biorseo.py
28 KB
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
#!/usr/bin/python3
# coding=utf-8
import sys
import getopt
from scipy import stats
import subprocess
from os import path, makedirs, getcwd, chdir, devnull, remove, walk
import matplotlib.pyplot as plt
from matplotlib import colors
from math import sqrt
from multiprocessing import cpu_count, Manager
import multiprocessing
import ast
from shutil import move
# ================== DEFINITION OF THE PATHS ==============================
# Retrieve Paths from file EditMe
jar3dexec = "/jar3d_2014-12-11.jar"
bypdir = "/byp/src"
biorseoDir = "/biorseo"
HLmotifDir = "/modules/BGSU/HL/3.2/lib"
ILmotifDir = "/modules/BGSU/IL/3.2/lib"
descfolder = "/modules/DESC"
runDir = path.dirname(path.realpath(__file__))
tempDir = "temp/"
# Parse options
try:
opts, args = getopt.getopt(sys.argv[1:], "bc:f:hi:jl:no:O:pt:v", [ "verbose","rna3dmotifs","3dmotifatlas","jar3d","bayespairing","patternmatch","func=",
"help","version","seq=","modules-path=", "first-objective=","output=","theta=",
"interrupt-limit=", "outputf="])
except getopt.GetoptError as err:
print(err)
sys.exit(2)
m = Manager()
running_stats = m.list()
running_stats.append(0) # n_launched
running_stats.append(0) # n_finished
running_stats.append(0) # n_skipped
# ================== CLASSES AND FUNCTIONS ================================
ignored_nt_dict = {}
def is_canonical_nts(seq):
for c in seq[:-1]:
if c not in "ACGU":
if c in ignored_nt_dict.keys():
ignored_nt_dict[c] += 1
else:
ignored_nt_dict[c] = 1
return False
return True
class NoDaemonProcess(multiprocessing.Process):
@property
def daemon(self):
return False
@daemon.setter
def daemon(self, value):
pass
class NoDaemonContext(type(multiprocessing.get_context())):
Process = NoDaemonProcess
class MyPool(multiprocessing.pool.Pool):
# We sub-class multiprocessing.pool.Pool instead of multiprocessing.Pool
# because the latter is only a wrapper function, not a proper class.
def __init__(self, *args, **kwargs):
kwargs['context'] = NoDaemonContext()
super(MyPool, self).__init__(*args, **kwargs)
class Loop:
def __init__(self, header, subsequence, looptype, position):
self.header = header
self.seq = subsequence
self.type = looptype
self.position = position
class InsertionSite:
def __init__(self, loop, csv_line):
# BEWARE : jar3d csv output is crap because of java's locale settings.
# On french OSes, it uses commas to delimit the fields AND as floating point delimiters !!
# Parse with caution, and check what the csv output files look like on your system...
info = csv_line.split(',')
self.loop = loop # the Loop object that has been searched with jar3d
# position of the loop's components, so the motif's ones, in the query sequence.
self.position = loop.position
# Motif model identifier of the RNA 3D Motif Atlas
self.atlas_id = info[2]
# alignment score of the subsequence to the motif model
self.score = int(float(info[4]))
# should the motif model be inverted to fit the sequence ?
self.rotation = int(info[-2])
def __lt__(self, other):
return self.score < other.score
def __gt__(self, other):
return self.score > other.score
class Job:
def __init__(self, command=[], function=None, args=[], how_many_in_parallel=0, priority=1, timeout=None):
self.cmd_ = command
self.func_ = function
self.args_ = args
self.priority_ = priority
self.timeout_ = timeout
if not how_many_in_parallel:
self.nthreads = cpu_count()
elif how_many_in_parallel == -1:
self.nthreads = cpu_count() - 1
else:
self.nthreads = how_many_in_parallel
class RNA:
def __init__(self, header, seq):
self.seq_ = seq
self.header = header
self.length = len(seq)
self.rnasubopt = []
self.biorseoRawA = []
self.biorseoRawB = []
self.biorseoBGSUJAR3DA = []
self.biorseoBGSUJAR3DC = []
self.biorseoBGSUJAR3DD = []
self.biorseoBGSUJAR3DB = []
self.biorseoBayesPairA = []
self.biorseoBayesPairC = []
self.biorseoBayesPairD = []
self.biorseoBayesPairB = []
self.biorseoBGSUBayesPairA = []
self.biorseoBGSUBayesPairC = []
self.biorseoBGSUBayesPairD = []
self.biorseoBGSUBayesPairB = []
class BiorseoInstance:
def __init__(self, opts):
# set default options
self.type = "dpm"
self.modules = "desc"
self.func = 'B'
self.inputfile = ""
self.finalname = ""
self.outputf = ""
self.output = ""
self.jobcount = 0
self.joblist = []
self.mode = 0 # default is single sequence mode
self.forward_options = []
for opt, arg in opts:
if opt == "-h" or opt == "--help":
print( "Biorseo, Bi-Objective RNA Structure Efficient Optimizer\n"
"Bio-objective integer linear programming framework to predict RNA secondary structures by including known RNA modules.\n"
"Developped by Louis Becquey (louis.becquey@univ-evry.fr), 2019\n\n")
print("Usage:\tYou must provide:\n\t1) a FASTA input file with -i,\n\t2) a module type with --rna3dmotifs or --3dmotifatlas"
"\n\t3) one module placement method in { --patternmatch, --jar3d, --bayespairing }\n\t4) one scoring function with --func A, B, C or D")
print()
print("Options:")
print("-h [ --help ]\t\t\tPrint this help message")
print("--version\t\t\tPrint the program version")
print("-i [ --seq=… ]\t\t\tFASTA file with the query RNA sequence")
print("-p [ --patternmatch ]\t\tUse regular expressions to place modules in the sequence")
print("-j [ --jar3d ]\t\t\tUse JAR3D to place modules in the sequence (requires --3dmotifatlas)")
print("-b [ --bayespairing ]\t\tUse BayesPairing to place modules in the sequence")
print("-o [ --output=… ]\t\tFile to summarize the results")
print("-O [ --outputf=… ]\t\tFolder where to output result and temp files")
print("-f [ --func=… ]\t\t\t(A, B, C or D, default is B)"
" Objective function to score module insertions:\n\t\t\t\t (A) insert big modules (B) insert light, high-order modules"
"\n\t\t\t\t (c) insert modules which score well with the sequence\n\t\t\t\t (D) insert light, high-order modules which score well with the sequence."
"\n\t\t\t\t C and D require cannot be used with --patternmatch.")
print("-c [ --first-objective=… ]\t(default 1) Objective to solve in the mono-objective portions of the algorithm."
"\n\t\t\t\t (1) is the module objective given by --func, (2) is the expected accuracy of the structure.")
print("-l [ --limit=… ]\t\t(default 500) Intermediate number of solutions in the Pareto set from which"
"we give up the computation.")
print("-t [ --theta=… ]\t\t(default 0.001) Pairing-probability threshold to consider or not the possibility of pairing")
print("-n [ --disable-pseudoknots ]\tAdd constraints to explicitly forbid the formation of pseudoknots")
print("-v [ --verbose ]\t\tPrint what is happening to stdout")
print("--modules-path=…\t\tPath to the modules data.\n\t\t\t\t The folder should contain modules in the DESC format as output by Djelloul & Denise's"
"\n\t\t\t\t 'catalog' program for use with --rna3dmotifs, or should contain the IL/ and HL/ folders from a release of\n\t\t\t\t the RNA 3D Motif Atlas"
"for use with --3dmotifatlas.\n\t\t\t\t Consider placing these files on a fast I/O device (NVMe SSD, ...)")
print("\nExamples:")
print("biorseo.py -i myRNA.fa -o myResultsFolder/ --rna3dmotifs --patternmatch --func B")
print("biorseo.py -i myRNA.fa -o myResultsFolder/ --3dmotifatlas --jar3d --func B -l 800")
print("biorseo.py -i myRNA.fa --3dmotifatlas --bayespairing --func D")
sys.exit()
elif opt == "-i" or opt == "--seq":
self.inputfile = arg
elif opt == "-O" or opt == "--outputf":
self.outputf = arg # output folder
if self.outputf[1] != '/':
self.outputf = getcwd() + '/' + self.outputf
if self.outputf[-1] != '/':
self.outputf = self.outputf + '/'
elif opt == "-o" or opt == "--output":
self.output = arg # output file
if self.output[1] != '/':
self.output = getcwd() + '/' + self.output
elif opt == "-f" or opt == "--func":
if arg in ['A', 'B', 'C', 'D']:
self.func = arg
else:
raise "Unknown scoring function " + arg
elif opt == "-p" or opt == "--patternmatch":
self.type = "dpm"
elif opt == "-j" or opt == "--jar3d":
self.type = "jar3d"
elif opt == "-b" or opt == "--bayespairing":
self.type = "byp"
elif opt == "--rna3dmotifs":
self.modules = "desc"
elif opt == "--3dmotifatlas":
self.modules = "bgsu"
elif opt == "--modulespath":
HLmotifDir = arg + "/HL/3.2/lib"
ILmotifDir = arg + "/IL/3.2/lib"
descfolder = arg
elif opt == "--version":
subprocess.call([biorseoDir+"/bin/biorseo", "--version"])
exit(0)
elif opt == "-l" or opt == "--interrupt-limit":
self.forward_options.append("-l")
self.forward_options.append(arg)
elif opt == "-v" or opt == "--verbose":
self.forward_options.append("-v")
elif opt == "-n" or opt == "--disable-pseudoknots":
self.forward_options.append("-n")
elif opt == "-t" or opt == "--theta":
self.forward_options.append("-t")
self.forward_options.append(arg)
elif opt == "-c" or opt == "--first-objective":
self.forward_options.append("-c")
self.forward_options.append(arg)
if self.outputf != "":
print("saving files to", self.outputf)
# create jobs
self.list_jobs()
# run them
self.execute_jobs()
# locate the results at the right place
if self.output != "" and self.outputf != "":
for src_dir, dirs, files in walk(tempDir):
dst_dir = src_dir.replace(tempDir, self.outputf, 1)
if not path.exists(dst_dir):
makedirs(dst_dir)
for file_ in files:
src_file = path.join(src_dir, file_)
dst_file = path.join(dst_dir, file_)
if path.exists(dst_file):
# in case of the src and dst are the same file
if path.samefile(src_file, dst_file):
continue
remove(dst_file)
move(src_file, dst_dir)
subprocess.call(["mv", self.outputf+self.finalname.split('/')[-1], self.output])
elif self.output != "":
subprocess.call(["mv", self.finalname, self.output])
elif self.outputf != "":
for src_dir, dirs, files in walk(tempDir):
dst_dir = src_dir.replace(tempDir, self.outputf, 1)
if not path.exists(dst_dir):
makedirs(dst_dir)
for file_ in files:
src_file = path.join(src_dir, file_)
dst_file = path.join(dst_dir, file_)
if path.exists(dst_file):
# in case of the src and dst are the same file
if path.samefile(src_file, dst_file):
continue
remove(dst_file)
move(src_file, dst_dir)
subprocess.call(["rm", "-rf", tempDir]) # remove the temp folder
def enumerate_loops(self, s):
def resort(unclosedLoops):
loops.insert(len(loops)-1-unclosedLoops, loops[-1])
loops.pop(-1)
opened = []
openingStart = []
closingStart = []
loops = []
loopsUnclosed = 0
consecutiveOpenings = []
if s[0] == '(':
consecutiveOpenings.append(1)
consecutiveClosings = 0
lastclosed = -1
previous = ''
for i in range(len(s)):
# If we arrive on an unpaired segment
if s[i] == '.':
if previous == '(':
openingStart.append(i-1)
if previous == ')':
closingStart.append(i-1)
# Opening basepair
if s[i] == '(':
if previous == '(':
consecutiveOpenings[-1] += 1
else:
consecutiveOpenings.append(1)
if previous == ')':
closingStart.append(i-1)
# We have something like (...(
if len(openingStart) and openingStart[-1] == opened[-1]:
# Create a new loop starting with this component.
loops.append([(openingStart[-1], i)])
openingStart.pop(-1)
loopsUnclosed += 1
# We have something like )...( or even )(
if len(closingStart) and closingStart[-1] == lastclosed:
# Append a component to existing multiloop
loops[-1].append((closingStart[-1], i))
closingStart.pop(-1)
opened.append(i)
# Closing basepair
if s[i] == ')':
if previous == ')':
consecutiveClosings += 1
else:
consecutiveClosings = 1
# This is not supposed to happen in real data, but whatever.
if previous == '(':
openingStart.append(i-1)
# We have something like (...) or ()
if len(openingStart) and openingStart[-1] == opened[-1]:
# Create a new loop, and save it as already closed (HL)
loops.append([(openingStart[-1], i)])
openingStart.pop(-1)
resort(loopsUnclosed)
# We have something like )...)
if len(closingStart) and closingStart[-1] == lastclosed:
# Append a component to existing multiloop and close it.
loops[-1].append((closingStart[-1], i))
closingStart.pop(-1)
loopsUnclosed -= 1
resort(loopsUnclosed)
if i+1 < len(s):
if s[i+1] != ')': # We are on something like: ).
# an openingStart has not been correctly detected, like in ...((((((...)))...)))
if consecutiveClosings < consecutiveOpenings[-1]:
# Create a new loop (uncompleted)
loops.append([(opened[-2], opened[-1])])
loopsUnclosed += 1
# We just completed an HL+stem, like ...(((...))).., we can forget its info
if consecutiveClosings == consecutiveOpenings[-1]:
consecutiveClosings = 0
consecutiveOpenings.pop(-1)
else: # There are still several basepairs to remember, forget only the processed ones, keep the others
consecutiveOpenings[-1] -= consecutiveClosings
consecutiveClosings = 0
else: # We are on something like: ))
# we are on an closingStart that cannot be correctly detected, like in ...(((...(((...))))))
if consecutiveClosings == consecutiveOpenings[-1]:
# Append a component to the uncomplete loop and close it.
loops[-1].append((i, i+1))
loopsUnclosed -= 1
resort(loopsUnclosed)
# Forget the info about the processed stem.
consecutiveClosings = 0
consecutiveOpenings.pop(-1)
opened.pop(-1)
lastclosed = i
previous = s[i]
# print(i,"=",s[i],"\t", "consec. Op=", consecutiveOpenings,"Cl=",consecutiveClosings)
return(loops)
def launch_JAR3D_worker(self, loop):
# write motif to a file
modulefolder = tempDir + loop.header[1:] + '/'
if not path.exists(modulefolder):
makedirs(modulefolder)
filename = modulefolder + loop.header[1:]+".fasta"
fasta = open(filename, 'w')
fasta.write('>'+loop.header+'\n'+loop.seq+'\n')
fasta.close()
# Launch Jar3D on it
if loop.type == 'h':
cmd = ["java", "-jar", jar3dexec, loop.header[1:]+".fasta", HLmotifDir+"/all.txt",
loop.header[1:]+".HLloop.csv", loop.header[1:]+".HLseq.csv"]
else:
cmd = ["java", "-jar", jar3dexec, loop.header[1:]+".fasta", ILmotifDir+"/all.txt",
loop.header[1:]+".ILloop.csv", loop.header[1:]+".ILseq.csv"]
nowhere = open(devnull, 'w')
logfile = open(biorseoDir + "/log_of_the_run.sh", 'a')
logfile.write(' '.join(cmd))
logfile.write("\n")
logfile.close()
chdir(modulefolder)
subprocess.call(cmd, stdout=nowhere)
chdir(biorseoDir)
nowhere.close()
# Retrieve results
insertion_sites = []
if loop.type == 'h':
capstype = "HL"
else:
capstype = "IL"
csv = open(modulefolder + loop.header[1:] +".%sseq.csv" % capstype, 'r')
l = csv.readline()
while l:
if "true" in l:
insertion_sites.append(InsertionSite(loop, l))
l = csv.readline()
csv.close()
return insertion_sites
def launch_JAR3D(self, seq_, basename):
rnasubopt_preds = []
# Extracting probable loops from RNA-subopt structures
rna = open(tempDir + basename + ".subopt", "r")
lines = rna.readlines()
rna.close()
for i in range(2, len(lines)):
ss = lines[i].split(' ')[0]
if ss not in rnasubopt_preds:
rnasubopt_preds.append(ss)
HLs = []
ILs = []
for ss in rnasubopt_preds:
loop_candidates = self.enumerate_loops(ss)
for loop_candidate in loop_candidates:
if len(loop_candidate) == 1 and loop_candidate not in HLs:
HLs.append(loop_candidate)
if len(loop_candidate) == 2 and loop_candidate not in ILs:
ILs.append(loop_candidate)
# Retrieve subsequences corresponding to the possible loops
loops = []
for i, l in enumerate(HLs):
loops.append(Loop(">HL%d" % (i+1), seq_[l[0][0]-1:l[0][1]], "h", l))
for i, l in enumerate(ILs):
loops.append(Loop(">IL%d" % (i+1), seq_[l[0][0]-1:l[0][1]]+'*'+seq_[l[1][0]-1:l[1][1]], "i", l))
# Scanning loop subsequences against motif database
pool = MyPool(processes=cpu_count())
insertion_sites = [x for y in pool.map(self.launch_JAR3D_worker, loops) for x in y]
insertion_sites.sort(reverse=True)
# Writing results to CSV file
c = 0
resultsfile = open(biorseoDir + "/" + tempDir+basename+".sites.csv", "w")
resultsfile.write("Motif,Rotation,Score,Start1,End1,Start2,End2\n")
for site in insertion_sites:
if site.score > 10:
c += 1
string = "FOUND with score %d:\t\t possible insertion of motif " % site.score + site.atlas_id
if site.rotation:
string += " (reversed)"
string += (" on " + site.loop.header + " at positions")
resultsfile.write(site.atlas_id+',' +
str(bool(site.rotation))+",%d" % site.score+',')
positions = [','.join([str(y) for y in x]) for x in site.position]
if len(positions) == 1:
positions.append("-,-")
resultsfile.write(','.join(positions)+'\n')
resultsfile.close()
def launch_BayesPairing(self, module_type, seq_, header_):
chdir(bypdir)
cmd = ["python3", "parse_sequences.py", "-seq", biorseoDir + '/' + tempDir +
header_ + ".fa", "-d", module_type, "-interm", "1"]
logfile = open(biorseoDir + "/log_of_the_run.sh", 'a')
logfile.write(" ".join(cmd))
logfile.write("\n")
logfile.close()
out = subprocess.check_output(cmd).decode('utf-8')
BypLog = out.split('\n')
idx = 0
l = BypLog[idx]
while l[:3] != "PUR":
idx += 1
l = BypLog[idx]
insertion_sites = [x for x in ast.literal_eval(l.split(":")[1][1:])]
if module_type == "rna3dmotif":
rna = open(biorseoDir + "/" + tempDir + header_ + ".byp.csv", "w")
else:
rna = open(biorseoDir + "/" + tempDir + header_ + ".bgsubyp.csv", "w")
rna.write("Motif,Score,Start1,End1,Start2,End2...\n")
for i, module in enumerate(insertion_sites):
if len(module):
for (score, positions, sequence) in zip(*[iter(module)]*3):
pos = []
q = -2
for p in positions:
if p-q > 1:
pos.append(q)
pos.append(p)
q = p
pos.append(q)
rna.write(module_type+str(i)+','+str(int(score)))
for (p, q) in zip(*[iter(pos[1:])]*2):
if q > p:
rna.write(','+str(p)+','+str(q))
rna.write('\n')
rna.close()
def execute_job(self, j):
running_stats[0] += 1
if len(j.cmd_):
logfile = open("log_of_the_run.sh", 'a')
logfile.write(" ".join(j.cmd_))
logfile.write("\n")
logfile.close()
print("["+str(running_stats[0]+running_stats[2]) +
'/'+str(self.jobcount)+"]\t"+" ".join(j.cmd_))
r = subprocess.call(j.cmd_, timeout=j.timeout_)
elif j.func_ is not None:
print("["+str(running_stats[0]+running_stats[2])+'/'+str(self.jobcount) +
"]\t"+j.func_.__name__+'('+", ".join([a for a in j.args_])+')')
try:
r = j.func_(*j.args_)
except:
r = 1
pass
running_stats[1] += 1
return r
def execute_jobs(self):
jobs = {}
self.jobcount = len(self.joblist)
for job in self.joblist:
if job.priority_ not in jobs.keys():
jobs[job.priority_] = {}
if job.nthreads not in jobs[job.priority_].keys():
jobs[job.priority_][job.nthreads] = []
jobs[job.priority_][job.nthreads].append(job)
nprio = max(jobs.keys())
for i in range(1,nprio+1):
if not len(jobs[i].keys()): continue
# check the thread numbers
different_thread_numbers = [n for n in jobs[i].keys()]
different_thread_numbers.sort()
for n in different_thread_numbers:
bunch = jobs[i][n]
if not len(bunch): continue
pool = MyPool(processes=n)
pool.map(self.execute_job, bunch)
pool.close()
pool.join()
def list_jobs(self):
# Read fasta file, which can contain one or several RNAs
RNAcontainer = []
if self.outputf != "":
subprocess.call(["mkdir", "-p", self.outputf]) # Create the output folder
subprocess.call(["mkdir", "-p", tempDir]) # Create the temp folder
print("loading file %s..." % self.inputfile)
db = open(self.inputfile, "r")
c = 0
header = ""
seq = ""
while True:
l = db.readline()
if l == "":
break
c += 1
c = c % 2
if c == 1:
if header != "": # This is our second RNA in the fasta file
self.mode = 1 # we switch to batch mode
header = l[1:-1]
if c == 0:
seq = l[:-1].upper()
if is_canonical_nts(seq):
header = header.replace('/', '_').replace('\'','').replace('(','').replace(')','').replace(' ','_').replace('>','')
RNAcontainer.append(RNA(header, seq))
if not path.isfile(tempDir + header + ".fa"):
rna = open(tempDir + header + ".fa", "w")
rna.write(">" + header +'\n')
rna.write(seq +'\n')
rna.close()
db.close()
for nt, number in ignored_nt_dict.items():
print("ignored %d sequences because of char %c" % (number, nt))
tot = len(RNAcontainer)
print("Loaded %d RNAs." % (tot))
# define job list
for instance in RNAcontainer:
executable = biorseoDir + "/bin/biorseo"
fastafile = tempDir+instance.header+".fa"
method_type = ""
ext = ".raw"
priority = 1
if self.type == "jar3d":
ext = ".jar3d"
method_type = "--jar3dcsv"
csv = tempDir + instance.header + ".sites.csv"
# RNAsubopt
self.joblist.append(Job(command=["RNAsubopt", "-i", fastafile, "--outfile="+ instance.header + ".subopt"], priority=1))
self.joblist.append(Job(command=["mv", instance.header + ".subopt", tempDir], priority=2))
# JAR3D
self.joblist.append(Job(function=self.launch_JAR3D, args=[instance.seq_, instance.header], priority=3, how_many_in_parallel=1))
priority = 4
if self.type == "byp":
method_type = "--bayespaircsv"
if self.modules == "desc":
ext = ".byp"
csv = tempDir + instance.header + ".byp.csv"
self.joblist.append(Job(function=self.launch_BayesPairing, args=["rna3dmotif", instance.seq_, instance.header], how_many_in_parallel=-1, priority=1))
elif self.modules == "bgsu":
ext = ".bgsubyp"
csv = tempDir + instance.header + ".bgsubyp.csv"
self.joblist.append(Job(function=self.launch_BayesPairing, args=["3dmotifatlas", instance.seq_, instance.header], how_many_in_parallel=-1, priority=1))
priority = 2
if self.type == "dpm":
method_type = "--descfolder"
csv = descfolder
command = [executable, "-s", fastafile ]
if method_type:
command += [ method_type, csv ]
self.finalname = tempDir + instance.header + ext + self.func
command += [ "-o", self.finalname, "--function", self.func ]
command += self.forward_options
self.joblist.append(Job(command=command, priority=priority, timeout=3600, how_many_in_parallel=3))
BiorseoInstance(opts)