-
Notifications
You must be signed in to change notification settings - Fork 3
/
progenome-classifier
executable file
·565 lines (478 loc) · 23.8 KB
/
progenome-classifier
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
#!/usr/bin/env python
from __future__ import division
import os
import errno
import sys
import argparse
import shlex
import shutil
import time
import subprocess
import glob
import multiprocessing
import tempfile
from collections import Counter
# position of the script -------------------------------------------------------
path_DB = os.path.realpath(__file__)
path_array = path_DB.split("/")
relative_path = "/".join(path_array[0:-1])
relative_path = relative_path + "/"
# check if setup.py has been ran already ---------------------------------------
if not(os.path.isdir(relative_path+'specI_DB')):
sys.stderr.write("[E::main] Error: database has not been downloaded. Run setup.py before using the progenomes classifier\n\n")
sys.exit(1)
# ------------------------------------------------------------------------------
# print the help informations
# ------------------------------------------------------------------------------
class CapitalisedHelpFormatter(argparse.HelpFormatter):
def add_usage(self, usage, actions, groups, prefix=None):
if prefix is None:
prefix = ''
return super(CapitalisedHelpFormatter, self).add_usage(usage, actions, groups, prefix)
def msg(name=None):
str_msg = '''
\00
Program: progenome-classifier - a tool for genome taxonomy annotation
Usage: progenome-classifier <fasta_file> [options]
Options:
-t INT number of threads [1]
-v INT verbose level: 1=error, 2=warning, 3=message, 4+=debugging [3]
-o FILE output file name [stdout]
-m FILE save the 10 marker genes [None]
-M FILE save the 10 marker genes and exit [None]
-s short output format (one-line output)
-H print the result in HTML format (used on the progenomes website)
'''
return str_msg
# ------------------------------------------------------------------------------
# function to check if a specific tool exists
def is_tool(name):
try:
devnull = open(os.devnull)
subprocess.Popen([name], stdout=devnull, stderr=devnull).communicate()
except OSError as e:
if e.errno == errno.ENOENT:
return False
return True
# ------------------------------------------------------------------------------
# MAIN
# ------------------------------------------------------------------------------
def main(argv=None):
devnull = open(os.devnull)
parser = argparse.ArgumentParser(usage=msg(), formatter_class=CapitalisedHelpFormatter,add_help=False)
parser.add_argument('fasta_file', action="store", default=None, help='fasta file')
parser.add_argument('-v', action='store', type=int, default=None, dest='verbose', help='Verbose levels')
parser.add_argument('-t', type=int, action="store", dest='threads', default=None, help='Number of threads to be used.')
parser.add_argument('-o', action="store", dest='output', default=None, help='name of output file')
parser.add_argument('-m', action="store", dest='save_10_MGs', default=None, help='save the 10 marker genes')
parser.add_argument('-M', action="store", dest='save_10_MGs_only', default=None, help='save the 10 marker genes, and do not run vsearch')
parser.add_argument('-s', action='store_true', default=None, dest='short_output', help='print the output in only one line')
parser.add_argument('-H', action='store_true', default=None, dest='print_html', help='print the output in html format')
args = parser.parse_args()
# set default for args.verbose
if (args.verbose is None): args.verbose = 3
# set the default
if (args.output is None): args.output = ""
if (args.threads is None): args.threads = 1
if (args.save_10_MGs is None): args.save_10_MGs = ""
if (args.save_10_MGs_only is None): args.save_10_MGs_only = ""
if (args.short_output is None): args.short_output = False
if (args.print_html is None): args.print_html = False
# name fasta file
fasta_name = args.fasta_file.split("/")[-1]
# ---------------------- check general parameters --------------------------
if args.verbose < 1:
sys.stderr.write("[E::main] Error: verbose level (-v) is less than 1\n")
sys.exit(1)
if args.threads < 1:
sys.stderr.write("[E::main] Error: number of threads (-t) is less than 1\n")
sys.exit(1)
# COG that we evaluate
marker_genes = {"COG0012":0, "COG0049":1, "COG0052":2, "COG0048":3, "COG0016":4,
"COG0018":5, "COG0080":6, "COG0088":7, "COG0081":8, "COG0087":9,
"COG0090":10, "COG0085":11, "COG0091":12, "COG0092":13, "COG0093":14,
"COG0094":15, "COG0096":16, "COG0097":17, "COG0098":18, "COG0099":19,
"COG0100":20, "COG0102":21, "COG0103":22, "COG0124":23, "COG0172":24,
"COG0184":25, "COG0185":26, "COG0186":27, "COG0197":28, "COG0200":29,
"COG0201":30, "COG0202":31, "COG0215":32, "COG0256":33, "COG0522":34,
"COG0495":35, "COG0533":36, "COG0525":37, "COG0552":38, "COG0541":39}
# --------------------------------------------------------------------------
# 0. CHECK DEPENDENCIES
# --------------------------------------------------------------------------
# Perl
#if not is_tool("perl --version"):
# sys.stderr.write("[E::main] Error: perl is not in the path. Please install perl.\n")
# sys.exit(1)
# cdbtools
if not is_tool("cdbyank"):
sys.stderr.write("[E::main] Error: cdbtools is not in the path. Please install cdbtools.\n")
sys.exit(1)
# Prodigal
if not is_tool("prodigal"):
sys.stderr.write("[E::main] Error: prodigal is not in the path. Please install prodigal.\n")
sys.exit(1)
# SAMtools
#if not is_tool("samtools"):
# sys.stderr.write("[E::main] Error: samtools is not in the path. Please install samtools.\n")
# sys.exit(1)
# HMMER
if not is_tool("hmmsearch"):
sys.stderr.write("[E::main] Error: hmmsearch is not in the path. Please install HMMER.\n")
sys.exit(1)
# vsearch
if not is_tool("vsearch"):
sys.stderr.write("[E::main] Error: vsearch is not in the path. Please install vsearch.\n")
sys.exit(1)
# --------------------------------------------------------------------------
# 0. CHECK FILE
# --------------------------------------------------------------------------
# check that it is a fasta file
try:
o = open(args.fasta_file,"r")
# check that it starts with ">"
if not(o.readline().startswith(">")):
sys.stderr.write("[E::main] Error. Not a fasta file: "+fasta_name+"\n")
sys.stderr.write(" Fasta file is expected to start with '>'\n")
o.close()
sys.exit(1)
o.close()
except:
sys.stderr.write("[E::main] Error: Cannot open file: "+fasta_name+"\n")
sys.exit(1)
# --------------------------------------------------------------------------
# 1. EXTRACT GENES
# --------------------------------------------------------------------------
# create a temp dir to save the intermediate results
if args.verbose > 2: sys.stderr.write("Extract genes...")
start = time.time()
genes = tempfile.mkdtemp()
# count the number of founded genes
founded_genes = {"COG0012":0, "COG0049":0, "COG0052":0, "COG0048":0, "COG0016":0,
"COG0018":0, "COG0080":0, "COG0088":0, "COG0081":0, "COG0087":0,
"COG0090":0, "COG0085":0, "COG0091":0, "COG0092":0, "COG0093":0,
"COG0094":0, "COG0096":0, "COG0097":0, "COG0098":0, "COG0099":0,
"COG0100":0, "COG0102":0, "COG0103":0, "COG0124":0, "COG0172":0,
"COG0184":0, "COG0185":0, "COG0186":0, "COG0197":0, "COG0200":0,
"COG0201":0, "COG0202":0, "COG0215":0, "COG0256":0, "COG0522":0,
"COG0495":0, "COG0533":0, "COG0525":0, "COG0552":0, "COG0541":0}
find_genes = "python "+ relative_path + 'makePaddedMG.py ' + args.fasta_file
find_genes = find_genes + " " +genes+"/tmp1 tmp2 --padLength 0 --numThreads "+str(args.threads)
if args.verbose > 3:
sys.stderr.write("call: "+find_genes+"\n")
find_genesCMD = shlex.split(find_genes)
if args.verbose > 3:
find_genes_cmd = subprocess.Popen(find_genesCMD)
else:
dummy_file = tempfile.NamedTemporaryFile(mode="w")
find_genes_cmd = subprocess.Popen(find_genesCMD,stdout=dummy_file, stderr=dummy_file)
return_code = find_genes_cmd.wait()
if return_code:
sys.stderr.write("[E::main] Error: extracting genes failed.\n")
sys.exit(1)
# save the genes to a file
genes_temp_file = tempfile.NamedTemporaryFile(delete=False, mode="w")
os.chmod(genes_temp_file.name, 0o644)
if args.verbose > 3:
sys.stderr.write("temp file with genes: "+genes_temp_file.name+"\n")
for i in marker_genes:
file_g = open(genes+"/tmp1/tmp2_markerGenes/"+i+".fna","r")
cont = 1
for k in file_g:
if k.startswith(">"):
genes_temp_file.write(">"+i+"_"+str(cont)+"\n")
cont = cont + 1
founded_genes[i] = founded_genes[i] + 1 # update dict with the number of founded genes
else:
genes_temp_file.write(k)
# close the temp file (but not deleted)
genes_temp_file.flush()
os.fsync(genes_temp_file.fileno())
genes_temp_file.close()
# remove temp dir
shutil.rmtree(os.path.abspath(os.path.join(genes)))
if args.verbose > 4:
sys.stderr.write("\nfounded_genes:\n")
for ii in founded_genes:
sys.stderr.write(str(ii)+": "+str(founded_genes[i])+"\n")
# print time
end_gene_finding = time.time()
if args.verbose > 2: sys.stderr.write(str( float("{0:.2f}".format(end_gene_finding - start)) )+" seconds\n")
# check if we only want to extract the genes and we dont care of vsearch
if args.save_10_MGs_only != "": # save it somewhere
try:
shutil.move(genes_temp_file.name,args.save_10_MGs_only) #It is not atomic if the files are on different filsystems.
except:
sys.stderr.write("[E::main] Error: failed to save the marker genes sequences\n")
os.remove(os.path.abspath(os.path.join(genes_temp_file.name)))
sys.exit(1)
sys.exit(0) # correct and exit
# find how many marker genes have multiple copies
n_MG_multiple_copies = 0
for cog in founded_genes:
if founded_genes[cog] > 1:
n_MG_multiple_copies = n_MG_multiple_copies + 1
## =========================================================================
# if genes are detected, then we map them with vsearch
if sum(founded_genes.values()) != 0:
# --------------------------------------------------------------------------
# 2. MAP GENES TO DATABASE
# --------------------------------------------------------------------------
# now in genes_temp_file.name we have all the extracted genes
if args.verbose > 2: sys.stderr.write("Map genes to specI database...")
start = time.time()
# load COG cutoffs
if args.verbose > 4: sys.stderr.write(" load cutoffs\n")
all_cutoffs = dict()
cutoff_f = open(relative_path+"lib/cutoffs_specI_40MGs_new.txt","r")
for i in cutoff_f:
all_v = i.rstrip().split("\t")
all_cutoffs[all_v[0]] = float(all_v[1])
cutoff_f.close()
vsearch_res = tempfile.NamedTemporaryFile(delete=False, mode="w")
os.chmod(vsearch_res.name, 0o644)
if args.verbose > 3:
sys.stderr.write("temp file with result from vsearch: "+vsearch_res.name+"\n")
map_genes = "vsearch --usearch_global "+genes_temp_file.name+" --db "+relative_path+"specI_DB/progenomes2_40MGs.fasta.gz --id 0.94 --blast6out "+vsearch_res.name+" --minqt 0.7 --maxrejects 10000 --threads "+str(args.threads)
map_genesCMD = shlex.split(map_genes)
if args.verbose > 3:
map_genes_cmd = subprocess.Popen(map_genesCMD)
else:
map_genes_cmd = subprocess.Popen(map_genesCMD,stdout=devnull, stderr=devnull)
return_code = map_genes_cmd.wait()
if return_code:
sys.stderr.write("Error: vsearch failed")
sys.exit(1)
# parse result from vsearch
matches = dict()
all_matched_perc_id = dict()
tp = open(vsearch_res.name,"r")
for i in tp:
vals = i.rstrip().split("\t")
all_matched_perc_id[vals[0]] = vals[2]
i_cog_type = vals[0].split("_")[0]
perc_id = float(vals[2])
if perc_id > all_cutoffs[i_cog_type]:
# add
query = vals[0]
matches[query] = vals[1]
tp.close()
# print time
end_mapping = time.time()
if args.verbose > 2: sys.stderr.write(str( float("{0:.2f}".format(end_mapping - start)) )+" seconds\n")
start = time.time()
# remove file with the results from vsearch
os.remove(os.path.abspath(os.path.join(vsearch_res.name)))
# decide what to do with the genes file
if args.save_10_MGs != "": # save it somewhere
try:
shutil.move(genes_temp_file.name,args.save_10_MGs) #It is not atomic if the files are on different filsystems.
except:
sys.stderr.write("[E::main] Error: failed to save the marker genes sequences\n")
os.remove(os.path.abspath(os.path.join(genes_temp_file.name)))
else: # or delete it
os.remove(os.path.abspath(os.path.join(genes_temp_file.name)))
# --------------------------------------------------------------------------
# 3. FIND CONGRUENCES BETWEEN THE SPECIs
# --------------------------------------------------------------------------
# now in matches we have the specI database ids
if args.verbose > 2: sys.stderr.write("Find assignemnt from genes...")
start = time.time()
# we check from matches the congruences and how to classify the input ---
# find matches
n_agreeing_genes = "-" # percentage of agreeing genes
perc_agreeing_genes = "-" # percentage of agreeing genes
n_mapped_genes = len(matches)
if len(matches) == 0:
best = "No match"
else:
list_founded_speci = list()
for i in matches:
list_founded_speci.append(matches[i].split("#")[-2])
all_tax = dict(Counter(list_founded_speci))
max_agree = max(all_tax.values())
n_max = 0
list_n_max = list()
for i in all_tax:
if all_tax[i] == max_agree:
n_max = n_max + 1
best = "Consistent"
list_n_max.append(i)
if n_max > 1:
best = "Inconsistent"
else:
perc_agreeing_genes = str( ( max_agree/(sum(all_tax.values())) ) * 100 )+"%" # percentage agreeing
n_agreeing_genes = str(max_agree)
# print time
end_assi = time.time()
if args.verbose > 2: sys.stderr.write(str( float("{0:.2f}".format(end_assi - start)) )+" seconds\n")
start = time.time()
## =========================================================================
# if no genes are detected, then no need to run vsearch and map to specI
else:
best = "No genes"
n_mapped_genes = 0
# ARRIVED HERE: we know what type of match it is
n_detected_genes = sum(founded_genes.values())
# if it is consistent, or inconsistent we find the taxonomy
tax_levels_class = ["-","-","-","-","-","-","-","-"]
if best != "No genes" and best != "No match":
# we only need the taxonomy
tax = dict()
f_ref_tax = open(relative_path+"specI_DB/specI_taxonomy.tsv","r")
f_ref_tax.readline() # remove header
for i in f_ref_tax:
all_v = i.rstrip().split("\t")
tax[all_v[0]] = all_v[1:8]
# remove NCBI id
for c in range(7):
tax[all_v[0]][c] = " ".join(tax[all_v[0]][c].split(" ")[1:])
f_ref_tax.close()
# find taxonomy agreement
# we use list_n_max
for i in range(7):
possible_vals = list()
for vv in list_n_max:
possible_vals.append(tax[vv][i])
tax_levels_class[i] = "/".join(list(set(possible_vals)))
# merge the specI
tax_levels_class[7] = "/".join(list(set(list_n_max)))
# Find the accuracy of the assignement
if best != "Consistent":
accuracy_v = "-"
else:
# load the data and check
try:
accu = dict()
f_accu = open(relative_path+"specI_DB/confidence_values.tsv","r")
f_accu.readline() # remove header
for i in f_accu:
all_v = i.rstrip().split("\t")
accu[str(all_v[0])+"-"+str(all_v[1])] = all_v[2]+" %"
f_accu.close()
curr_genes_info = str(n_agreeing_genes)+"-"+str(n_mapped_genes)
if curr_genes_info in accu:
accuracy_v = accu[curr_genes_info]
else:
accuracy_v = "-"
except:
sys.stderr.write("Error while calculating accuracy.\n")
accuracy_v = "-"
# SET UP THE PRINTING ######################################################
# general print
if args.output != "":
outfile = tempfile.NamedTemporaryFile(delete=False, mode="w")
os.chmod(outfile.name, 0o644)
else:
outfile = sys.stdout
# PRINT RESULT IN HTML FORMAT ==============================================
if args.print_html:
outfile.write("<h2>Result</h2>\n")
outfile.write("<strong>kingdom: </strong><em>"+tax_levels_class[0]+"</em><br>\n")
outfile.write("<strong>phylum: </strong><em>"+tax_levels_class[1]+"</em><br>\n")
outfile.write("<strong>class: </strong><em>"+tax_levels_class[2]+"</em><br>\n")
outfile.write("<strong>order: </strong><em>"+tax_levels_class[3]+"</em><br>\n")
outfile.write("<strong>family: </strong><em>"+tax_levels_class[4]+"</em><br>\n")
outfile.write("<strong>genus: </strong><em>"+tax_levels_class[5]+"</em><br>\n")
outfile.write("<strong>species: </strong><em>"+tax_levels_class[6]+"</em><br>\n")
outfile.write("<strong>specI: </strong>")
if tax_levels_class[7] != "-":
link_to_specI = list()
for i in tax_levels_class[7].split("/"):
link_to_specI.append('<a href="http://progenomes.embl.de/index.cgi?search='+i+'">'+i+'</a>')
outfile.write( ("/".join(link_to_specI)) + "<br>\n")
else:
outfile.write("-<br>\n")
outfile.write("<br>\n")
outfile.write("<strong>Annotation:</strong> "+str(best)+"<br>\n")
outfile.write("<strong>Confidence:</strong> "+str(accuracy_v)+"<br>\n")
outfile.write("<br>\n")
outfile.write("<h3>Classification information</h3>\n")
outfile.write("<strong>Number of detected genes:</strong> "+str(n_detected_genes)+"<br>\n")
outfile.write("<strong>Unique marker genes found in multiple copies [chimera?]:</strong> "+str(n_MG_multiple_copies)+"<br>\n")
outfile.write("<strong>Number of mapped genes:</strong> "+str(n_mapped_genes)+"<br>\n")
outfile.write("<strong>Number of agreeing genes:</strong> "+str(n_agreeing_genes)+"<br>\n")
outfile.write("<strong>Percentage of agreeing genes:</strong> "+str(perc_agreeing_genes)+"<br>\n")
outfile.write("<br>\n")
outfile.write("<h3>Single genes classification</h3>\n")
outfile.write("<table>\n")
outfile.write(" <tr>\n")
outfile.write(" <th style=\"text-align:center\">Gene from fasta file</th>\n")
outfile.write(" <th style=\"text-align:center\">SpecI gene</th>\n")
outfile.write(" <th style=\"text-align:center\">Percentage identity</th>\n")
outfile.write(" <tr>\n")
for i in matches:
outfile.write(" <tr>\n")
outfile.write(" <td style=\"text-align:center\">"+i+"</td>\n")
outfile.write(" <td style=\"text-align:center\">"+matches[i]+"</td>\n")
outfile.write(" <td style=\"text-align:center\">"+str(all_matched_perc_id[i])+"</td>\n")
outfile.write(" <tr>\n")
outfile.write("</table>\n")
# PRINT NORMAL RESULT ======================================================
if (not args.print_html) and (not args.short_output):
outfile.write("RESULT\n")
outfile.write("fasta sequence: "+fasta_name+"\n\n")
outfile.write("kingdom: "+tax_levels_class[0]+"\n")
outfile.write("phylum: "+tax_levels_class[1]+"\n")
outfile.write("class: "+tax_levels_class[2]+"\n")
outfile.write("order: "+tax_levels_class[3]+"\n")
outfile.write("family: "+tax_levels_class[4]+"\n")
outfile.write("genus: "+tax_levels_class[5]+"\n")
outfile.write("species: "+tax_levels_class[6]+"\n")
outfile.write("specI: "+tax_levels_class[7]+"\n\n")
outfile.write("Annotation: "+best+"\n")
outfile.write("Confidence: "+accuracy_v+"\n\n")
outfile.write("Classification information\n")
outfile.write("Number of detected genes: "+str(n_detected_genes)+"\n")
outfile.write("Unique marker genes found in multiple copies [chimera?]: "+str(n_MG_multiple_copies)+"\n")
outfile.write("Number of mapped genes: "+str(n_mapped_genes)+"\n")
outfile.write("Number of agreeing genes: "+str(n_agreeing_genes)+"\n")
outfile.write("Percentage of agreeing genes: "+str(perc_agreeing_genes)+"\n\n")
outfile.write("Single genes classification\n")
for i in matches:
outfile.write(i+"\t")
outfile.write(matches[i]+"\t")
outfile.write(str(all_matched_perc_id[i])+"\n")
# PRINT NORMAL RESULT - ONE LINE VERSION ===================================
if (not args.print_html) and args.short_output:
outfile.write(fasta_name+"\t")
outfile.write(tax_levels_class[0]+"\t")
outfile.write(tax_levels_class[1]+"\t")
outfile.write(tax_levels_class[2]+"\t")
outfile.write(tax_levels_class[3]+"\t")
outfile.write(tax_levels_class[4]+"\t")
outfile.write(tax_levels_class[5]+"\t")
outfile.write(tax_levels_class[6]+"\t")
outfile.write(tax_levels_class[7]+"\t")
outfile.write(best+"\t")
outfile.write(accuracy_v+"\t")
outfile.write(str(n_detected_genes)+"\t")
outfile.write(str(n_MG_multiple_copies)+"\t")
outfile.write(str(n_mapped_genes)+"\t")
outfile.write(str(n_agreeing_genes)+"\t")
outfile.write(str(perc_agreeing_genes)) # "\t" will be after
for i in matches:
outfile.write(i+"#")
outfile.write(matches[i]+"#")
outfile.write(str(all_matched_perc_id[i])+"\t")
outfile.write("\n")
# CLOSE UP THE PRINTING ####################################################
if args.output != "":
try:
outfile.flush()
os.fsync(outfile.fileno())
outfile.close()
except:
sys.stderr.write("[E::main] Error: failed to save the output file\n")
sys.exit(1)
try:
#os.rename(outfile.name,output) # atomic operation
shutil.move(outfile.name,args.output) #It is not atomic if the files are on different filsystems.
except:
sys.stderr.write("[E::main] Error: failed to save the output file\n")
sys.stderr.write("[E::main] you can find the file here:\n"+outfile.name+"\n")
sys.exit(1)
return 0 # success
#-------------------------------- run main -------------------------------------
if __name__ == '__main__':
status = main()
sys.exit(status)