-
Notifications
You must be signed in to change notification settings - Fork 16
/
flexidot_v1.06.py
3403 lines (2879 loc) · 155 KB
/
flexidot_v1.06.py
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
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
#!/usr/bin/python2.7
# -*- coding: utf-8 -*-
"""
FlexiDot Version 1.06
FlexiDot: Highly customizable ambiguity-aware dotplots for visual sequence investigation
Kathrin M. Seibt, Thomas Schmidt and Tony Heitkam
Institute of Botany, TU Dresden, Dresden, 01277, Germany
Bioinformatics (2018) Vol. 34 (20), 3575–3577, doi 10.1093/bioinformatics/bty395
"""
###############################
# Requirements #
###############################
# import system modules
import os, glob
import time, datetime
import sys
import shutil, getopt
import unicodedata
def module_install_command(module_name, upgrade=False):
"""
create installation commands for Python modules and print information
"""
if upgrade:
load_command = "python -m pip install --upgrade %s" % module_name
else:
load_command = "python -m pip install %s" % module_name
try:
logprint("Installing Python module: %s\n\t%s\n" % (module_name, load_command))
except:
print "Installing Python module: %s\n\t%s\n" % (module_name, load_command)
return load_command
def load_modules():
"""
load Python modules, if possible - otherwise try to install them
"""
# make module names global
global cllct, gridspec, patches, rcParams, mplrc, P, Color, SeqIO, np, mcolors, rgb2hex, regex
# matplotlib
try:
import matplotlib.collections as cllct
except:
command = module_install_command("matplotlib", upgrade=True)
try:
os.system(command)
print "\n"
import matplotlib.collections as cllct
except:
print "Please install module matplotlib manually"
import matplotlib.colors as mcolors
import matplotlib.gridspec as gridspec
import matplotlib.patches as patches
import pylab as P
P.switch_backend('agg') # bugfix for _tkinter.TclError on CentOs 7 servers, see Github Issue #5
# specify matplotlib font settings
from matplotlib import rc as mplrc
mplrc('pdf', fonttype=42, compression=0)
from matplotlib import rcParams
rcParams['font.family'] = 'sans-serif'
rcParams['font.sans-serif'] = ['Helvetica', 'Verdana', 'Tahoma' , 'DejaVu Sans', 'Droid Sans Mono', 'Sans', 'Liberation', 'Ubuntu', 'Arial', ]
# colour for color gradient palette
try:
from colour import Color
except:
command = module_install_command("colour")
try:
os.system(command)
print "\n"
from colour import Color
except:
print "Please install module colour manually"
# color converter
try:
from colormap import rgb2hex
except:
command = module_install_command("colormap")
# additional module easydev.tools required by colormap
command2 = module_install_command("easydev")
try:
os.system(command)
os.system(command2)
print "\n"
from colormap import rgb2hex
except:
print "Please install module colormap manually"
# biopython
try:
from Bio import SeqIO
except:
command = module_install_command("biopython")
try:
os.system(command)
print "\n"
from Bio import SeqIO
except:
print "Please install module biopython manually"
# numpy
try:
import numpy as np
except:
command = module_install_command("numpy")
try:
os.system(command)
print "\n"
import numpy as np
except:
print "Please install module numpy manually"
# regex for pattern matching
try:
import regex
except:
command = module_install_command("regex")
try:
os.system(command)
print "\n"
import regex
except:
print "Please install module regex manually"
###############################
# Usage & Input #
###############################
def usage():
"""
usage and help
"""
print """\n\n FLEXIDOT
-------------------------------------------------------------------
Version:
1.06
Citation:
Kathrin M. Seibt, Thomas Schmidt, Tony Heitkam (2018)
"FlexiDot: Highly customizable ambiguity-aware dotplots for visual sequence investigation"
Bioinformatics 34 (20), 3575–3577, doi: 10.1093/bioinformatics/bty395
General usage:
$ python flexidot.py -a [ARGUMENTS]
$ python flexidot.py -i <fasta_file_name> [ARGUMENTS]
ARGUMENTS
-------------------------------------------------------------------
INPUT/OUTPUT OPTIONS... required are [-a] OR [-i]
-a, --auto_fas Imports all fasta files from current directory (*.fasta, *.fas, *.fa, *.fna)
-i is not needed, if -a is activated
[inactive by default]
-i, --in_file Input fasta file (fasta file name or comma-separated file list)
> Provide multiple files: Recall -i or provide comma-separated file names
-o, --output_file_prefix File prefix to be added to the generated filenames [default = NONE]
-c, --collage_output Multiple dotplots are combined in a collage
Y or 1 = ON [default]
N or 0 = OFF
-m, --m_col Number of columns per page [default = 4] (only if --collage_output is ON)
-n, --n_row Number of rows per page [default = 5] (only if --collage_output is ON)
-f, --filetype Output file format
0 = PNG [default]
1 = PDF
2 = SVG
-s, --alphabetic_sorting Sort sequences alphabetically according to titles
Y or 1 = ON
N or 0 = OFF [default]
CALCULATION PARAMETERS...
-k, --wordsize Wordsize (kmer length) for dotplot comparison [default = 10]
-p, --plotting_mode Mode of FlexiDot dotplotting
0 = self [default]
1 = paired
2 = poly (matrix with all-against-all dotplots)
> Run multiple plotting modes: Recall -p or provide comma-separated numbers
-t, --type_nuc Type of residue is nucleotide
Y or 1 = nucleotide [default]
N or 0 = amino acid
-w, --wobble_conversion Ambiguity handling for relaxed matching
Y or 1 = ON
N or 0 = OFF [default]
-S, --substitution_count Number of substitutions (mismatches) allowed per window for relaxed matching
[default = 0]
-r, --rc_option Find reverse complementary matches (only if type_nuc=y)
Y or 1 = ON [default]
N or 0 = OFF
-O, --only_vs_first_seq Limit pairwise comparisons to match all sequences to 1st sequence only
(only if --plotting_mode=1)
Y or 1 = ON
N or 0 = OFF [default]
GRAPHIC FORMATTING...
-A, --line_width Line width [default = 1]
-B, --line_col_for Line color [default = black]
-C, --line_col_rev Reverse line color [default = green]
-D, --x_label_pos Position of the X-label
Y or 1 = top [default]
N or 0 = bottom
-E, --label_size Font size [default = 10]
-F, --spacing Spacing between all-against-all dotplots (only if --plotting_mode=2)
[default = 0.04]
-L, --length_scaling Scale plot size for pairwise comparison (only if --plotting_mode=1)
Y or 1 = Scaling ON (axes scaled according to sequence length)
N or 0 = Scaling OFF (squared plots) [default]
-M, --mirror_y_axis Flip y-axis bottom to top (cartesian coordinate system)
Y or 1 = y-axis bottom to top
N or 0 = y-axis top to bottom [default]
-P, --plot_size Plotsize [default = 10]
-R, --representation Region of plot to display (only if --plotting_mode=2)
0 = full [default]
1 = upper
2 = lower
-T, --title_length Limit title length for dotplot comparisons
[default = 20]
Position of selection can be specified by appending a letter (e.g. -T 20E)
B = beginning [default]
E = end
GFF SHADING (for -p/--plotting_mode=0 only)...
-g, --input_gff_files GFF3 file used for markup in self-dotplots
(provide multiple files: Recall -g or provide comma-separated file names)
-G, --gff_color_config_file Tab-delimited config file for custom gff shading
column 1: feature type
column 2: color
column 3: alpha
column 4: zoom factor (for small regions)
LCS SHADING OPTIONS (for -p/--plotting_mode=2 only)...
-x, --lcs_shading Shade subdotplot based on the length of the longest common substring (LCS)
Y or 1 = ON
N or 0 = OFF [default]
-X, --lcs_shading_num Number of shading intervals (hues) for LCS (-x) and user matrix shading (-u)
[default = 5]
-y, --lcs_shading_ref Reference for LCS shading
0 = maximal LCS length [default]
1 = maximally possible length (length of shorter sequence in pairwise comparison)
2 = given interval sizes - DNA [default 100 bp] or proteins [default 10 aa] - see -Y
-Y, --lcs_shading_interval_len Length of intervals for LCS shading (only if --lcs_shading_ref=2)
[default for nucleotides = 50; default for amino acids = 10]
-z, --lcs_shading_ori Shade subdotplots according to LCS on
0 = forward [default],
1 = reverse, or
2 = both strands (forward shading above diagonal, reverse shading on diagonal and below;
if using --input_user_matrix_file, best LCS is used below diagonal)
CUSTOM USER MATRIX SHADING OPTIONS (for -p/--plotting_mode=2 only)...
-u, --input_user_matrix_file Shading above diagonal according to values in matrix file specified by the user
(tab-delimited or comma-separated matrix with sequence name in column 1 and numbers in columns 2-n
e.g. identity matrix from multiple sequence alignment - strings are ignored)
-U, --user_matrix_print Display provided matrix entries in the fields above diagonal of all-against-all dotplot
Y or 1 = ON
N or 0 = OFF [default]
OTHERS...
-h, --help Help screen
-v, --verbose Verbose
"""
def check_input(argv, trial_mode=False):
"""
commandline argument parsing
"""
global log_txt, aa_bp_unit
# helpers for argument parsing
######################################
arguments = ["-a", "--auto_fas", "a", "auto_fas",
"-i", "--input_fasta", "i:", "input_fasta=",
"-o", "--output_file_prefix", "o:", "output_file_prefix=",
"-c", "--collage_output", "c:", "collage_output=",
"-m", "--m_col", "m:", "m_col=",
"-n", "--n_row", "n:", "n_row=",
"-f", "--filetype", "f:", "filetype=",
"-t", "--type_nuc", "t:", "type_nuc=",
"-g", "--input_gff_files", "g:", "input_gff_files",
"-G", "--gff_color_config_file", "G:", "gff_color_config_file",
"-k", "--wordsize", "k:", "wordsize=",
"-p", "--plotting_mode", "p:", "plotting_mode=",
"-w", "--wobble_conversion", "w:", "wobble_conversion=",
"-S", "--substitution_count", "S:", "substitution_count=",
"-r", "--rc_option", "r:", "rc_option=",
"-O", "--only_vs_first_seq", "O:", "only_vs_first_seq=",
"-s", "--alphabetic_sorting", "s:", "alphabetic_sorting=",
"-x", "--lcs_shading", "x:", "lcs_shading=",
"-X", "--lcs_shading_num", "X:", "lcs_shading_num=",
"-y", "--lcs_shading_ref", "y:", "lcs_shading_ref=",
"-Y", "--lcs_shading_interval_len", "Y:", "lcs_shading_interval_len=",
"-z", "--lcs_shading_ori", "z:", "lcs_shading_ori=",
"-u", "--input_user_matrix_file", "u:", "input_user_matrix_file=",
"-U", "--user_matrix_print", "U:", "user_matrix_print=",
"-P", "--plot_size", "P:", "plot_size=",
"-A", "--line_width", "A:", "line_width=",
"-B", "--line_col_for", "B:", "line_col_for=",
"-C", "--line_col_rev", "C:", "line_col_rev=",
"-D", "--x_label_pos", "D:", "x_label_pos=",
"-E", "--label_size", "E:", "label_size=",
"-F", "--spacing", "F:", "spacing=",
"-L", "--length_scaling", "L:", "length_scaling=",
"-M", "--mirror_y_axis", "M:", "mirror_y_axis=",
"-R", "--representation", "R:", "representation=",
"-T", "--title_length", "T:", "title_length=",
"-h", "--help", "h", "help",
"-v", "--verbose", "v", "verbose"]
arguments_sysargv = tuple(arguments[0::4] + arguments[1::4])
arguments_opts = "".join(arguments[2::4])
arguments_args = arguments[3::4]
# setting defaults
######################################
auto_fas = False # 0
input_fasta = []
output_file_prefix = None
collage_output = True # 1
m_col = 4
n_row = 5
filetype = 0
type_nuc = True
input_gff_files = []
gff_color_config_file = ""
wordsize = 10
plotting_modes = [0]
wobble_conversion = False # 0
substitution_count = 0
rc_option = True # 1
alphabetic_sorting = False # 0
only_vs_first_seq = False # 0
lcs_shading = False # 0
lcs_shading_num = 4
lcs_shading_ref = 0
lcs_shading_interval_len = 50 # interval default changes to "10" for amino acids [type_nuc = n]
lcs_shading_ori = 0
input_user_matrix_file = ""
user_matrix_print = False
plot_size = 10
line_width = 1
line_col_for = "black"
line_col_rev = "#009243"
x_label_pos = True # 0
label_size = 10
spacing = 0.04
length_scaling = False # 0
title_length = 20 # float("Inf")
title_clip_pos = "B" # B (begin), E (end)
max_N_percentage = 49 # fixed value, no user input
mirror_y_axis = False
representation = 0
aa_bp_unit = "bp"
verbose = False # 0
filetype_dict = {0: "png", 1: "pdf", 2: "svg"}
lcs_shading_ref_dict = {0: "maximal LCS length", 1: "maximally possible length", 2: "given interval sizes"}
plotting_mode_dict = {0: "self", 1: "paired", 2: "all-against-all"}
lcs_shading_ori_dict = {0: "forward", 1: "reverse complement", 2: "both"}
representation_dict = {0: "full", 1: "upper", 2: "lower"}
# return default parameters for testing purposes
if trial_mode:
print "ATTENTION: YOU ARE IN THE TRIAL MODE!!!\n\n"
commandline = "trial_mode\n"
parameters = [commandline, auto_fas, input_fasta, output_file_prefix, collage_output, m_col, n_row, filetype_dict[filetype], type_nuc, input_gff_files, gff_color_config_file, wordsize, plotting_modes, wobble_conversion, substitution_count, rc_option, alphabetic_sorting, only_vs_first_seq, lcs_shading, lcs_shading_num, lcs_shading_ref, lcs_shading_interval_len, lcs_shading_ori, input_user_matrix_file, user_matrix_print, plot_size, line_width, line_col_for, line_col_rev, x_label_pos, label_size, spacing, length_scaling, title_length, title_clip_pos, max_N_percentage, mirror_y_axis, representation, verbose]
return parameters
# read arguments
######################################
commandline = ""
for arg in sys.argv:
commandline += arg + " "
log_txt = "\n...reading input arguments..."
print log_txt
if len(sys.argv) < 2:
print "\nERROR: More arguments are needed. Exit..."
log_txt += "\nERROR: More arguments are needed. Exit..."
usage()
sys.exit()
elif sys.argv[1] not in arguments_sysargv:
print "\nINPUT ERROR: Input argument %s unknown. Please check the help screen." % sys.argv[1]
log_txt += "\nINPUT ERROR: Input argument %s unknown. Please check the help screen." % sys.argv[1]
# usage()
sys.exit()
try:
opts, args = getopt.getopt(sys.argv[1:], arguments_opts, arguments_args)
except getopt.GetoptError:
print "\nINPUT ERROR (getopt): Input argument %s unknown. Please check the help screen." % sys.argv[1:]
log_txt += "\nINPUT ERROR (getopt): Input argument %s unknown. Please check the help screen." % sys.argv[1:]
# usage()
sys.exit()
for opt, arg in opts:
if opt in ("-h", "--help"):
print "...fetch help screen"
log_txt += "\n...fetch help screen"
usage(), sys.exit()
if opt in ("-v", "--verbose"):
print "...verbose output"
log_txt += "\n...verbose output"
verbose = True
elif opt in ("-i", "--input_fasta"):
if "," in arg:
arg_list = arg.split(",")
for temp_file in arg_list:
if not os.path.exists(str(temp_file)):
message = "\nERROR: fasta_file '%s' was not found!" % str(temp_file)
sys.exit(message)
else:
input_fasta.append(str(temp_file))
print "fasta file #%i: %s" % (len(input_fasta), str(temp_file))
log_txt += "\nfasta file #%i: %s" % (len(input_fasta), str(temp_file))
else:
if not os.path.exists(str(arg)):
message = "\nERROR: fasta_file '%s' was not found!" % str(arg)
log_txt += message
sys.exit(message)
else:
input_fasta.append(str(arg))
print "fasta file #%i: %s" % (len(input_fasta), str(arg))
log_txt += "\nfasta file #%i: %s" % (len(input_fasta), str(arg))
elif opt in ("-a", "--auto_fas"):
auto_fas = True
# multiple gff files: reads them into a list
elif opt in ("-g", "--input_gff_files"):
# append gff file only if existing
if "," in arg:
arg_list = arg.split(",")
for temp_file in arg_list:
if not os.path.exists(str(temp_file)):
message = "\nERROR: gff_file '%s' was not found!" % str(temp_file)
print message
log_txt += message
print " -->Running FlexiDot without this gff file!"
log_txt += "\n -->Running FlexiDot without this gff file!"
else:
print "GFF file #%i: %s" %(len(input_gff_files), str(temp_file))
log_txt += "\nGFF file #%i: %s" %(len(input_gff_files), str(temp_file))
input_gff_files.append(str(temp_file))
else:
if not os.path.exists(str(arg)):
message = "\nERROR: gff_file '%s' was not found!" % str(arg)
print message
log_txt += message
print " -->Running FlexiDot without this gff file!"
log_txt += "\n -->Running FlexiDot without this gff file!"
else:
input_gff_files.append(str(arg))
print "GFF file #%i: %s" %(len(input_gff_files), str(arg))
log_txt += "\nGFF file #%i: %s" %(len(input_gff_files), str(arg))
elif opt in ("-G", "--gff_color_config_file"):
if not os.path.exists(str(arg)):
message = "\nERROR: gff_color_config_file '%s' was not found!" % str(arg)
print message + "\n -->Running FlexiDot with default gff coloring specification!"
log_txt += message + "\n -->Running FlexiDot with default gff coloring specification!"
else:
gff_color_config_file = str(arg)
elif opt in ("-u", "--input_user_matrix_file"):
if not os.path.exists(str(arg)):
message = "\nERROR: input_user_matrix_file '%s' was not found!" % str(arg)
print message + "\n -->Running FlexiDot without input_user_matrix_file %s!" % arg
log_txt += message + "\n -->Running FlexiDot withdefault matrix shading file!"
else:
input_user_matrix_file = str(arg)
elif opt in ("-U", "--user_matrix_print"):
user_matrix_print = check_bools(str(arg), default=user_matrix_print)
elif opt in ("-o", "--output_file_prefix"):
output_file_prefix = arg
elif opt in ("-c", "--collage_output"):
collage_output = check_bools(str(arg), default=collage_output)
elif opt in ("-m", "--m_col"):
try: m_col = int(arg)
except:
print "m_col - invalid argument - using default value"
log_txt += "\nm_col - invalid argument - using default value"
elif opt in ("-n", "--n_row"):
try: n_row = int(arg)
except:
print "n_row - invalid argument - using default value"
log_txt += "\nn_row - invalid argument - using default value"
elif opt in ("-f", "--filetype"):
if 0 <= int(arg) <= 2:
filetype = int(arg)
else:
print "\nERROR: Please provide valid filetype argument. %s is out of range. It will be set to -f 0 [default]." %(filetype)
log_txt += "\nERROR: Please provide valid filetype argument. %s is out of range. It will be set to -f 0 [default]." %(filetype)
elif opt in ("-t", "--type_nuc"):
type_nuc = check_bools(str(arg), default=type_nuc)
if type_nuc == False:
# interval default changed for amino acids
lcs_shading_interval_len = 10
aa_bp_unit = "aa"
elif opt in ("-k", "--wordsize"):
try: wordsize = int(arg)
except:
print "wordsize - invalid argument - using default value"
log_txt += "\nwordsize - invalid argument - using default value"
elif opt in ("-p", "--plotting_mode"):
if "," in arg:
temp_modes = arg.split(",")
for item in temp_modes:
if item in ["0","1","2"]:
plotting_modes.append(int(item))
elif arg in ["0","1","2"]:
plotting_modes = [int(arg)]
else:
print "Please provide valid plotting_modes argument - e.g. 1 or 0,1,2 - using default [0]"
log_txt += "\nPlease provide valid plotting_modes argument - e.g. 1 or 0,1,2 - using default [0]"
elif opt in ("-w", "--wobble_conversion"):
wobble_conversion = check_bools(str(arg), default=wobble_conversion)
elif opt in ("-S", "--substitution_count"):
try: substitution_count = int(arg)
except:
print "substitution_count - invalid argument - using default value"
log_txt += "\nsubstitution_count - invalid argument - using default value"
elif opt in ("-r", "--rc_option"):
rc_option = check_bools(str(arg), default=rc_option)
elif opt in ("-s", "--alphabetic_sorting"):
alphabetic_sorting = check_bools(str(arg), default=alphabetic_sorting)
elif opt in ("-O", "--only_vs_first_seq"):
only_vs_first_seq = check_bools(str(arg), default=only_vs_first_seq)
elif opt in ("-x", "--lcs_shading"):
lcs_shading = check_bools(str(arg), default=lcs_shading)
elif opt in ("-X", "--lcs_shading_num"):
try: lcs_shading_num = int(arg) - 1
except:
print "lcs_shading_num - invalid argument - using default value"
log_txt += "\nlcs_shading_num - invalid argument - using default value"
elif opt in ("-y", "--lcs_shading_ref"):
try:
if 0 <= int(arg) <= 2:
lcs_shading_ref = int(arg)
else:
print "\nERROR: lcs_shading_ref %s out of range. It will be set to -y 0 [default]." %(lcs_shading_ref)
log_txt += "\nERROR: lcs_shading_ref %s out of range. It will be set to -y 0 [default]." %(lcs_shading_ref)
except:
print "lcs_shading_ref - invalid argument - using default value"
log_txt += "\nlcs_shading_ref - invalid argument - using default value"
elif opt in ("-Y", "--lcs_shading_interval_len"):
try: lcs_shading_interval_len = int(arg)
except:
print "lcs_shading_interval_len - invalid argument - using default value"
log_txt += "\nlcs_shading_interval_len - invalid argument - using default value"
elif opt in ("-z", "--lcs_shading_ori"):
if 0 <= int(arg) <= 2:
lcs_shading_ori = int(arg)
else:
print "\nERROR: Please provide valid lcs_shading_ori argument. %s is out of range. It will be set to -z 0 [default]." %(lcs_shading_ori)
log_txt += "\nERROR: Please provide valid lcs_shading_ori argument. %s is out of range. It will be set to -z 0 [default]." %(lcs_shading_ori)
elif opt in ("-P", "--plot_size"):
try: plot_size = float(arg)
except:
print "plot_size - invalid argument - using default value"
log_txt += "\nplot_size - invalid argument - using default value"
elif opt in ("-A", "--line_width"):
try: line_width = float(arg)
except:
print "line_width - invalid argument - using default value"
log_txt += "\nline_width - invalid argument - using default value"
elif opt in ("-B", "--line_col_for"):
if mcolors.is_color_like(arg):
line_col_for = arg
else:
print "line_col_for - invalid argument - using default value"
log_txt += "\nline_col_for - invalid argument - using default value"
elif opt in ("-C", "--line_col_rev"):
if mcolors.is_color_like(arg):
line_col_rev = arg
else:
print "line_col_rev - invalid argument - using default value"
log_txt += "\nline_col_rev - invalid argument - using default value"
elif opt in ("-D", "--x_label_pos"):
x_label_pos = check_bools(str(arg), default=x_label_pos)
elif opt in ("-E", "--label_size"):
try: label_size = float(arg)
except:
print "label_size - invalid argument - using default value"
log_txt += "\nlabel_size - invalid argument - using default value"
elif opt in ("-F", "--spacing"):
try: spacing = float(arg)
except:
print "spacing - invalid argument - using default value"
log_txt += "\nspacing - invalid argument - using default value"
elif opt in ("-L", "--length_scaling"):
length_scaling = check_bools(str(arg), default=length_scaling)
elif opt in ("-M", "--mirror_y_axis"):
mirror_y_axis = check_bools(str(arg), default=mirror_y_axis)
elif opt in ("-R", "--representation"):
if 0 <= int(arg) <= 2:
representation = int(arg)
else:
print "\nERROR: Please provide valid representation argument. %s is out of range. It will be set to -R 0 [default]." %(representation)
log_txt += "\nERROR: Please provide valid representation argument. %s is out of range. It will be set to -R 0 [default]." %(representation)
elif opt in ("-T", "--title_length"):
try: title_length = int(arg)
except:
try:
title_length = int(str(arg)[:-1])
if arg[-1].upper() in ["B", "E"]: # B (beginning), E (end)
title_clip_pos = arg[-1].upper()
else:
print "title_length position information invalid - using default value"
log_txt += "\ntitle_length position information invalid - using default value"
except:
print "title_length - invalid argument - using default value"
log_txt += "\ntitle_length - invalid argument - using default value"
# start logging file
logprint(commandline, start=True, printing=False, prefix=output_file_prefix)
logprint(log_txt, start=False, printing=False)
# print chosen arguments
######################################
text = "\n%s\n" % (70 * "-")
text += "\n" + "INPUT/OUTPUT OPTIONS...\n"
text += "\n" + "Input fasta file: " + ", ".join(input_fasta)
text += "\n" + "Automatic fasta collection from current directory: " + str(auto_fas)
text += "\n" + "Collage output: " + str(collage_output)
text += "\n" + "Number of columns per page: " + str(m_col)
text += "\n" + "Number of rows per page: " + str(n_row)
text += "\n" + "File format: " + filetype_dict[filetype]
text += "\n" + "Residue type is nucleotide: " + str(type_nuc)
text += "\n" + "\n\nCALCULATION PARAMETERS...\n"
text += "\n" + "Wordsize: " + str(wordsize)
text += "\n" + "Sustitution count: " + str(substitution_count)
text += "\n" + "Plotting mode: " + str(plotting_modes).replace("[", "").replace("]", "") + "\n" + 51 * " "
for item in plotting_modes:
text += plotting_mode_dict[item] + " "
text += "\n" + "Ambiguity handling: " + str(wobble_conversion)
text += "\n" + "Reverse complement scanning: " + str(rc_option)
text += "\n" + "Alphabetic sorting: " + str(alphabetic_sorting)
if 1 in plotting_modes:
text += "\n" + "Only matching sequences to first entry: " + str(only_vs_first_seq)
if 0 in plotting_modes and input_gff_files != []:
text += "\n" + "Input gff files: " + ", ".join(input_gff_files)
if gff_color_config_file != "":
text += "\n" + "GFF color config file: " + gff_color_config_file
text += "\n" + "Prefix for output files: " + str(output_file_prefix)
if 2 in plotting_modes:
text += "\n" + "\n\nLCS SHADING OPTIONS (plotting_mode 'all-against-all' only)...\n"
text += "\n" + "LCS shading: " + str(lcs_shading)
text += "\n" + "LCS shading interval number: " + str(lcs_shading_num + 1)
text += "\n" + "LCS shading reference: " + lcs_shading_ref_dict[lcs_shading_ref]
if lcs_shading_ref == 2:
text += "\n" + "LCS shading interval size [%s]: " % (aa_bp_unit) + str(lcs_shading_interval_len)
text += "\n" + "LCS shading orientation: " + lcs_shading_ori_dict[lcs_shading_ori]
if input_user_matrix_file != "":
text += "\n" + "Custom user shading matrix file: " + input_user_matrix_file
text += "\n" + "Print user matrix values (instead of dotplot): " + str(user_matrix_print)
text += "\n" + "Displayed plot region: " + representation_dict[representation]
text += "\n" + "\n\nGRAPHIC FORMATTING...\n"
text += "\n" + "Plot size: " + str(plot_size)
text += "\n" + "Line width: " + str(line_width)
text += "\n" + "Line color: " + line_col_for
text += "\n" + "Reverse line color: " + line_col_rev
text += "\n" + "X label position: " + str(x_label_pos)
text += "\n" + "Label size: " + str(label_size)
text += "\n" + "Spacing: " + str(spacing)
if mirror_y_axis:
text += "\n" + "Y-axis mirrored (bottom to top) " + str(mirror_y_axis)
if title_clip_pos == "E":
text += "\n" + "Title length (limit number of characters): " + "last" + str(title_length) + "characters"
else:
text += "\n" + "Title length (limit number of characters): " + "first" + str(title_length) + "characters"
text += "\n" + "Length scaling: " + str(length_scaling)
text += "\n%s\n" % (70 * "-")
logprint(text)
# collect settings
parameters = [commandline, auto_fas, input_fasta, output_file_prefix, collage_output, m_col, n_row, filetype_dict[filetype], type_nuc, input_gff_files, gff_color_config_file, wordsize, plotting_modes, wobble_conversion, substitution_count, rc_option, alphabetic_sorting, only_vs_first_seq, lcs_shading, lcs_shading_num, lcs_shading_ref, lcs_shading_interval_len, lcs_shading_ori, input_user_matrix_file, user_matrix_print, plot_size, line_width, line_col_for, line_col_rev, x_label_pos, label_size, spacing, length_scaling, title_length, title_clip_pos, max_N_percentage, mirror_y_axis, representation, verbose]
return parameters
###############################
# Helper Functions #
###############################
def alphabets(type_nuc=True):
"""
provide ambiguity code for sequences
"""
nucleotide_alphabet = ["A", "C", "G", "T"]
nucleotide_alphabet_full = ["A", "C", "G", "T", "N", "B", "D", "H",
"V", "Y", "R", "W", "S", "K", "M"]
nucleotide_ambiguity_code = {"N": ["A", "C", "G", "T"], # any
"B": ["C", "G", "T"], # not A
"D": ["A", "G", "T"], # not C
"H": ["A", "C", "T"], # not G
"V": ["A", "C", "G"], # not T
"Y": ["C", "T"], # pyrimidine
"R": ["A", "G"], # purine
"W": ["A", "T"], # weak
"S": ["C", "G"], # strong
"K": ["G", "T"], # keto
"M": ["A", "C"]} # amino
nucleotide_match_dict = {"N": "[ACGTNBDHVYRWSKM]", # any
"B": "[CGTNBDHVYRWSKM]", # not A
"D": "[AGTNBDHVYRWSKM]", # not C
"H": "[ACTNBDHVYRWSKM]", # not G
"V": "[ACGNBDHVYRWSKM]", # not T
"K": "[GTNBDHVYRWSK]", # keto - not A,C,M
"M": "[ACNBDHVYRWSM]", # amino - not G,T,K
"W": "[ATNBDHVYRWKM]", # weak - not C,G,S
"S": "[CGNBDHVYRSKM]", # strong - not A,G,W
"Y": "[CTNBDHVYWSKM]", # pyrimidine - not A,G,R
"R": "[AGNBDHVRWSKM]", # purine - not C,T,Y
"A": "[ANDHVRWM]",
"C": "[CNBHVYSM]",
"G": "[GNBDVRSK]",
"T": "[TNBDHYWK]"}
# nucleotide_match_dict = {"N": ".", # any
# "B": "[^A]", # not A
# "D": "[^C]", # not C
# "H": "[^G]", # not G
# "V": "[^T]", # not T
# "K": "[^ACM]", # keto - not A,C,M
# "M": "[^GTK]", # amino - not G,T,K
# "W": "[^CGS]", # weak - not C,G,S
# "S": "[^AGW]", # strong - not A,G,W
# "Y": "[^AGR]", # pyrimidine - not A,G,R
# "R": "[^CTY]", # purine - not C,T,Y
# "A": "[ANDHVRWM]",
# "C": "[CNBHVYSM]",
# "G": "[GNBDVRSK]",
# "T": "[TNBDHYWK]"}
aminoacid_alphabet = ["A", "R", "N", "D", "C", "E", "Q", "G",
"H", "I", "L", "K", "M", "F", "P", "S",
"T", "W", "Y", "V", "U", "O", "*"]
aminoacid_alphabet_full = ["A", "R", "N", "D", "C", "E", "Q", "G",
"H", "I", "L", "K", "M", "F", "P", "S",
"T", "W", "Y", "V", "U", "O", "*", "J",
"Z", "B", "X"]
aminoacid_ambiguity_code = {"J": ["I", "L"],
"Z": ["Q", "E"],
"B": ["N", "D"],
"X": ["A", "R", "N", "D", "C", "E", "Q", "G",
"H", "I", "L", "K", "M", "F", "P", "S",
"T", "W", "Y", "V", "U", "O", "*"]} # any
aminoacid_match_dict = {"J": "[ILJ]",
"Z": "[QEZ]",
"B": "[NDB]",
# "X": ".",
"X": "[ARNDCEQGHILKMFPSTWYVUO*XBZJ]",
"A": "[AX]",
"R": "[RX]",
"N": "[NXB]",
"D": "[DXB]",
"C": "[CX]",
"E": "[EXZ]",
"Q": "[QXZ]",
"G": "[GX]",
"H": "[HX]",
"I": "[IXJ]",
"L": "[LXJ]",
"K": "[KX]",
"M": "[MX]",
"F": "[FX]",
"P": "[PX]",
"S": "[SX]",
"T": "[TX]",
"W": "[WX]",
"Y": "[YX]",
"V": "[VX]",
"U": "[UX]",
"O": "[OX]",
"*": "[*X]"}
aa_only = set(['E', 'F', 'I', 'J', 'L', 'O', 'Q', 'P', 'U', 'X', 'Z', '*'])
# return nucleotide_alphabet, nucleotide_alphabet_full, nucleotide_ambiguity_code, aminoacid_alphabet, aminoacid_alphabet_full, aminoacid_ambiguity_code, aa_only
if type_nuc:
return nucleotide_alphabet, nucleotide_alphabet_full, nucleotide_ambiguity_code, nucleotide_match_dict
else:
return aminoacid_alphabet, aminoacid_alphabet_full, aminoacid_ambiguity_code, aminoacid_match_dict
def logprint(text, start=False, printing=True, prefix=""):
"""
log output to log_file and optionally print
"""
# define log file name and open file
global log_file_name
if start and trial_mode:
log_file_name = "log_file.txt"
if prefix != "" and prefix != None:
if not prefix.endswith("-"):
prefix = prefix + "-"
log_file_name = prefix + log_file_name
log_file = open(log_file_name, 'w')
log_file.write("Date: %s\n\n" % str(datetime.datetime.now()))
elif start:
date = datetime.date.today()
time = str(datetime.datetime.now()).split(" ")[1].split(".")[0].replace(":", "-")
log_file_name = "%s_%s_log_file.txt" % (date, time)
if prefix != "" and prefix != None:
if not prefix.endswith("-"):
prefix = prefix + "-"
log_file_name = prefix + log_file_name
log_file = open(log_file_name, 'w')
log_file.write("Date: %s\n\n" % str(datetime.datetime.now()))
else:
log_file = open(log_file_name, 'a')
# write log (and print)
log_file.write(text + "\n")
if printing:
print text
log_file.close()
def time_track(starting_time, show=True):
"""
calculate time passed since last time measurement
"""
now = time.time()
delta = now - starting_time
if show:
text = "\n\t %s seconds\n" % str(delta)
logprint(text, start=False, printing=True)
return now
def calc_fig_ratio(ncols, nrows, plot_size, verbose=False):
"""
calculate size ratio for given number of columns (ncols) and rows (nrows)
with plot_size as maximum width and length
"""
ratio = ncols*1./nrows
if verbose:
text = " ".join([ncols, nrows, ratio])
logprint(text, start=False, printing=True)
if ncols >= nrows:
figsize_x = plot_size
figsize_y = plot_size / ratio
else:
figsize_x = plot_size * ratio
figsize_y = plot_size
return figsize_x, figsize_y
def shorten_name(seq_name, max_len=20, title_clip_pos="B"): #, delim="_"):
"""
shorten sequence names (for diagram titles)
"""
if len(seq_name) <= max_len:
return seq_name
# take last characters
if title_clip_pos == "E":
name = seq_name[len(seq_name)-max_len:]
# take first characters
else:
name = seq_name[:max_len]
"""# keep first and last part if multiple parts separated by delimiter (e.g. species_prefix + sequence_id)
if delim in seq_name:
if seq_name.count(delim) >= 2:
name = "%s..." % delim.join(seq_name.split(delim)[:1]) + seq_name.split(delim)[-1] # .replace("_000", "-")