get_value(S,28)
entry.gp['flabrot'] = self.get_value(S,29)
entry.gp['ID'] = self.get_value(S,31)
seqs.append(entry)
S = self.iter_next(S)
return seqs
# Transform the ListStore as a list Feature dictionaries, more convenient to be handled in the Drawing script
def return_featDictionary(self):
feats = []
F = self.get_iter_first()
F = self.iter_next(F)
while F != None:
entry = {}
entry['id'] = self.get_value(F,3)
entry['sel'] = int(self.get_value(F,4))
entry['flegsel'] = int(self.get_value(F,26))
entry['feat'] = self.get_value(F,5)
entry['strand'] = self.get_value(F,6)
entry['shape'] = self.get_value(F,7)
entry['hatching'] = self.get_value(F,8)
entry['height'] = self.get_value(F,9)
entry['col'] = self.get_value(F,11)
entry['fill'] = int(self.get_value(F,12))
entry['stroke'] = self.get_value(F,13)
entry['strokecol'] = self.get_value(F,15)
entry['filter'] = self.get_value(F,16)
entry['field'] = self.get_value(F,17)
entry['flabsel'] = self.get_value(F,19)
entry['flabval'] = self.get_value(F,20)
entry['flabpos'] = self.get_value(F,21)
entry['flabbold'] = self.get_value(F,27)
entry['flabital'] = self.get_value(F,28)
entry['flabcol'] = self.get_value(F,23)
entry['flabsize'] = self.get_value(F,24)
entry['flabrot'] = self.get_value(F,25)
feats.append(entry)
F = self.iter_next(F)
return feats
# Transform the ListStore as a list Decoration dictionaries, more convenient to be handled in the Drawing script
def return_decoDictionary(self):
decoration = []
D = self.get_iter_first()
D = self.iter_next(D)
while D != None:
entry = {}
entry['id'] = self.get_value(D,4)
entry['select'] = int(self.get_value(D,5))
entry['type'] = self.get_value(D,6)
entry['step'] = int(self.get_value(D,7))
entry['window'] = int(self.get_value(D,8))
entry['pos'] = self.get_value(D,9)
entry['heightR'] = self.get_value(D,10)
entry['linewidth'] = self.get_value(D,11)
entry['linecolor'] = self.get_value(D,13)
entry['reverse'] = self.get_value(D,14)
entry['labelprint'] = self.get_value(D,15)
entry['labelcolor'] = self.get_value(D,17)
entry['labelsize'] = self.get_value(D,18)
entry['labelpos'] = self.get_value(D,19)
Sebastien leclercq
committed
entry['labelgbkpos'] = self.get_value(D,21)
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
decoration.append(entry)
D = self.iter_next(D)
return decoration
################################################################################################
#
# Transfer Class to copy the information from the Dndlistbox sequence type
# for use in the Drawing command
#
################################################################################################
class SeqEntry:
#--------------------------------------------------------------------------
def __init__(self,seqname,bname,rec):
self.record = copy.deepcopy(rec)
self.bname = bname
self.gp = {}
self.gp['name'] = seqname
# Drawing parameters
self.xpos = 0
self.ypos = 0
self.length = len(self.record.seq)
self.lengthO = self.length
# Set the record name if necessary
if self.record.name == '<unknown name>': self.record.name = seqname
################################################################################################
#
# Small class to store the BioSeq record into the ListStore
#
################################################################################################
class BioSeqobj(GObject.GObject):
def __init__(self,rec,afile):
GObject.GObject.__init__(self)
self.file = afile
self.record = rec
# create a unique name including Accession + reverse compl. and region information when necessary
self.bname = self.record.name
if 'accessions' in self.record.annotations.keys() and 'REGION:' in self.record.annotations['accessions']:
R = self.record.annotations['accessions'][2].replace("complement(","c").replace(")","")
self.bname += "_"+R
def length(self):
return self.record.__len__()
def getfile(self):
return self.file
# to get general infos for dialog box
def getinfo(self):
infos = ""
infos = infos + "name:\t"+self.record.name+"\n"
if 'accessions' in self.record.annotations.keys():
infos = infos + "accession:\t"+self.record.annotations['accessions'][0]+"\n"
if 'REGION:' in self.record.annotations['accessions']:
infos = infos + "position in accession:\t"+self.record.annotations['accessions'][2]+"\n"
if 'source' in self.record.annotations.keys():
infos = infos + "source:\t"+self.record.annotations['source']+"\n"
if 'organism' in self.record.annotations.keys():
infos = infos + "organism:\t"+self.record.annotations['organism']+"\n"
Sebastien leclercq
committed
if len(self.record.features) > 0 and ("strain" in self.record.features[0].qualifiers.keys()):
infos = infos + "strain:\t"+self.record.features[0].qualifiers["strain"][0]+"\n"
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
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
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
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
infos = infos + "description:\t"+self.record.description+"\n"
infos = infos + "size:\t"+str(self.length())+" bp\n"
infos = infos + "filename:\t"+self.file
return infos
def getFeattypes(self):
featslist = {}
for feat in self.record.features:
if feat.type != "source":
featslist[feat.type] = 0
return featslist.keys()
################################################################################################
#
# This is a custom Dialog class to ask for a custom x position for sequences
#
################################################################################################
class DialogXpos(Gtk.Dialog):
def __init__(self,parent,seqname,xval):
Gtk.Dialog.__init__(self,"custom position",parent)
self.set_default_size(170, 50)
labelX = Gtk.Label("x position for "+seqname+":")
self.entryX = Gtk.Entry()
self.entryX.set_text(xval)
self.entryX.connect("activate", self.on_entry_edited)
contentbox = self.get_content_area()
contentbox.add(labelX)
contentbox.add(self.entryX)
self.show_all()
def on_entry_edited(self,widget):
self.response(Gtk.ResponseType.OK)
################################################################################################
#
# This is a custom Entry class to set up directly the size and the default value
#
################################################################################################
class EntrySmall(Gtk.Entry):
def __init__(self,size,value, minval, maxval):
Gtk.Entry.__init__(self)
self.min = minval
self.max = maxval
self.savedval = value
self.set_width_chars(size)
self.set_max_width_chars(size)
self.set_text(value)
# to check the value integrity after modification
self.connect("focus-out-event",self.checkvalue)
# Automatically check whether the value is integer and in the range of min-max value
def checkvalue(self,entry,val2):
text = entry.get_text()
try: int(text)
except: entry.set_text(self.savedval)
else:
if int(text) < self.min: entry.set_text(str(self.min))
elif int(text) > self.max: entry.set_text(str(self.max))
else:
entry.set_text(text)
self.savedval = text
################################################################################################
#
# A child of EntrySmall class to deal with float values
#
################################################################################################
class EntrySmallFloat(EntrySmall):
def __init__(self,size,value, minval, maxval):
EntrySmall.__init__(self,size,value, minval, maxval)
# Automatically check whether the value is float and in the range of min-max value
def checkvalue(self,entry,val2):
text = entry.get_text()
try: float(text)
except: entry.set_text(self.savedval)
else:
if float(text) < self.min: entry.set_text(str(self.min))
elif float(text) > self.max: entry.set_text(str(self.max))
else:
entry.set_text(text)
self.savedval = text
################################################################################################
#
# A child of EntrySmall class to deal with "-" values
#
################################################################################################
class EntrySmallSameAs(EntrySmall):
def __init__(self,size,value, minval, maxval):
EntrySmall.__init__(self,size,value, minval, maxval)
# Automatically check whether the value is float and in the range of min-max value
def checkvalue(self,entry,val2):
text = entry.get_text()
if text=='' or text==' ' or text=='-':
entry.set_text("-")
self.savedval = "-"
return 1
try: float(text)
except: entry.set_text(self.savedval)
else:
if float(text) < self.min: entry.set_text(str(self.min))
elif float(text) > self.max: entry.set_text(str(self.max))
else:
entry.set_text(text)
self.savedval = text
################################################################################################
#
# This is a custom CellCombo class to set up directly the model and other properties
#
################################################################################################
class CellRendererComboNoEntry(Gtk.CellRendererCombo):
def __init__(self,liststore):
Gtk.CellRendererCombo.__init__(self)
self.set_property("editable", True)
self.set_property("has-entry", False)
self.set_property("text-column",0)
self.set_property("model",liststore)
################################################################################################
#
# This is a custom Dialog class to create the custom blast selection
#
################################################################################################
class DialogCustomBlast(Gtk.Dialog):
#------------------------------------------------------
def __init__(self, parent, blasttype, listseqs, listchecked):
Gtk.Dialog.__init__(self, title="Custom matches selection for "+blasttype, parent=parent, modal=True)
self.add_buttons(Gtk.STOCK_CLOSE, Gtk.ResponseType.CLOSE)
self.nbseqs = len(listseqs)
self.set_default_size(150, 150)
self.set_modal(False)
# Avoid the destruction of the window
self.connect('delete-event', lambda w, e: w.hide() or True)
self.connect('response', lambda w, e: w.hide() or True)
# Box including a grid displaying the cross-sequence selection
self.boxBlastSel = Gtk.Box(Gtk.Orientation.VERTICAL,3)
self.boxBlastSel.set_property("margin-bottom",20)
self.gridBlastSel = Gtk.Grid()
# create labels for the selection
for i in range(0,self.nbseqs):
labnby = Gtk.Label(str(i+1)+". ")
labely = Gtk.Button(listseqs[i])
labely.connect("clicked",self.on_click_Name,i)
labnby.set_xalign(1)
labely.set_property("margin-end",4)
# print the number and sequence name in lines
self.gridBlastSel.attach(labnby,0,i,1,1)
self.gridBlastSel.attach(labely,1,i,1,1)
# print the number in columns, but skip the last sequence
if i < self.nbseqs-1:
self.gridBlastSel.attach(Gtk.Label(str(i+1)+"."),i+2,self.nbseqs,1,1)
# create the checkboxes
for i in range(0,self.nbseqs):
seq1 = self.gridBlastSel.get_child_at(1,i)
for j in range(0,i):
checkb = Gtk.CheckButton()
# test if it was checked previously
if listchecked != None:
seq2 = self.gridBlastSel.get_child_at(1,j)
for cc in listchecked:
if seq1.get_label() in cc and seq2.get_label() in cc: # here is the real check test
checkb.set_active(True)
listchecked.remove(cc)
# insert the checkbox in that grid
self.gridBlastSel.attach(checkb,j+2,i,1,1)
# create buttons
self.labbb = Gtk.Label("Select:", name="label-blast")
self.labbb.set_xalign(0)
self.butAdj = Gtk.Button("Adjacent")
self.butAdj.connect("clicked",self.on_click_Adj)
self.butNoAdj = Gtk.Button("No Adj.")
self.butNoAdj.connect("clicked",self.on_click_NoAdj)
self.butAll = Gtk.Button("All")
self.butAll.connect("clicked",self.on_click_All)
self.butClear = Gtk.Button("Clear")
self.butClear.connect("clicked",self.on_click_Clear)
self.boxBlastSel.pack_start(self.labbb,False,True,0)
self.boxBlastSel.pack_start(self.butAdj,False,True,0)
self.boxBlastSel.pack_start(self.butNoAdj,False,True,0)
self.boxBlastSel.pack_start(self.butAll,False,True,0)
self.boxBlastSel.pack_start(self.butClear,False,True,0)
scrolledwindow = Gtk.ScrolledWindow()
scrolledwindow.set_policy(Gtk.PolicyType.AUTOMATIC,Gtk.PolicyType.AUTOMATIC)
scrolledwindow.set_min_content_height(600)
scrolledwindow.add(self.gridBlastSel)
box = self.get_content_area()
box.add(self.boxBlastSel)
box.add(scrolledwindow)
box.set_property("margin",10)
box.show_all()
# return the list of checked combinations
#------------------------------------------------------
def get_checked(self):
print("look at checked")
listchecked = []
# pass all the checkboxes
for i in range(0,self.nbseqs):
for j in range(0,i):
check = self.gridBlastSel.get_child_at(j+2,i)
# store when active
if check.get_active():
seq1 = self.gridBlastSel.get_child_at(1,j)
seq2 = self.gridBlastSel.get_child_at(1,i)
listchecked.append([seq1.get_label(),seq2.get_label()])
return listchecked
# return the matrix of checked combinations
#------------------------------------------------------
def get_checkedMatrix(self):
mxchecked = []
# pass all the checkboxes
for i in range(0,self.nbseqs):
mxchecked.append([])
for j in range(0,i):
check = self.gridBlastSel.get_child_at(j+2,i)
# store 1 when active, 0 otherwise
if check.get_active():
mxchecked[i].append(1)
else:
mxchecked[i].append(0)
return mxchecked
# various selection actions
#------------------------------------------------------
def on_click_Adj(self,button):
for i in range(2,self.nbseqs+1):
check = self.gridBlastSel.get_child_at(i,i-1)
check.set_active(True)
def on_click_NoAdj(self,button):
for i in range(2,self.nbseqs+1):
check = self.gridBlastSel.get_child_at(i,i-1)
check.set_active(False)
def on_click_All(self,button):
for i in range(2,self.nbseqs+1):
for j in range(2,i+1):
check = self.gridBlastSel.get_child_at(j,i-1)
check.set_active(True)
def on_click_Clear(self,button):
for i in range(2,self.nbseqs+1):
for j in range(2,i+1):
check = self.gridBlastSel.get_child_at(j,i-1)
check.set_active(False)
def on_click_Name(self,button,pos):
for i in range(2,pos+2):
check = self.gridBlastSel.get_child_at(i,pos)
check.set_active(True)
for i in range(pos+1,self.nbseqs):
check = self.gridBlastSel.get_child_at(pos+2,i)
check.set_active(True)
################################################################################################
#
# This is a custom Filechooser dialog class for sequence selection
# -> to avoid core dumped errors linked to python library bugs not fixed
#
################################################################################################
class SeqFileChooserDialog(Gtk.FileChooserDialog):
#------------------------------------------------------
def __init__(self, parent, title,action):
Gtk.FileChooserDialog.__init__(self,title="Please choose a sequence file", parent=parent, action=Gtk.FileChooserAction.OPEN)
# Avoid the destruction of the window to avoid Segmentation fault
self.connect('delete-event', lambda k, e: k.hide() or True)
self.connect('response', lambda k, e: k.hide() or True)
################################################################################################
#
# This is a custom Dialog class to create the custom decoration selection
#
################################################################################################
class DialogCustomDecoration(Gtk.Dialog):
#------------------------------------------------------
def __init__(self, parent, seqslist):
Gtk.Dialog.__init__(self, title="Custom sequences display for Decoration", parent=parent, modal=True)
#self.add_buttons(Gtk.STOCK_CLOSE, Gtk.ResponseType.CLOSE)
self.seqIDlist = [a[0] for a in seqslist]
self.seqNamelist = [a[1] for a in seqslist]
self.nbseqs = len(seqslist)
self.set_default_size(400, 350)
self.set_modal(False)
# Avoid the destruction of the window
self.connect('delete-event', lambda w, e: w.hide() or True)
self.connect('response', lambda w, e: w.hide() or True)
self.gridDecoSel = Gtk.Grid()
self.scrolledwindow = Gtk.ScrolledWindow()
self.scrolledwindow.set_policy(Gtk.PolicyType.NEVER,Gtk.PolicyType.AUTOMATIC)
self.scrolledwindow.set_min_content_height(350)
self.scrolledwindow.add(self.gridDecoSel)
self.butValidate = Gtk.Button(label="Validate")
self.butValidate.connect("clicked", self.on_validate_customSeq, parent)
self.decoNameLabel = Gtk.Label()
self.box = self.get_content_area()
self.box.add(self.decoNameLabel)
self.box.add(self.scrolledwindow)
self.box.add(self.butValidate)
self.box.set_property("margin",10)
self.box.show_all()
def update_seqslist(self, seqslist, decoName):
self.seqIDlist = [a[0] for a in seqslist]
self.seqNamelist = [a[1] for a in seqslist]
self.nbseqs = len(seqslist)
self.decoNameLabel.set_text(decoName)
while True:
if self.gridDecoSel.get_child_at(0,1)!= None:
self.gridDecoSel.remove_row(1)
else:
break
checkAll = Gtk.Button(label="Check All")
checkAll.connect('clicked', self.check_all)
self.gridDecoSel.attach(checkAll,0,0,2,1)
uncheckAll = Gtk.Button(label="Uncheck All")
uncheckAll.connect('clicked', self.uncheck_all)
self.gridDecoSel.attach(uncheckAll,3,0,2,1)
# create labels for the selection
for i in range(0,self.nbseqs):
label = Gtk.Label(str(self.seqNamelist[i]))
labely = Gtk.Switch()
labely.set_active(False)
label.set_xalign(1)
# print the number and sequence name in lines
self.gridDecoSel.attach(label,0,i+1,2,1)
self.gridDecoSel.attach(Gtk.Label(label=" "),2,i+1,2,1)
self.gridDecoSel.attach(labely,4,i+1,1,1)
self.gridDecoSel.show_all()
def on_validate_customSeq(self, widget, parent):
parent.DecorationSequences[self.decoNameLabel.get_text()] = self.get_checked()
self.hide()
# return the list of checked combinations
#------------------------------------------------------
def get_checked(self):
listchecked = dict()
for i in range(0,max(self.seqIDlist)):
try:
switch = self.gridDecoSel.get_child_at(4,i+1)
if switch.get_active():
listchecked[self.seqIDlist[i]] = 1
else:
listchecked[self.seqIDlist[i]] = 0
except:
continue
return listchecked
def update_check_from_values(self, values):
for i in range(0,max(self.seqIDlist)):
try:
switch = self.gridDecoSel.get_child_at(4,i+1)
if values[self.seqIDlist[i]] == 1:
switch.set_active(True)
else:
switch.set_active(False)
except:
continue
def check_all(self, widget):
for i in range(0,self.nbseqs):
switch = self.gridDecoSel.get_child_at(4,i+1)
switch.set_active(True)
def uncheck_all(self, widget):
for i in range(0,self.nbseqs):
switch = self.gridDecoSel.get_child_at(4,i+1)
switch.set_active(False)
################################################################################################
#
# Blast table data Class
#
################################################################################################
class BlastTable:
#--------------------------------------------------------------------------
def __init__(self, nbseq, hashseq, minlength, maxeval, minident):
# get the filter parameters
self.hashseq = hashseq
self.minlength = int(minlength)
self.maxeval = float(maxeval)
self.minident = float(minident)
# initialize the blast table
# with the number of row and column equal to the number of sequences
self.Btable = []
for i in range(0,nbseq):
self.Btable.append(list())
for j in range(0,nbseq):
self.Btable[i].append(list())
# gets all blast hits length > minlength and e value < mineval and identity > minident
#--------------------------------------------------------------------------
def readBlast(self,filename):
# Test for Blast file presence
if filename == '':
return None
# Get Blast Information
blast = open(filename)
lineI= blast.readline().rstrip()
if lineI.find("\t") > 0: spchar = "\t"
elif lineI.find(",") > 0: spchar = ","
elif lineI.find(" ") > 0: spchar = " "
blast.seek(0,0)
for line in blast:
# empty line
if len(line) == 1 : continue
# define a new blast hit
(query, ref, ident, length, mismatch, gaps, qStart, qEnd, rStart, rEnd, eValue, bitscore) = tuple(line.split(spchar))
blstHit=BlastHit(query, ref, ident, length, mismatch, gaps, qStart, qEnd, rStart, rEnd, eValue, bitscore)
# Test for match on existing sequences
if blstHit.query not in self.hashseq.keys() or blstHit.ref not in self.hashseq.keys():
continue
# Test for length and identity filters
if blstHit.length >= self.minlength and blstHit.eValue <= self.maxeval and blstHit.ident >= self.minident:
# save hits for all pairs of sequences matching this hit (one same sequences can be found several times in the figure)
for i in self.hashseq[blstHit.query]:
for j in self.hashseq[blstHit.ref]:
self.Btable[i][j].append(blstHit.qr())
# get all hits for a given pairwise comparison
#--------------------------------------------------------------------------
def hits(self,i,j):
return self.Btable[i][j]
# remove all hits for a given pairwise comparison
#--------------------------------------------------------------------------
def removehits(self,i,j):
self.Btable[i][j]=list()
# Fill empty table entries in case of non symetrical blast files
#--------------------------------------------------------------------------
def mirroring(self):
for i in range(0,len(self.hashseq)-1):
for j in range(i+1,len(self.hashseq)):
if len(self.Btable[i][j]) == 0 and len(self.Btable[j][i]) > 0:
# copy all hits but by reverting query and reference
for h in self.Btable[j][i]:
self.Btable[i][j].append({'qStart':h['rStart'],
'qEnd':h['rEnd'],
'rStart':h['qStart'],
'rEnd':h['qEnd'],
'ident':h['ident']})
# return ALL displayed hits as a new global list with the length as an aditional parameter
# Used for the 'best blast' positionning option
#--------------------------------------------------------------------------
def returnhits(self):
table = []
for i in range(0,len(self.hashseq)-1):
for j in range(i+1,len(self.hashseq)):
for h in self.Btable[i][j]:
table.append((i,j, abs(h['qEnd']-h['qStart'])+1, h))
# return(sorted(table,key=lambda seqpair: seqpair[2]))
return(table)
# for debugging purpose
#--------------------------------------------------------------------------
def printT(self):
print("\n\n Btable:\n")
for i in range(0,len(self.hashseq)):
for j in range(0,len(self.hashseq)):
for h in self.Btable[i][j]:
print("hit "+str(i)+" vs "+str(j)+": "+str(h['qStart'])+":"+str(h['qEnd'])+" -> "+str(h['rStart'])+":"+str(h['rEnd']))
# select hits which match the subregions selected for the sequences n and m
#--------------------------------------------------------------------------
def filterHits(self,n,m,pmin1,pmax1,pmin2,pmax2):
i=0
while i < len(self.Btable[n][m]):
hit=self.Btable[n][m][i]
# Invert Start and End positions of the query if necessary
if (hit['qStart'] > hit['qEnd']):
qtmp=hit['qStart']
rtmp=hit['rStart']
hit['qStart']=hit['qEnd']
hit['rStart']=hit['rEnd']
hit['qEnd']=qtmp
hit['rEnd']=rtmp
# Get ref hit orientation
if (hit['rStart'] <= hit['rEnd']): o=1
else: o=-1
# Get real min and max positions for the ref
rS = min(hit['rStart'],hit['rEnd'])
rE = max(hit['rStart'],hit['rEnd'])
# condition to be in the selected regions
if (hit['qEnd'] > pmin1) and (hit['qStart'] < pmax1) and (rE > pmin2) and (rS < pmax2) :
# Define the new coordinates on the ref, according to the query position in the subset
# An offset is necessary when the subsequence ends in a middle of a hit
offset = 0
if hit['qStart'] < pmin1: offset = pmin1 - hit['qStart']
temprS=hit['rStart'] - pmin2 + offset*o
offset = 0
if hit['qEnd'] > pmax1: offset = hit['qEnd'] - pmax1
temprE=hit['rEnd'] - pmin2 - offset*o
# Define the new coordinates on the query, according to the ref position
offset = 0
if hit['rStart'] < pmin2:
offset = pmin2 - hit['rStart']
elif hit['rStart'] > pmax2: