-
Notifications
You must be signed in to change notification settings - Fork 0
/
dot_plot_heatmap.py
378 lines (293 loc) · 10.6 KB
/
dot_plot_heatmap.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
### Boas Pucker ###
### bpucker@cebitec.uni-bielefeld.de ###
### v1.3 ###
## based on: Pucker et al., 2019; https://doi.org/10.1371/journal.pone.0216233 ###
__usage__ = """
python dot_plot_heatmap.py\n
--in1 <FULL_PATH_TO_FASTA_FILE1>
--in2 <FULL_PATH_TO_FASTA_FILE2>
--out <FULL_PATH_TO_OUTPUT_DIRECTORY>[.]\n
OPTIONAL:
--gff1 <GFF_FILE_TO_INCLUDE_AGIs>
--gff2 <GFF_FILE_TO_INCLUDE_BAC_IDs>
--chr <CHROMOSOME>
--start <START>
--end <END>
--show dot plot heatmap will be displayed as interactive figure
--cite will not run the script, but display the reference to cite for it
--block <INT, size of blocks represented by one dot [bp]>[1000]
--namex <STRING, name of first sequence>
--namey <STRING, name of second sequence>
--title <STRING, title of plot>[""]
--name <PREFIX_OF_RESULT_FILES>[""]
bug reports and feature requests: bpucker@cebitec.uni-bielefeld.de
"""
__reference__ = """Pucker et al., 2019: https://doi.org/10.1371/journal.pone.0216233"""
import sys, os, re
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from datetime import datetime
from operator import itemgetter
# --- end of imports --- #
def chunk_generator( seq, chunk_size):
"""! @brief generates successive n-sized chunks from input sequence """
for i in xrange( 0, len( seq ), chunk_size):
yield seq[ i:i + chunk_size]
def construct_seq_block_file( input_file, output_file, block_size ):
"""! @brief construct file with chunked sequence """
counter = 0
with open( output_file, "w" ) as out:
with open( input_file, "r" ) as f:
f.readline() #remove header
seq = []
line = f.readline()
while line:
if line[0] == ">":
chunks = chunk_generator( "".join( seq ), block_size)
for each in chunks:
out.write( '>' + str( counter ).zfill( 8 ) + '\n' + each + '\n' )
counter += 1
seq = []
else:
seq.append( line.strip() )
line = f.readline()
chunks = chunk_generator( "".join( seq ), block_size)
for each in chunks:
out.write( '>' + str( counter ).zfill( 8 ) + '\n' + each + '\n' )
counter += 1
def load_blast_results( blast_result_file ):
"""! @brief load blast results for plot """
blast_results = {}
with open( blast_result_file, "r" ) as f:
line = f.readline()
while line:
parts = line.strip().split('\t')
try:
hit = blast_results[ parts[0] ]
if float( parts[-1] ) > hit['score']:
del blast_results[ parts[0] ]
blast_results.update( { parts[0]: { 'id': parts[0], 'chr': parts[1], 'pos': ( int( parts[8] )+int( parts[9] ) )*0.5, 'score': float( parts[-1] ) } } )
except KeyError:
blast_results.update( { parts[0]: { 'id': parts[0], 'chr': parts[1], 'pos': ( int( parts[8] )+int( parts[9] ) )*0.5, 'score': float( parts[-1] ) } } )
line = f.readline()
return blast_results
def calculate_color( value ):
"""! @brief calculates color for given value """
r = 255-int( 255*value**4 )
g = 255-int( 255*value**4 )
b = 255
color = '#%02x%02x%02x' % (r, g, b)
return color
def construct_dot_plot( self_blast_results, other_blast_results, output_figure, show_status, namex, namey, title ):
"""! @brief construct dot plot with score weighted points """
# --- construction of plot --- #
fig, ax = plt.subplots( figsize=(10,10) )
maxx = 0
maxy = 0
for key in self_blast_results.keys():
try:
other_point = other_blast_results[ key ]
self_point = self_blast_results[ key ]
score = other_point[ 'score' ] / self_point[ 'score' ]
point_color = calculate_color( score )
x = self_point['pos'] / 1000.0
if x > maxx:
maxx = 0 + x
y = other_point['pos'] / 1000.0
if y > maxy:
maxy = 0 + y
ax.scatter( x, y, color=point_color,s=1 )
except KeyError:
pass
ax.set_xlabel( namex + " [kbp]" )
ax.set_ylabel( namey + " [kbp]" )
ax.set_xlim( 0, maxx )
ax.set_ylim( 0, maxy )
ax.ticklabel_format( axis='y', scilimits=(-2,2) ) #, style="sci"
ax.ticklabel_format( axis='x', scilimits=(-2,2) ) #, style="sci"
ax.get_xaxis().get_major_formatter().set_scientific(False)
ax.get_yaxis().get_major_formatter().set_scientific(False)
patches = []
for i in range( 11 ):
patches.append( mpatches.Patch(color=calculate_color( i/10.0 ), label=str(i/10.0) ) )
ax.legend( handles=patches, loc='upper left' ) #'lower right'
ax.set_title( title )
if show_status:
plt.show()
fig.savefig( output_figure, dpi=1200 )
def load_all_seqs_from_multiple_fasta_file( filename ):
"""! @brief load all sequences from multiple fasta file """
data = {}
with open( filename, "r" ) as f:
header = f.readline().strip()[1:].split(' ')[0]
line = f.readline()
seq = []
while line:
if line[0] == '>':
data.update( { header: "".join( seq ) } )
header = line.strip()[1:].split(' ')[0]
seq = []
else:
seq.append( line.strip() )
line = f.readline()
data.update( { header: "".join( seq ) } )
return data
def generate_concatenated_seq( infile, outfile ):
"""! @brief generate new sequence file with concatenated sequence """
seq = []
with open( infile, "r" ) as f:
line = f.readline()
while line:
if line[0] != '>':
seq.append( line.strip() )
line = f.readline()
with open( outfile, "w" ) as out:
out.write( '>seq\n' + "".join( seq ) + '\n' )
def load_gene_positions( gff1_file ):
"""! @brief load gene positions from given GFF file """
gene_positions = {}
with open( gff1_file, "r" ) as f:
line = f.readline()
while line:
if line[0] != '#':
parts = line.strip().split('\t')
if parts[2] == "gene":
ID = re.findall( "AT\dG\d+", parts[-1] )[0]
try:
gene_positions[ parts[0] ].append( { 'start': int( parts[3] ), 'end': int( parts[4] ), 'agi': ID } )
except KeyError:
gene_positions.update( { parts[0]: [ { 'start': int( parts[3] ), 'end': int( parts[4] ), 'agi': ID } ] } )
line = f.readline()
return gene_positions
def load_BAC_positions( gff2_file ):
"""! @brief load BAC IDs from GFF file """
BAC_IDs = {}
with open( gff2_file, "r" ) as f:
line = f.readline()
while line:
if line[0] != "#":
parts = line.strip().split('\t')
try:
BAC_IDs[ parts[0] ].append( { 'start': int( parts[3] ), 'end': int( parts[4] ), 'id': parts[-1] } )
except KeyError:
BAC_IDs.update( { parts[0]: [ { 'start': int( parts[3] ), 'end': int( parts[4] ), 'id': parts[-1] } ] } )
line = f.readline()
return BAC_IDs
def main( arguments ):
"""! @brief runs all parts of this script """
in_seq_ref_file1 = arguments[ arguments.index( '--in1' )+1 ]
in_seq_ref_file2 = arguments[ arguments.index( '--in2' )+1 ]
if '--show' in arguments:
show_status = True
else:
show_status = False
if '--block' in arguments:
block_size = int( arguments[ arguments.index( '--block' )+1 ] )
else:
block_size = 1000
if '--namex' in arguments:
namex = arguments[ arguments.index( '--namex' )+1 ]
else:
namex = "x"
if '--namey' in arguments:
namey = arguments[ arguments.index( '--namey' )+1 ]
else:
namey = "y"
if '--name' in arguments:
name = arguments[ arguments.index( '--name' )+1 ]
else:
name = ""
if '--title' in arguments:
title = arguments[ arguments.index( '--title' )+1 ]
else:
title = ""
if '--gff1' in arguments:
gff1_file = arguments[ arguments.index( '--gff1' )+1 ]
genes = load_gene_positions( gff1_file )
else:
genes = {}
if '--gff2' in arguments:
gff2_file = arguments[ arguments.index( '--gff2' )+1 ]
BACs = load_BAC_positions( gff2_file )
else:
BACs = {}
if '--chr' in arguments:
chromosome = arguments[ arguments.index( '--chr' )+1 ]
else:
chromosome = ""
if '--start' in arguments:
start = int( arguments[ arguments.index( '--start' )+1 ] )
else:
start = 0
if '--end' in arguments:
end = int( arguments[ arguments.index( '--end' )+1 ] )
else:
end = 0
# --- construct complex name --- #
try:
genes_per_chr = sorted( genes[ chromosome ], key=itemgetter('start') )
gene_names = []
for gene in genes_per_chr:
if gene['start'] < end:
if gene['end'] > start:
gene_names.append( gene['agi'] )
if len( gene_names ) > 0:
if len( gene_names ) > 2:
title += "_" + gene_names[0] + "..." + gene_names[-1]
else:
title += "_" + ";".join( gene_names )
except KeyError:
pass
try:
bacs_per_chr = sorted( BACs[ chromosome ], key=itemgetter('start') )
bac_names = []
for bac in bacs_per_chr:
if bac['start'] < end:
if bac['end'] > start:
bac_names.append( bac['id'] )
if len( bac_names ) > 0:
if len( bac_names ) > 2:
title += "_" + bac_names[0] + "..." + bac_names[-1]
else:
title += "_" + ";".join( bac_names )
except KeyError:
pass
prefix = arguments[ arguments.index( '--out' )+1 ]
if prefix[-1] != "/":
prefix += "/"
if not os.path.exists( prefix ):
os.makedirs( prefix )
output_figure = prefix + name + "_dot_plot_heatmap.pdf"
seq_ref_file1 = prefix + name + "_seq1.fasta"
seq_ref_file2 = prefix + name + "_seq2.fasta"
generate_concatenated_seq( in_seq_ref_file1, seq_ref_file1 )
generate_concatenated_seq( in_seq_ref_file2, seq_ref_file2 )
active = True
# --- set output files --- #
self_blast_result_file = prefix + "self_blast_result_file.txt"
other_blast_result_file = prefix + "other_blast_result_file.txt"
if active:
seq_block_file1 = prefix + "seq_blocks.fasta"
construct_seq_block_file( seq_ref_file1, seq_block_file1, block_size )
# --- run blast vs. self and vs. other --- #
self_blast_db = prefix + "self_blast_db"
other_blast_db = prefix + "other_blast_db"
if active:
os.popen( "makeblastdb -in " + seq_ref_file1 + " -out " + self_blast_db + " -dbtype nucl" )
os.popen( "makeblastdb -in " + seq_ref_file2 + " -out " + other_blast_db + " -dbtype nucl" )
if active:
os.popen( "blastn -query " + seq_block_file1 + " -db " + self_blast_db + " -out " + self_blast_result_file + " -outfmt 6 -evalue 0.01 -num_threads 8" )
os.popen( "blastn -query " + seq_block_file1 + " -db " + other_blast_db + " -out " + other_blast_result_file + " -outfmt 6 -evalue 0.01 -num_threads 8" )
# --- load blast results --- #
self_blast_results = load_blast_results( self_blast_result_file )
other_blast_results = load_blast_results( other_blast_result_file )
print "Generating dot plot heatmap ..."
construct_dot_plot( self_blast_results, other_blast_results, output_figure, show_status, namex, namey, title )
if '--cite' in sys.argv:
sys.exit( __reference__ )
if '--help' in sys.argv or '-h' in sys.argv:
sys.exit( __usage__ )
elif '--out' in sys.argv and '--in1' in sys.argv and '--in2' in sys.argv:
main( sys.argv )
else:
sys.exit( __usage__ )