biorseo.py
17.9 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
#!/usr/bin/python3
# coding=utf-8
import sys
import getopt
from scipy import stats
import subprocess
from os import path, makedirs, getcwd, chdir, devnull
import matplotlib.pyplot as plt
from matplotlib import colors
from math import sqrt
from multiprocessing import Pool, cpu_count, Manager
import multiprocessing
import ast
# ================== DEFINITION OF THE PATHS ==============================
# Retrieve Paths from file EditMe
jar3dexec = ""
bypdir = ""
biorseoDir = "."
exec(compile(open(biorseoDir+"/EditMe").read(), '', 'exec'))
runDir = path.dirname(path.realpath(__file__))
outputDir = biorseoDir + "/results/"
HLmotifDir = biorseoDir + "/data/modules/BGSU/HL/3.2/lib"
ILmotifDir = biorseoDir + "/data/modules/BGSU/IL/3.2/lib"
descfolder = biorseoDir + "/data/modules/DESC"
# ================== CLASSES AND FUNCTIONS ================================
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
# We sub-class multiprocessing.pool.Pool instead of multiprocessing.Pool
# because the latter is only a wrapper function, not a proper class.
class MyPool(multiprocessing.pool.Pool):
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
def get_header(self):
return self.header
def subsequence(self):
return self.seq
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, checkFunc=None, checkArgs=[]):
self.cmd_ = command
self.func_ = function
self.args_ = args
self.checkFunc_ = checkFunc
self.checkArgs_ = checkArgs
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 BiorseoInstance:
def __init__(self, argv):
# set default options
self.type = "dpm"
self.modules = "desc"
self.func = 'B'
self.outputf = outputDir
self.jobcount = 0
# Parse options
try:
opts, args = getopt.getopt(
argv, "hil::o:", ["type=", "func=", "modules="])
except getopt.GetoptError:
print("Please provide arguments !")
sys.exit(2)
for opt, arg in opts:
if opt == "-h":
print("biorseo.py -i myRNA.fa -o myRNA.jar3dB --type jar3d --func B")
sys.exit()
elif opt == "-i":
self.inputfile = arg
self.mode = 0 # single sequence mode
elif opt == "-l":
self.inputfile = arg
self.mode = 1 # batch mode
elif opt == "-o":
self.outputf = arg # output file or folder...
elif opt == "--func":
if arg in ['A', 'B', 'C', 'D']:
self.func = arg
else:
raise "Unknown scoring function " + arg
elif opt == "--type":
if arg in ['dpm', 'jar3d', 'byp']:
self.type = arg
else:
raise "Unknown pattern matching method " + arg
elif opt == "--modules":
if arg in ['desc', 'bgsu']:
self.modules = arg
else:
raise "Unsupported module model type " + arg
else:
raise "Unknown option " + opt
if self.mode:
# Create a job manager
self.manager = Manager()
self.running_stats = self.manager.list()
self.running_stats.append(0) # n_launched
self.running_stats.append(0) # n_finished
self.running_stats.append(0) # n_skipped
self.fails = self.manager.list()
# Create the output folder
subprocess.call(["mkdir", "-p", self.outputf])
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
newpath = getcwd()+'/'+loop.header[1:]
if not path.exists(newpath):
makedirs(newpath)
chdir(newpath)
filename = loop.header[1:]+".fasta"
fasta = open(filename, 'w')
fasta.write('>'+loop.get_header()+'\n'+loop.subsequence()+'\n')
fasta.close()
# Launch Jar3D on it
if loop.type == 'h':
cmd = ["java", "-jar", jar3dexec, filename, HLmotifDir+"/all.txt",
loop.header[1:]+".HLloop.csv", loop.header[1:]+".HLseq.csv"]
else:
cmd = ["java", "-jar", jar3dexec, filename, ILmotifDir+"/all.txt",
loop.header[1:]+".ILloop.csv", loop.header[1:]+".ILseq.csv"]
nowhere = open(devnull, 'w')
logfile = open("log_of_the_run.sh", 'a')
logfile.write(' '.join(cmd))
logfile.write("\n")
logfile.close()
subprocess.call(cmd, stdout=nowhere)
nowhere.close()
# Retrieve results
insertion_sites = []
if loop.type == 'h':
capstype = "HL"
else:
capstype = "IL"
csv = open(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()
# Cleaning
chdir("..")
subprocess.call(["rm", "-r", loop.header[1:]])
return insertion_sites
def launch_JAR3D(self, seq_, basename):
rnasubopt_preds = []
# Extracting probable loops from RNA-subopt structures
rna = open(outputDir + 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(outputDir+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.get_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_, basename):
chdir(bypdir)
cmd = ["python3", "parse_sequences.py", "-seq", outputDir +
basename + ".fa", "-d", module_type, "-interm", "1"]
logfile = open("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(outputDir + basename + ".byp.csv", "w")
else:
rna = open(outputDir + basename + ".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):
if j.checkFunc_ is not None:
if j.checkFunc_(*j.checkArgs_):
self.running_stats[2] += 1
print("["+str(self.running_stats[0]+self.running_stats[2]) +
'/'+str(self.jobcount)+"]\tSkipping a finished job")
return 0
self.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(self.running_stats[0]+self.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(self.running_stats[0]+self.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
if r:
self.fails.append(j)
self.running_stats[1] += 1
return r
def check_result_existence(self, datatype, method, function, with_PK, basename):
folder = self.outputf+"PK/" if with_PK else self.outputf+"noPK/"
if datatype == "bgsu":
if method == "jar3d":
extension = ".jar3d"
elif method == "byp":
extension = ".bgsubyp"
else:
raise "Unknown method !"
elif datatype == "desc":
if method == "dpm":
extension = ".raw"
elif method == "byp":
extension = ".byp"
else:
raise "Unknown method !"
else:
raise "Unknown data type !"
return path.isfile(folder + basename + extension + function)
def check_csv_existence(self, datatype, method, basename):
if datatype == "bgsu":
if method == "jar3d":
extension = ".sites.csv"
elif method == "byp":
extension = ".bgsubyp.csv"
else:
raise "Unknown method !"
elif datatype == "desc":
if method == "byp":
extension = ".byp.csv"
else:
raise "You cannot use " + method + " with " + datatype + " data !"
else:
raise "Unknown data type !"
return path.isfile(self.outputf + basename + extension)
if __name__ == "__main__":
BiorseoInstance(sys.argv)