-
Notifications
You must be signed in to change notification settings - Fork 0
/
neural_cell_test_random_sampling.py
executable file
·1407 lines (961 loc) · 37.7 KB
/
neural_cell_test_random_sampling.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
#!/Users/panix/anaconda/bin/python
print "Tic"
from pybrain.structure import FeedForwardNetwork, SigmoidLayer, LinearLayer
from pybrain.structure import FullConnection, LinearConnection
from pybrain.datasets import SupervisedDataSet
from pybrain.utilities import percentError
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.supervised.trainers import RPropMinusTrainer
from pybrain.tools.customxml.networkwriter import NetworkWriter
from pybrain.tools.customxml.networkreader import NetworkReader
import networkx as nx
import collections
import copy
import sys
import random
#import numpy as np
#import matplotlib.pyplot as plt
# First we need a test network
test_g = nx.MultiDiGraph()
# Target gene
test_g.add_node("RV1026", type="gene")
# Regulatory elements
test_g.add_node("RV0102", type="gene,TF")
test_g.add_node("RV3056", type="gene,TF")
test_g.add_node("RV0912", type="gene,TF")
test_g.add_node("RV0007", type="gene,TF")
test_g.add_node("RV0972", type="not_connected")
# Other element to ignore
test_g.add_node("RV3296", type="other")
# Edges including energy value
test_g.add_edges_from([("RV0102","RV1026",{'weight':1}),("RV3056","RV1026",{'weight':3}),("RV0007","RV1026",{'weight':4}),("RV0912","RV1026",{'weight':2}),("RV3296","RV1026")])
# Write to visualize
nx.write_gml(test_g, "test.gml")
#print test_g.edges()
#print test_g["Gene_1"]["TF_1"]["Energy"]
# Done
# Mock test dataset
training_data = []
exp_dataset_1 = {}
exp_dataset_2 = {}
exp_dataset_3 = {}
exp_dataset_4 = {}
exp_dataset_1["RV0102"] = '2'
exp_dataset_1["RV3056"] = '3'
exp_dataset_1["RV0912"] = '2'
exp_dataset_1["RV0007"] = '4'
exp_dataset_1["RV1026"] = '19'
exp_dataset_2["RV0102"] = '5'
exp_dataset_2["RV3056"] = '3'
exp_dataset_2["RV0912"] = '1'
exp_dataset_2["RV0007"] = '1'
exp_dataset_2["RV1026"] = '16'
exp_dataset_3["RV0102"] = '1'
exp_dataset_3["RV3056"] = '4'
exp_dataset_3["RV0912"] = '2'
exp_dataset_3["RV0007"] = '3'
exp_dataset_3["RV1026"] = '20'
exp_dataset_4["RV0102"] = '2'
exp_dataset_4["RV3056"] = '7'
exp_dataset_4["RV0912"] = '11'
exp_dataset_4["RV0007"] = '4'
exp_dataset_4["RV1026"] = '49'
training_data.append(exp_dataset_1)
training_data.append(exp_dataset_2)
training_data.append(exp_dataset_3)
training_data.append(exp_dataset_4)
bias_training_data = []
exp_dataset_1 = {}
exp_dataset_2 = {}
exp_dataset_3 = {}
exp_dataset_4 = {}
exp_dataset_5 = {}
exp_dataset_1["rv0102"] = '1'
exp_dataset_1["rv3056"] = '12'
exp_dataset_1["rv0912"] = '2'
exp_dataset_1["rv0007"] = '5'
exp_dataset_1["rv1026"] = '10'
exp_dataset_2["rv0102"] = '5'
exp_dataset_2["rv3056"] = '3'
exp_dataset_2["rv0912"] = '4'
exp_dataset_2["rv0007"] = '1'
exp_dataset_2["rv1026"] = '19'
exp_dataset_3["rv0102"] = '1'
exp_dataset_3["rv3056"] = '15'
exp_dataset_3["rv0912"] = '6'
exp_dataset_3["rv0007"] = '3'
exp_dataset_3["rv1026"] = '28'
exp_dataset_4["rv0102"] = '2'
exp_dataset_4["rv3056"] = '6'
exp_dataset_4["rv0912"] = '4'
exp_dataset_4["rv0007"] = '4'
exp_dataset_4["rv1026"] = '19'
exp_dataset_5["rv0102"] = '2'
exp_dataset_5["rv3056"] = '6'
exp_dataset_5["rv0912"] = '10'
exp_dataset_5["rv0007"] = '4'
exp_dataset_5["rv1026"] = '46'
bias_training_data.append(exp_dataset_1)
bias_training_data.append(exp_dataset_2)
bias_training_data.append(exp_dataset_3)
bias_training_data.append(exp_dataset_4)
bias_training_data.append(exp_dataset_5)
all_H37Rv_non_TF_genes = ['Rv1979c','Rv1980c','Rv1981c','Rv1982c','Rv1983','Rv1984c','Rv1995','Rv1996','Rv1997','Rv1998c','Rv1999c','Rv2000','Rv2001','Rv2002','Rv2003c','Rv2004c','Rv2005c','Rv2006','Rv2007c','Rv2008c','Rv2009','Rv2010','Rv2011c','Rv2012','Rv2013','Rv2014','Rv2015c','Rv2016','Rv2017','Rv2018','Rv2019','Rv2020c','Rv2021c','Rv2022c','Rv2023A','Rv2023c']
class RPropMinusTrainer_Evolved(RPropMinusTrainer):
def train(self):
""" Train the network for one epoch """
from scipy import sqrt
self.module.resetDerivatives()
errors = 0
ponderation = 0
for seq in self.ds._provideSequences():
e, p = self._calcDerivs(seq)
errors += e
ponderation += p
if self.verbose:
print(("epoch {epoch:6d} total error {error:12.5g} avg weight {weight:12.5g}".format(
epoch=self.epoch,
error=errors / ponderation,
weight=sqrt((self.module.params ** 2).mean()))))
self.module._setParameters(self.descent(self.module.derivs - self.weightdecay * self.module.params))
self.epoch += 1
self.totalepochs += 1
self.total_error = (errors / ponderation)
return errors / ponderation
class gene_Neuron_Cluster:
def __init__(self, gml_path):
self.gml_path = gml_path
self.gml = nx.read_gml(gml_path, relabel=True)
def add_xml_file(self, xml_filepath):
self.xml_filepath = xml_filepath
self.xml = NetworkReader.readFrom(self.xml_filepath)
print 'Number of inputs:' , str(len(self.xml.inputbuffer[0]))
def add_organism(self, organism):
self.organism = organism
def predict_output(self, input_dict):
input_list = input_dict
return self.xml.activate(input_list)
def input_list(self):
#print self.gml.nodes(data=True)
#for node in self.gml.nodes(data=True):
#print '\n'
out_degree_dict = self.gml.out_degree()
in_degree_dict = self.gml.in_degree()
input_nodes = []
for key in out_degree_dict.keys():
if out_degree_dict[key] > 0 and in_degree_dict[key] == 0:
input_nodes.append(key)
#print input_nodes
# Dealing with the gml network
gml_dict = {}
for gml_gene in input_nodes:
edge_weights = []
for g_edge in self.gml[gml_gene]:
edge_weights.append(str(self.gml[gml_gene][g_edge]['weight'])[:6])
gml_dict[gml_gene] = edge_weights
#print gml_dict
#print '\n'
# Dealing with the xml network
xml_dict = {}
for mod in self.xml.modules:
if mod.name == 'Input_layer':
for conn in self.xml.connections[mod]:
#print dir(conn)
#print conn.params
#print len(conn.params)
for cc in range(len(conn.params)):
#print conn.whichBuffers(cc), conn.params[cc]
#print conn.whichBuffers(cc)[0], conn.params[cc]
order_string = str(conn.whichBuffers(cc)[0])
if order_string in xml_dict.keys():
xml_dict[order_string].append(str(conn.params[cc])[:6])
else:
ent_list = [str(conn.params[cc])[:6]]
xml_dict[order_string] = ent_list
#print xml_dict
mapping_dict = {}
for in_gene in gml_dict.keys():
for in_number in xml_dict.keys():
if collections.Counter(gml_dict[in_gene]) == collections.Counter(xml_dict[in_number]):
#print in_gene, in_number
mapping_dict[in_gene] = in_number
return mapping_dict
def parallel_function(f):
def easy_parallize(f, sequence):
""" assumes f takes sequence as input, easy w/ Python's scope """
# See http://scottsievert.github.io/blog/2014/07/30/simple-python-parallelism/
from multiprocessing import Pool
pool = Pool(processes=4) # depends on available cores
result = pool.map(f, sequence) # for i in sequence: result[i] = f(i)
cleaned = [x for x in result if not x is None] # getting results
cleaned = asarray(cleaned)
pool.close() # not optimal! but easy
pool.join()
return cleaned
from functools import partial
return partial(easy_parallize, f)
def pesos_conexiones(n):
for mod in n.modules:
for conn in n.connections[mod]:
print conn
for cc in range(len(conn.params)):
print conn.whichBuffers(cc), conn.params[cc]
def import_training_data(data_path):
training_data = []
data_obj = open(data_path, "r")
if data_path[-3:] == "pcl":
headder = True
unformatted_data = {}
for line in data_obj.readlines():
if headder == True:
headder_list_old = line.split("\t")
headder_list = headder_list_old[:-1]
headder_list.append(headder_list_old[-1].strip())
experiment_count = len(headder_list) - 3
experiment_names = headder_list[-experiment_count:]
headder = False
else:
line_list = line.split("||")
gene_name_list = line_list[0].split()
gene_name = gene_name_list[0]
# Dealing with wrong cases
gene_name = gene_name.lower()
#gene_name = gene_name.replace('RV','Rv')
#gene_name = gene_name.replace('C','c')
val_list_old = line_list[3].split("\t")
val_list = val_list_old[1:-1]
val_list.append(val_list_old[-1].strip())
#print gene_name, val_list, len(val_list)
unformatted_data[gene_name] = val_list
#print unformatted_data
count = 1 # Starts at one because of the 1 used for scaling as the GWEIGHT
for experiment in experiment_names:
experiment_dict = {}
#print experiment
for gene in unformatted_data.keys():
#print gene, unformatted_data[gene][count]
experiment_dict[gene] = unformatted_data[gene][count]
count += 1
training_data.append(experiment_dict)
# Checks
#print headder_list
#print len(headder_list)
#print experiment_count
#print experiment_names
#print training_data[17]['RV0193C']
return training_data
def mean(a):
return sum(a) / len(a)
def check_missing_experiments(list_A):
"For removes the experiments where not all genes were used"
complete = True
for element in list_A:
if len(element) < 1:
complete = False
return complete
def get_nn_details(ann):
for mod in ann.modules:
for conn in ann.connections[mod]:
#print conn
pred_weights = []
for cc in range(len(conn.params)):
pred_weights.append(conn.params[cc])
return pred_weights
def get_sub_list_from_network(origional_network, a_gene, a_label, edge_threshold, *extra_gene_list):
"Return a list of genes to be used in training"
#print full_network.nodes(data=True)
print "Getting input network structure"
print 'For gene: ' + a_gene
print 'For connected nodes with label: ' + a_label
full_network = copy.deepcopy(origional_network)
#print full_network.node[a_gene]
for node in full_network.nodes(data=True):
if node[1]['type'] != a_label and node[0] != a_gene:
#print node[0]
full_network.remove_node(node[0])
#print full_network.nodes(data=True)
'''
# Removed for now so not to remove edges below the threshold. all TFs are thus included
for edge in full_network.edges(data=True):
#print "----->" ,edge
if edge[2]['fold_change'] < abs(edge_threshold):
full_network.remove_edge(edge[0],edge[1])
'''
#print "------------------"
sub_graph = 0
all_nodes_list = []
for con_gene in nx.all_neighbors(full_network, a_gene):
all_nodes_list.append(str(con_gene))
#print sub_graph.nodes(data=True)
#print all_nodes_list
#print set(all_nodes_list)
all_nodes_list = list(set(all_nodes_list))
if len(extra_gene_list) > 0:
needed_input_nodes = len(all_nodes_list)
random_list = []
random_list.append(a_gene)
gene_count = 0
while gene_count < needed_input_nodes:
print random.choice(all_H37Rv_non_TF_genes)
random_list.append(random.choice(all_H37Rv_non_TF_genes))
gene_count += 1
all_nodes_list = random_list
return all_nodes_list
'''
if full_network[a_gene].degree() > 0:
sub_graph = nx.ego_graph(full_network, a_gene, undirected=True)
#print sub_graph.nodes(data=True)
return sub_graph.nodes()
'''
def filter_expression_dataset(gene_list, dataset_list, *low_sig_thres):
""" Primary filtering removes data not needed so the next step is not thrown by other genes values """
filtered_dataset_list = []
#This fitering step needs work, potentially the 'del' function removes the data for all instances
# Also needed if subsiquent step of filtering is to have any real effect
print gene_list
for experiment in dataset_list:
list_genes_only_experiment = {}
for gene in experiment.keys():
#print gene
if gene.lower() in gene_list:
#print gene
#print experiment[gene]
list_genes_only_experiment[gene] = experiment[gene]
filtered_dataset_list.append(list_genes_only_experiment)
#filtered_dataset_list = dataset_list
#print "+++++++++++++++++++++++"
#print filtered_dataset_list
""" Secondary filtering needs revision. perhaps work out the average """
# Are smaller values better? In pcl file it seems that value 1 is no change, and values to either side are change. Therefore the threshold should be a max rather
# The above made a massive difference increasing the accuracy of the nets
if len(low_sig_thres[0]) > 0:
extra_filtered_dataset_list = []
#print 'filtering'
number_of_experiments = 0
for experiment in filtered_dataset_list:
total = 0
num_of_included_readings = 0
for gene in experiment.keys():
if len(experiment[gene]) > 0:
#print "Here"
#print experiment[gene]
#print "End"
abs_experiment = abs(float(experiment[gene]))
total += abs_experiment
num_of_included_readings += 1
print 'total experiment weight'
print total
if num_of_included_readings > 0:
print 'average experiment weight'
average_exp_weight = total / num_of_included_readings
print average_exp_weight
if average_exp_weight < float(low_sig_thres[0]):
extra_filtered_dataset_list.append(experiment)
number_of_experiments += 1
print "number of experiments retained:"
# test this part out (vary cutoff, see effect)
print number_of_experiments
filtered_dataset_list = extra_filtered_dataset_list
return filtered_dataset_list
def ANN_blind_analysis_multi_hidden(a_network, a_gene, a_dataset, boot_val, train_for):
"Creates and trains a network that is created to reflect the structure of the hypothesized network"
regulatory_network = FeedForwardNetwork()
# retrieving needed parameters from the input network
upper_case_data_node_list = get_sub_list_from_network(a_network, a_gene, "TF", 1, all_H37Rv_non_TF_genes)
print upper_case_data_node_list
# to lower case for everything
data_node_list = [x.lower() for x in upper_case_data_node_list]
a_gene = a_gene.lower()
# If the target gene is also a TF, remove it from the list as it will be added
if a_gene in data_node_list: data_node_list.remove(a_gene)
print 'What is in data_node_list:'
print data_node_list
if len(data_node_list) == 0:
print "No connections to " + a_gene + " found."
return [a_gene, '0', '0']
# Check for missing entries in the dataset (DS)
# For the main gene
#print a_gene
#print a_dataset[0].keys()
# Check for missing entries in the dataset (DS)
# For the main gene
if a_gene not in a_dataset[0].keys():
#print 'herp'
return [a_gene, '0', '0']
# For the linked genes
for each_gene in data_node_list:
if each_gene not in a_dataset[0].keys():
data_node_list.remove(each_gene)
if len(data_node_list) == 0:
print "No connections to " + a_gene + " found."
return [a_gene, '0', '0']
print len(data_node_list)
print data_node_list
# Need to add +1 node to the input layer that represents the "other" control variables
# describing network modules to be used
inLayer = LinearLayer(len(data_node_list), name="Input_layer")
hiddenLayer = SigmoidLayer(len(data_node_list) + 1, name="Hidden_sigmoid_layer_1")
hiddenLayer2 = SigmoidLayer(len(data_node_list) + 1, name="Hidden_sigmoid_layer_2")
outLayer = LinearLayer(1, name="Output_layer")
# Adding layers to network
regulatory_network.addInputModule(inLayer)
regulatory_network.addModule(hiddenLayer)
regulatory_network.addModule(hiddenLayer2)
regulatory_network.addOutputModule(outLayer)
# Adding connections between layers
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_hidden2 = FullConnection(hiddenLayer, hiddenLayer2)
hidden2_to_out = FullConnection(hiddenLayer2, outLayer)
regulatory_network.addConnection(in_to_hidden)
regulatory_network.addConnection(hidden_to_hidden2)
regulatory_network.addConnection(hidden2_to_out)
get_nn_details(regulatory_network)
# Other stuff added
regulatory_network.sortModules()
# Formatting the dataset
input_dimention = len(data_node_list)
print "in_dimention = ", input_dimention
DS = SupervisedDataSet( input_dimention, 1 )
# Adding data, there may be a problem with order here where tfs are not always the same... seems ok though
# This may not be the best way, but is needed due to the next for statement
data_node_list.append(a_gene)
print 'node list contains: '
print data_node_list
# An additional filtering step to slim down the dataset and remove low signal data -------------------------------------------< FILTER
a_filtered_dataset = a_dataset
a_filtered_dataset = filter_expression_dataset(data_node_list, a_filtered_dataset, '0.8')
# This is where the ordered dict needs to be used to link the input name to the input node.
for experiment in a_filtered_dataset:
tf_list = []
gene_list = []
tf_labels = []
first_round = True
for TF in data_node_list:
if TF != a_gene:
#print TF, "<---"
tf_list.append(experiment[TF])
if first_round == True:
tf_labels.append(TF)
else:
#print TF, "<---gene"
gene_list.append(experiment[TF])
first_round = False
# View the input data sets
print tf_labels
print tf_list
print gene_list
if (check_missing_experiments(tf_list) == True) and (check_missing_experiments(gene_list) == True):
float_tf_list = [float(i) for i in tf_list]
float_gene_list = [float(i) for i in gene_list]
DS.appendLinked( float_tf_list, float_gene_list )
print "......"
print 'Network before training'
print regulatory_network
#pesos_conexiones(regulatory_network)
print regulatory_network.outputerror
#print DS
# Training
trainer = RPropMinusTrainer_Evolved(regulatory_network, verbose=False)
trainer.setData(DS)
result_list = []
best_run_error = 1000
train_for = int(train_for)
boot_count = 0
while boot_count < boot_val:
print '\n'
print 'Bootstrap round ' + str(boot_count + 1)
trainer.trainEpochs(train_for)
this = get_nn_details(regulatory_network)
# Corrected error
print trainer.total_error
current_run_error = trainer.total_error
print 'Bootstrap round ' + str(boot_count + 1) + ' error: ' + str(current_run_error)
if abs(current_run_error) < abs(best_run_error):
best_run_error = current_run_error
trained_net_filename = a_gene + '_trained_net.xml'
NetworkWriter.writeToFile(regulatory_network, trained_net_filename)
export_to_gml(regulatory_network, tf_labels, a_gene)
#result_list.append(this)
regulatory_network.reset()
regulatory_network.randomize()
trainer = RPropMinusTrainer_Evolved(regulatory_network, verbose=False)
trainer.setData(DS)
boot_count += 1
#print "TF Labels"
#print tf_labels
#print regulatory_network.params
#print inLayer
#print "Pesos Conexiones"
#pesos_conexiones(regulatory_network)
#print dir(regulatory_network)
#print dir(trainer)
#print 'look here'
#print regulatory_network.outputerror
#print '<><><><><>'
#print dir(regulatory_network['SigmoidLayer-7'])
#print '\n'
#print vars(regulatory_network['SigmoidLayer-7'])
#print '\n'
#print regulatory_network['SigmoidLayer-7'].forward
#print regulatory_network['SigmoidLayer-7'].bufferlist
result_list.append(a_gene)
result_list.append(best_run_error)
result_list.append(len(tf_list))
return result_list
def ANN_blind_analysis(a_network, a_gene, a_dataset, boot_val):
"Creates and trains a network that is created to reflect the structure of the hypothesized network"
regulatory_network = FeedForwardNetwork()
# retrieving needed parameters from the input network
upper_case_data_node_list = get_sub_list_from_network(a_network, a_gene, "gene,TF", 1)
# to lower case for everything
data_node_list = [x.lower() for x in upper_case_data_node_list]
a_gene = a_gene.lower()
# If the target gene is also a TF, remove it from the list as it will be added
if a_gene in data_node_list: data_node_list.remove(a_gene)
print 'what is in data_node_list:'
print data_node_list
if len(data_node_list) == 0:
print "No connections to " + a_gene + " found."
return [a_gene, '0', '0']
# Check for missing entries in the dataset (DS)
# For the main gene
#print a_gene
#print a_dataset[0].keys()
# Check for missing entries in the dataset (DS)
# For the main gene
if a_gene not in a_dataset[0].keys():
#print 'herp'
return [a_gene, '0', '0']
# For the linked genes
for each_gene in data_node_list:
if each_gene not in a_dataset[0].keys():
data_node_list.remove(each_gene)
if len(data_node_list) == 0:
print "No connections to " + a_gene + " found."
return [a_gene, '0', '0']
print len(data_node_list)
print data_node_list
# Need to add +1 node to the input layer that represents the "other" control variables
# describing network modules to be used
inLayer = LinearLayer(len(data_node_list), name="Input_layer")
hiddenLayer = SigmoidLayer(len(data_node_list) + 1, name="Hidden_sigmoid_layer_1")
outLayer = LinearLayer(1, name="Output_layer")
# Adding layers to network
regulatory_network.addInputModule(inLayer)
regulatory_network.addModule(hiddenLayer)
regulatory_network.addOutputModule(outLayer)
# Adding connections between layers
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
regulatory_network.addConnection(in_to_hidden)
regulatory_network.addConnection(hidden_to_out)
get_nn_details(regulatory_network)
# Other stuff added
regulatory_network.sortModules()
# Formatting the dataset
input_dimention = len(data_node_list)
print "in_dimention = ", input_dimention
DS = SupervisedDataSet( input_dimention, 1 )
# Adding data, there may be a problem with order here where tfs are not always the same... seems ok though
# This may not be the best way, but is needed due to the next for statement
data_node_list.append(a_gene)
print 'node list contains: '
print data_node_list
# This is where the ordered dict needs to be used to link the input name to the input node.
for experiment in a_dataset:
tf_list = []
gene_list = []
tf_labels = []
first_round = True
for TF in data_node_list:
if TF != a_gene:
#print TF, "<---"
tf_list.append(experiment[TF])
if first_round == True:
tf_labels.append(TF)
else:
#print TF, "<---gene"
gene_list.append(experiment[TF])
first_round = False
# View the input data sets
print tf_labels
print tf_list
print gene_list
if (check_missing_experiments(tf_list) == True) and (check_missing_experiments(gene_list) == True):
float_tf_list = [float(i) for i in tf_list]
float_gene_list = [float(i) for i in gene_list]
DS.appendLinked( float_tf_list, float_gene_list )
print "......"
print 'Network before training'
print regulatory_network
pesos_conexiones(regulatory_network)
print regulatory_network.outputerror
#print DS
# Training
trainer = RPropMinusTrainer_Evolved(regulatory_network, verbose=False)
trainer.setData(DS)
result_list = []
best_run_error = 1000
boot_count = 0
while boot_count < boot_val:
print '\n'
print 'Bootstrap round ' + str(boot_count + 1)
trainer.trainEpochs(500)
this = get_nn_details(regulatory_network)
# Corrected error
print trainer.total_error
current_run_error = trainer.total_error
print 'Bootstrap round ' + str(boot_count + 1) + ' error: ' + str(current_run_error)
if abs(current_run_error) < abs(best_run_error):
best_run_error = current_run_error
trained_net_filename = a_gene + '_trained_net.xml'
NetworkWriter.writeToFile(regulatory_network, trained_net_filename)
export_to_gml(regulatory_network, tf_labels, a_gene)
#result_list.append(this)
regulatory_network.reset()
regulatory_network.randomize()
trainer = RPropMinusTrainer_Evolved(regulatory_network, verbose=False)
trainer.setData(DS)
boot_count += 1
#print "TF Labels"
#print tf_labels
#print regulatory_network.params
#print inLayer
#print "Pesos Conexiones"
#pesos_conexiones(regulatory_network)
#print dir(regulatory_network)
#print dir(trainer)
#print 'look here'
#print regulatory_network.outputerror
#print '<><><><><>'
#print dir(regulatory_network['SigmoidLayer-7'])
#print '\n'
#print vars(regulatory_network['SigmoidLayer-7'])
#print '\n'
#print regulatory_network['SigmoidLayer-7'].forward
#print regulatory_network['SigmoidLayer-7'].bufferlist
result_list.append(a_gene)
result_list.append(best_run_error)
result_list.append(len(tf_list))
return result_list
def ANN_edge_analysis(a_network, a_gene, a_dataset, boot_val):
"Creates and trains a network that is created to reflect the structure of the hypothesized network"
regulatory_network = FeedForwardNetwork()
# retrievingneeded parameters from the input network
data_node_list = get_sub_list_from_network(a_network, a_gene, "gene,TF", 1)
# Need to add +1 node to the input layer that represents the "other" control variables
# describing network modules to be used
inLayer = LinearLayer(len(data_node_list)-1)
#hiddenLayer = LinearLayer(len(data_node_list)-1))
outLayer = LinearLayer(1)
# Adding layers to network
regulatory_network.addInputModule(inLayer)
#regulatory_network.addModule(hiddenLayer)
regulatory_network.addOutputModule(outLayer)
# Adding connections between layers
#in_to_hidden = LinearConnection(inLayer,hiddenLayer)
#hidden_to_out = FullConnection(hiddenLayer, outLayer)
in_to_out = FullConnection(inLayer, outLayer)
#regulatory_network.addConnection(in_to_hidden)
#regulatory_network.addConnection(hidden_to_out)
regulatory_network.addConnection(in_to_out)
get_nn_details(regulatory_network)
# Other stuff added
regulatory_network.sortModules()
# Formatting the dataset
input_dimention = len(data_node_list)-1
print "in_dimention = ", input_dimention
DS = SupervisedDataSet( input_dimention, 1 )
# Adding data, there may be a problem with order here where tfs are not always the same... seems ok though
for experiment in a_dataset:
tf_list = []
gene_list = []
tf_labels = []
for TF in data_node_list:
if TF != a_gene:
#print TF, "<---"
tf_list.append(experiment[TF])
tf_labels.append(TF)
else:
#print TF, "<---gene"
gene_list.append(experiment[TF])
print tf_list
print gene_list
if (check_missing_experiments(tf_list) == True) and (check_missing_experiments(gene_list) == True):
float_tf_list = [float(i) for i in tf_list]
float_gene_list = [float(i) for i in gene_list]
DS.appendLinked( float_tf_list, float_gene_list )
print "......"
print DS
# Training
trainer = BackpropTrainer(regulatory_network, momentum=0.1, verbose=True, weightdecay=0.01)
trainer.setData(DS)
result_list = []
boot_count = 0
while boot_count < boot_val:
#trainer.trainEpochs(1000)
trainer.trainUntilConvergence(validationProportion=0.25)
print regulatory_network
this = get_nn_details(regulatory_network)
result_list.append(this)
regulatory_network.reset()
boot_count += 1