summaryrefslogtreecommitdiff
path: root/Code/html_network.py
blob: 56296abd101004789cc0184fbf94c19edded3b47 (plain)
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
# Usage: python html_network.py -f edges.txt -r parameter_for_buildRmatrix.txt -c parameter_for_buildCmatrix.txt -n parameter_for_net.txt
# Purpose: make a summary.html plus its associated files (stored in folder edges) given an edge file (edges.txt).  These files will be served as static files online.  The total volumn of these static files can be quite large, as we get one file for each edge.
#
#          This program is used in update_network.py.
#
# Created on 26 Feb 2017, SLCU, Hui
# Last modified 24 Mar 2017, SLCU, Hui
# Last modified 21 Apr 2017, SLCU, Hui [w2ui for regulatee and regulator tables]
# Last modified 19 Jun 2017, SLCU, Hui [changed text_to_dict to fit the updated RNA_SEQ_INFO_DATABASE]
# Last modified 29 Jun 2017, SLCU, Hui [added key 'sample_id' in text_to_dict]
# Last reviewed 01 Fen 2019, Hui [code review]

import sys, os
import networkx as nx # Run this command on MacOS: export PYTHONPATH="/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages
import numpy as np
from optparse import OptionParser
from itertools import islice
import operator
from datetime import datetime
import collections, re, glob
from geneid2name import make_gene_name_AGI_map_dict
from param4net import make_global_param_dict
import re

## Global variables
REGENERATE_ALL_EDGE_FILES  = 'YES'
INDEX_PAGE                 = '../Webapp/static/summary.html' # change
DIR_NAME                   = '../Webapp/static/edges'        # change

RNA_SEQ_INFO_DATABASE   = '../Data/information/rnaseq_info_database.txt'
RNA_SEQ_INFO_DATABASE_JSON   = '../Data/information/rnaseq_info_database.json'
RNA_SEQ_INFO_HTML_PAGE  = 'rnaseqinfo.html'

GENE_ID_TO_GENE_NAME    = '../Data/information/AGI-to-gene-names_v2.txt'
CHIP_SEQ_INFO_HTML_PAGE = 'chipseqinfo.html'

JSON_DIR                = '../Data/history/expr/json'   # move this directory to the same place as this file html_network.py, for gene expression scatterplot
JSON_DIR2               = '../Data/history/bind/json2'  # for displaying binding plots
C3_DIR                  = './depend/c3'
W2UI_DIR                = './depend/w2ui'
C3_FILES                = ['c3.min.css', 'c3.min.js', 'd3.min.js', 'scatterplot.js', 'barchart.js'] # for displaying scatterplots and binding strength
W2UI_FILES              = ['jquery.min.for.w2ui.js', 'w2ui.min.js', 'w2ui.min.css']
ALPHA                   = 0.6 # weight indicating the importance of number of RNA-seq experiments

### my functions

def get_id(s):
    lst = s.split(' ')
    return lst[0]

def get_name(s, agi2name_dict):
    s = s.strip()
    if s == '':
        return '???'
    if s in agi2name_dict:
        name = agi2name_dict[s]
        lst = name.split(';')
        return re.escape(lst[0]) # use json.dumps to escape prime character in 'F3'H'.  Something like {genename:'F3'H'} is invalid in JavaScript.
    else:
        return s

def show_path(G, lst, options):
    s = ''
    n = len(lst)
    count = 0
    for i in range(n-1):
        u = lst[i]
        v = lst[i+1]
        e = G.get_edge_data(u, v)
        padding = ''
        if e['weight'] > 0:
            s += padding + '%s\t(%s,%2.2f)\t-> ' % (u, e['color'], e['weight']) + ('[%s]\n' % (e['condition']) if options.cond==True else '\n')
        else:
            s += padding + '%s\t(%s,%2.2f)\t|| ' % (u, e['color'], e['weight']) + ('[%s]\n' % (e['condition']) if options.cond==True else '\n')
        count += 4
    print(s + v)
    print('')



def not_bad_line(s):
    if s.strip() == '':
        return False
    if 'WARNING' in s:
        return False
    if 'number' in s:
        return False
    if 'Need' in s:
        return False
    if 'Error' in s:
        return False
    if 'Too' in s:
        return False
    if not s.startswith('AT'): # need modification for other organisms
        return False
    return True


def build_network_from_file(fname):
    ''' build the network from the big edge file, edges.txt. '''
    MG = nx.MultiDiGraph(max_rsubset_size=1400) # maximum size of conditionR list

    max_rsize = 0
    
    f = open(fname)
    cond_list = []
    for line in f:
        line = line.strip()
        if not_bad_line(line):
            lst = line.split('\t')
            g1 = lst[0].split()[0] # target gene id
            g2 = lst[1].split()[0] # source gene id
            MG.add_node(g1)
            MG.add_node(g2)
            edge_type = lst[3] # all or mix

            condR_lst = []
            condC_lst = []
            model_fit_measure = '?'
            if len(lst) > 6:
                condR = lst[4]
                condR_lst = lst[4].split()
                condC = lst[5]
                condC_lst = lst[5].split()
                model_fit_measure = lst[6]
                if model_fit_measure == '.' and edge_type == 'mix':
                    model_fit_measure = '-1000.0'  # RNA-seq samples were selected using post.translation.3.  Search '-1000.0' in QUICKSTART.html for more detail.
                if '=' in model_fit_measure: # in early days, the log likelihood field looks like loglik=-1234.2
                    model_fit_measure = model_fit_measure.split('=')[1] # remove 'loglik='

            size_condR = len(condR_lst)
            if size_condR > max_rsize:
                max_rsize = size_condR

            create_date = '20161201' # default 2016-12-01
            if len(lst) > 7: # has date information, date information is the 8th column
                create_date = lst[7]

            metric = float(lst[8])    # appended by update_network.py
            tissue_or_method = lst[9] # appended by update_network.py

            score = float(lst[2]) # strength of various kinds of relationship.
            
            # Not sure why I distinguished 'all' and 'mix', as the add_edge statements are the same.
            if score > 0:
                MG.add_edge(g2, g1, action='>', weight=score, metric=metric, conditionR=condR_lst, conditionC=condC_lst, rmse=model_fit_measure, edge_date=create_date, subset=tissue_or_method)
            elif score < 0:
                MG.add_edge(g2, g1, action='X', weight=score, metric=metric, conditionR=condR_lst, conditionC=condC_lst, rmse=model_fit_measure, edge_date=create_date, subset=tissue_or_method)

    f.close()

    MG.graph['max_rsubset_size'] = max_rsize

    return MG


def get_value(s, delimit):
    ''' Get the value after the first delimit. '''
    lst = s.split(delimit, 1) # split by the first delimit
    return lst[1].strip()


def text_to_dict(fname, ignore_first_line=True):
    ''' fname is RNA_SEQ_INFO_DATABASE (see above).  '''
    if not os.path.exists(fname):
        print('html_network.py: you must provide %s. See parse_ena_xml.py on how to make it.' % (fname))
        sys.exit()

    d = {}
    f = open(fname)
    lines = f.readlines()
    if ignore_first_line == True:
        lines = lines[1:]
    f.close()
    for line in lines:
        line = line.strip()
        lst = line.split('\t')
        run_id = lst[0]
        d[run_id] = {}  # run_id is ENA/SRA run id
        d[run_id]['experiment_id'] = lst[2]
        if len(lst) < 5:
            continue
        d[run_id]['project_id'] = lst[4]
        d[run_id]['sample_id'] = lst[1].split('...')[0]
        d[run_id]['description'] = '\t'.join(lst[5:])
    return d

def get_true_run_id(s):
    s = s[2:] # s looks like R0SRR1548701XX, so 2 is the position of 'S'.
    index = s.find('X')
    if index >= 0:  # we don't need X
        return s[0:index]
    return s

def make_rna_seq_info_dict(fname):
    db_dict = text_to_dict(RNA_SEQ_INFO_DATABASE)
    f = open(fname)
    d = {}
    for line in f:
        line = line.strip()
        if line.startswith('@'):
            run_id = line[1:] # run_id is sth like R0SRR1548701XX
            run_id2 = get_true_run_id(run_id)
            if run_id2 in db_dict:
                d[run_id] = db_dict[run_id2]
            else:
                d[run_id] = {'project_id':'#', 'experiment_id':'#', 'sample_id':'#', 'description':'NA'}
            
    f.close()
    return d


def make_rna_seq_info_html_page(fname, d):
    f = open(fname, 'w')
    f.write('<html><head><style> body {font-family:\"HelveticaNeue-Light\", \"Helvetica Neue Light\", \"Helvetica neue\"} table {table-layout: fixed; width: 800px;}</style></head><body>')
    for k in sorted(d.keys()):
        run_link = 'http://www.ebi.ac.uk/ena/data/view/%s' % (get_true_run_id(k))
        s = '<p><a href=\"%s\" name=\'%s\'>%s</a></p>' % (run_link, k, k)
        d2 = d[k]
        s += '<table>'
        project_link    = 'http://www.ebi.ac.uk/ena/data/view/%s' % (d2['project_id'])
        experiment_link = 'http://www.ebi.ac.uk/ena/data/view/%s' % (d2['experiment_id'])
        biosample_link  = 'http://www.ebi.ac.uk/biosamples/samples/%s' % (d2['sample_id'])
        description     = d2['description']
        s += '<tr> <td><b>%s</b></td> <td><a href=\"%s\">%s</a> / <a href=\"%s\">%s</a> / <a href=\"%s\">%s</a></td>  </tr>' % ('External links', project_link, d2['project_id'], experiment_link, d2['experiment_id'], biosample_link, d2['sample_id'])
        s += '<tr> <td><b>%s</b></td> <td>%s</td> </tr>' % ('Description', description)
        s += '</table><br>\n'
        f.write(s)
    f.write('</body></html>')
    f.close()

def make_chip_seq_info_dict(fname):
    '''  See QUICKSTART.html#parameter-for-buildcmatrix '''
    f = open(fname)
    d = {}
    for line in f:
        line = line.strip()
        if line.startswith('@'):
            experiment_id = line[1:]
            d[experiment_id] = {}
        if line.startswith('PROTEIN_ID'):
            d[experiment_id]['PROTEIN_ID'] = get_value(line, ':')
        if line.startswith('PROTEIN_NAME'):
            d[experiment_id]['PROTEIN_NAME'] = get_value(line, ':')
        if line.startswith('DATA_NAME'):
            d[experiment_id]['DATA_NAME'] = get_value(line, ':')
        if line.startswith('DESCRIPTION'):
            d[experiment_id]['DESCRIPTION'] = get_value(line, ':')
        if line.startswith('LOCATION'):
            d[experiment_id]['LOCATION'] = get_value(line, ':')
        if line.startswith('NOTE'):
            d[experiment_id]['NOTE'] = get_value(line, ':')

    f.close()
    return d


def make_chip_seq_info_html_page(fname, d):
    f = open(fname, 'w')
    f.write('<html><head><style> body {font-family:\"HelveticaNeue-Light\", \"Helvetica Neue Light\", \"Helvetica neue\"} table {table-layout: fixed; width: 800px;}</style></head><body>')
    for k in sorted(d.keys()):
        s = '<p><a name=\'%s\'>%s</a></p>' % (k, k)
        d2 = d[k]
        s += '<table>'
        for k2 in sorted(d2.keys()):
            s += '<tr> <td>%s</td> <td>%s</td> </tr>' % (k2, d2[k2])
        s += '</table><br>\n'
        f.write(s)
    f.write('</body></html>')
    f.close()


def make_link_string_for_cond(s, type):
    ''' s is a string of RNA-seq IDs or ChIP IDs. '''
    lst = s.split()
    result = ''
    for x in lst:
        if type == 'rnaseq':
            path = '%s#%s' % (RNA_SEQ_INFO_HTML_PAGE, x)
        else:
            path = '%s#%s' % (CHIP_SEQ_INFO_HTML_PAGE, x)
        result += '<a href=\'%s\'>%s</a> ' % (path, x)
    return result


def get_chip_signal(s, d):
    ''' extract signal information, and return the words ordered by frequency '''    
    lst = s.split()
    result = ''
    for x in lst:
        if x in d:
            desc = d[x]['DESCRIPTION']
            lst2 = desc.split('\t')
            for y in lst2:
                if y.startswith('SIGNAL='):
                    result += ';' + y[7:] # 7 means after the '=' in 'SIGNAL='
                    break
    return word_freq(result)


def get_chip_phenotype(s, d):
    ''' extract phenotype information, and return the words ordered by frequency '''
    lst = s.split()
    result = ''
    for x in lst:
        if x in d:
            desc = d[x]['DESCRIPTION']
            lst2 = desc.split('\t')
            for y in lst2:
                if y.startswith('PHENOTYPE='):
                    result += ';' + y[10:]  # 10 means after the '=' in 'PHENOTYPE='
                    break
    return word_freq(result)


def word_freq(s): # for ChIP-seq data
    ''' s is string.  return a string of words ordered by frequency '''
    if s == '':
        return ''
    
    lst = s.split(';')
    d = {}
    for x in lst:
        lst2 = x.split()
        for y in lst2:
            #k = y.lower()
            k = y
            k = k.strip(',')
            k = k.strip('.')
            k = k.strip(')')
            k = k.strip('(')            
            if not k.lower() in ['at', 'in', 'to', 'with', ',', '.', ':', '-']: # exclude these words
                if not k in d:
                    d[k] = 1
                else:
                    d[k] += 1

    sorted_tuples =  sorted(d.items(), key=operator.itemgetter(1), reverse=True)
    first_items = [x[0] for x in sorted_tuples]
    return ' '.join(first_items)


def word_freq2(lst): # for RNA-seq data
    ''' s is string.  return a string of words ordered by frequency '''

    if lst == []:
        return ''
    
    d = {}
    for x in lst: # each description
        lst2 = x.split()
        for y in lst2: # each word
            k = y
            k = k.strip(',') # remove superfluous charaters, if any
            k = k.strip('.')
            k = k.strip(')')
            k = k.strip('(')
            k = k.strip(';')            
            if not k.startswith('SRR') and not k.startswith('ERR') and not k.startswith('DRR') and not k.isdigit() and not ':' in k and len(k) > 1 and not k.lower() in ['just', 'library', 'libraries',  'dna', 'nextseq', 'nextseq500', 'sequencing', 'end', 'al;', 'which', 'analyse', 'analyze', 'analyzer', 'whole-genome', 'thus', 'plant', 'plants', 'future', 'such', 'not', 'alone', 'most', 'within', 'into', 'but', 'between', 'we', 'is', 'or', 'also', 'was', 'can', 'be', 'use', 'kit', 'used', 'et', 'al', 'by', 'this', 'the', 'their', 'at', 'in', 'to', 'on', 'with', ',', '.', ':', '-', 'rna-seq', 'rnaseq', 'of', 'hiseq', 'hiseq2000', 'illumina', 'arabidopsis', 'thaliana', 'from', '<br><br>[title]', '<br><br>[description]', 'using', 'were', 'are', 'and', 'under', 'a', 'an', 'one', 'two', 'three', 'as', 'for', 'after', 'none', 'mapping', 'na', 'whole', 'chip-seq', 'paired']: # exclude these strings
                if not k in d:
                    d[k] = 1
                else:
                    d[k] += 1

    sorted_tuples =  sorted(d.items(), key=operator.itemgetter(1), reverse=True)
    first_items = [x[0] + ' (' + str(x[1]) + ')' for x in sorted_tuples]
    return '<br>'.join(first_items)


def word_freq3(lst): # for RNA-seq data, bag-of-words model
    ''' similar to word_freq2, but may be faster  '''
    if lst == []:
        return ''
    
    bow = [collections.Counter(re.findall(r'\w+', s)) for s in lst] # bag of words
    d = sum(bow, collections.Counter()) # frequency of each word
    sorted_tuples = d.most_common(len(d))
    exclude_lst = ['basis', 'requires', 'population', 'resolution', 'via', 'overall', 'elements', 'grown', 'expression', 'appears', 'total', 'have', 'here', 'of', 'just', 'type', 'transcriptomes', 'transcriptome', 'transcriptomic', 'transcription', 'transcriptional', 'report', 'during', 'diversity', 'investigated', 'library', 'per', 'libraries', '2500', '2000', '1210', '1001', '1107', 'dna', 'nextseq', 'nextseq500', 'seq', 'sequencing', 'sequencing;', 'end', 'al;', 'whereas', 'which', 'analyse', 'analyze', 'analyzer', 'quality', 'analysis', 'analyses', 'whole-genome', 'thus', 'plant', 'plants', 'future', 'such', 'not', 'alone', 'most', 'molecular', 'within', 'into', 'but', 'however', 'between', 'we', 'is', 'origin', 'or', 'also', 'was', 'can', 'be', 'been', 'use', 'kit', 'used', 'et', 'al', 'by', 'this', 'that', 'these', 'the', 'their', 'at', 'in', 'to', 'on', 'with', 'mrna', 'rna', 'rnas', 'rna-seq', 'rnaseq', 'of', 'hiseq', 'hiseq2000', 'illumina', 'arabidopsis', 'thaliana', 'from', 'roles', 'title', 'description', 'using', 'were', 'are', 'and', 'unknown', 'under', 'a', 'an', 'one', 'two', 'three', 'as', 'for', 'found', 'after', 'none', 'mapping', 'na', 'whole', 'chip-seq', 'play', 'paired', 'br', 'future', 'rowan', 'study', 'studies', 'may', 'sample', 'truseq', 'until', 'gene', 'genes', 'genetic', 'genome', 'genomes', 'units', 'its', 'yelina', 'data', 'set', 'tube', 'single-base', 'size', 'room', 'along', 'before', 'several', 'less', 'protocol', 'profiling', 'profiles', 'conditions', 'collection', 'complete', 'reveal', 'given', 'ii', 'isolated', 'described', 'describe', 'na', 'worldwide', 'accessions', 'identify', 'identification'] # exclude these words
    first_items = [x[0] + ' (' + str(x[1]) + ')' for x in sorted_tuples if x[1] > 2 and len(x[0]) > 1 and not x[0].startswith('SRR') and not x[0].startswith('ERR') and not x[0].startswith('DRR') and not x[0].isdigit() and not ':' in x[0] and not x[0].lower() in exclude_lst]
    return ' '.join(first_items)




def replace_old_html_page(fname, edge_date):
    ''' If the file fname needs updating, return True.  '''
    if not os.path.exists(fname): # if the file does not exist, it needs updating
        return True

    # Check all files AT2G43790_AT1G03080_0.html,  AT2G43790_AT1G03080_1.html, AT2G43790_AT1G03080_2.html, etc.  If any of them is too old, create a new one.    
    index = fname.rfind('_') 
    if index < 0:
        print('html_network.py: %s has no underscore.' % (fname))
        sys.exit()
    fname_part = fname[:index]
    for fn in glob.glob(os.path.join(fname_part, '*.html')):
        file_date = datetime.fromtimestamp(os.path.getmtime(fn)).strftime('%Y%m%d')
        if int(edge_date) - int(file_date) > 1: # edge_date is at least 1 day newer than edge file date
            return True

    return False


def format_date(s):
    ''' s in the form of 20170419.  Return 2017-04-19 '''
    s = s.strip()
    if len(s) != 8:
        return s
    return s[0:4] + '-' + s[4:6] + '-' + s[6:]


def make_html_page_for_condition(fname, tf_name, target_name, condRstr, condCstr, edge_date, subset): # important page ***

    ### if the page already exists, and its information is up-to-date, then don't create it again (to save time)
    if REGENERATE_ALL_EDGE_FILES == 'NO' and not replace_old_html_page(fname, edge_date):
        return
    
    d3_library =  '<link href=\"./c3.min.css\" rel=\"stylesheet\" /><script src=\"./d3.min.js\"></script><script src=\"./c3.min.js\"></script><script src=\"./scatterplot.js\"></script><script src=\"./barchart.js\"></script>'
    f = open(fname, 'w')
    f.write('<html><head> %s  <style> body {font-family:\"HelveticaNeue-Light\", \"Helvetica Neue Light\", \"Helvetica neue\"} </style></head><body>' % (d3_library))

    ### RNA-seq
    f.write('<h2>RNA-seq experiments</h2>')
    part = os.path.splitext( os.path.basename(fname) )[0] # get file name without extension
    id_lst = part.split('_')
    gene1_file = os.path.join('json', id_lst[0] + '.json') # TF
    gene2_file = os.path.join('json', id_lst[1] + '.json') # target

    f.write('<p>TF is %s %s.  Target is %s %s.  Edge made on %s.  Method: %s.</p>'% (id_lst[0], '' if tf_name == id_lst[0] else tf_name, id_lst[1], '' if target_name == id_lst[1] else target_name, format_date(edge_date), subset))
    cond_lst_str = str(condRstr.split()) # insert to javascript function call code
    rnaseq_info_file = os.path.basename(RNA_SEQ_INFO_DATABASE_JSON)
    s = '<p><a id=\"myLink\" href=\"javascript:void(0);\" onclick=\"drawScatterPlot(\'%s\',\'%s\', \'%s\', %s);\">Click for gene expression scatter-plot</a></p>  <p id=\"chart\"></p>' % (gene1_file, gene2_file, rnaseq_info_file, cond_lst_str)
    f.write(s)

    f.write('<h2>ChIP-seq experiments</h2>')
    gene1_file = os.path.join('json2', id_lst[0] + '.json') # TF
    gene2_file = os.path.join('json2', id_lst[1] + '.json' ) # target
    cond_lst_str = str(condCstr.split())
    s = '<a id=\"myLink2\" href=\"javascript:void(0);\" onclick=\"drawBarChart(\'%s\',%s);\">Click for plot</a>  <p id=\"chart_bind\"></p>' % (gene2_file, cond_lst_str) # display binding strength
    f.write(s)

    global glb_chip_seq_info_dict
    s = get_chip_signal(condCstr, glb_chip_seq_info_dict)
    if s != '':
        f.write('<h3>Signal</h3> <p>Note: words are ordered by frequency.</p>' + '<p>' + s + '</p>')
    else:
        f.write('<h3>Signal</h3>' + '<p>None.</p>')

    s = get_chip_phenotype(condCstr, glb_chip_seq_info_dict)
    f.write('<h3>Phenotype</h3>' + '<p>' + s + '</p>')
    
    f.write('<p>%s</p>' % (make_link_string_for_cond(condCstr, 'chipseq')))
    f.write('</body></html>')   
    f.close()


def make_w2ui_table_page(fname, gene_str, download_str, dict_lst_regulates, dict_lst_regulatedby):
    ''' each element in dict_lst_* must have the form  {'strength': '', 'metric': '', 'geneid': '', 'genename': ''} '''
    start_part = '''
    <html>
      <head>
        <title>%s</title>
        <script src="./jquery.min.for.w2ui.js"></script>
        <script src="./w2ui.min.js"></script>
        <link rel="stylesheet" type="text/css" href="./w2ui.min.css" />    
        <script>
            $(function() {
    ''' % (
        gene_str)
    
    # the first table showing targets of a TF
    grid1 = '''
        $('#grid1').w2grid({ 
            name:'grid1', 
            header:'%s regulates',
            show:{ footer:true, toolbar:true, header:true },
            columns:[	
                { field:'recid', caption:'No.', size:'50px', sortable:true, resizable:true},
                { field:'strength', caption:'Corr', size:'150px', sortable:true, resizable:true, searchable:true },
                { field:'metric', caption:'Metric', size:'150px', sortable:true, resizable:true, searchable:true },
                { field:'geneid', caption:'Gene ID', size:'150px', sortable:true, resizable:true, searchable:true },
                { field:'genename', caption:'Gene name', size:'150px', sortable:true, resizable:true, searchable:true }
            ],
           records: 
    ''' % (
        gene_str)

    grid1 += '[\n'
    i = 1
    for d in dict_lst_regulates:
        grid1 += '    {recid:%d, strength:\'%s\', metric:\'%s\', geneid:\'%s\', genename:\'%s\'},\n' % (i, d['strength'], d['metric'], d['geneid'], d['genename'])
        i += 1
    grid1 = grid1.rstrip('\n').rstrip(',')
    grid1 += ']\n'
    grid1 += '});\n'

    # the second table showing TF's regulators
    grid2 = '''
        $('#grid2').w2grid({ 
            name:'grid2', 
            header:'%s is regulated by',
            show:{ footer:true, toolbar:true, header:true },
            columns:[	
                { field:'recid', caption:'No.', size:'50px', sortable:true, resizable:true},
                { field:'strength', caption:'Corr', size:'150px', sortable:true, resizable:true, searchable:true },
                { field:'metric', caption:'Metric', size:'150px', sortable:true, resizable:true, searchable:true },
                { field:'geneid', caption:'Gene ID', size:'150px', sortable:true, resizable:true, searchable:true },
                { field:'genename', caption:'Gene name', size:'150px', sortable:true, resizable:true, searchable:true }
            ],
           records: 
    ''' % (
        gene_str)

    grid2 += '[\n'
    i = 1
    for d in dict_lst_regulatedby:
        grid2 += '    {recid:%d, strength:\'%s\', metric:\'%s\', geneid:\'%s\', genename:\'%s\'},\n' % (i, d['strength'], d['metric'], d['geneid'], d['genename'])        
        i += 1
    grid2 = grid2.rstrip('\n').rstrip(',')
    grid2 += ']\n'
    grid2 += '});\n'

    end_part = '''
    });
        </script>
      </head>
      <body>
        <div id="grid1" style="position:absolute; left:0px; width:49.9%%; height:99%%;">regulatee table</div>
        <div id="grid2" style="position:absolute; right:0px; width:49.9%%; height:99%%;">regulator table</div>
        <br/>
        <div id="download">%s</div>
      </body>
    </html>
    ''' % (
        download_str)
    
    result = start_part + grid1 + grid2 + end_part

    # minify html 
    lst = re.split(r'\s{2,}', result)
    result = ''.join(lst)
    f = open(fname, 'w')
    f.write(result)
    f.close()


def make_html_page(node, G, fname, agi2name_dict):
    ''' Make html pages for node's successors and predecessors.  '''

    download_str = ''
    gname = get_name(node, agi2name_dict)
    # gene_str include both gene id and gene name (if possible)
    if node.strip() == gname.strip(): # id only
        gene_str = node
    else:
        gene_str = '%s' % (node + ' ' + gname)

    N = G.graph['max_rsubset_size']
    
    predecessors = G.predecessors(node)
    successors = G.successors(node)

    d1 = {}
    d2 = {}

    for n in successors:
        name = n.split()[0] + '.html'
        d = G.get_edge_data(node, n) # n is node's target
        for k in d.keys(): # can have multiple edges between two nodes
            t = d[k]['action']
            t = int(np.abs(d[k]['weight'])*10) * t # edge strength
            R = '  '.join(d[k]['conditionR'])
            C = '  '.join(d[k]['conditionC'])
            RMSE = d[k]['rmse']
            edge_date = d[k]['edge_date']
            subset = d[k]['subset']
            info_page = get_id(node) + '_' + get_id(n) + '_' + str(k) + '.html' # node is TF, n is target
            info_page_path = os.path.join(os.path.dirname(fname), info_page)
            tf_name = get_name(node, agi2name_dict)
            target_name = get_name(n, agi2name_dict)
            #make_html_page_for_condition(info_page_path, tf_name, target_name, R, C, edge_date, subset)  # ***

            d1[info_page] = float(d[k]['metric'])
            display_name = n + ' ' + ('' if target_name == n else target_name)
            d2[info_page] = (t, name, display_name, RMSE)

    # order edges by strength
    regulatee_dict_lst = []
    for tpl in sorted(d1.items(), key=operator.itemgetter(1), reverse=True):        
        k = tpl[0]
        info_page = k
        t = d2[k][0]
        name = d2[k][1]
        n = d2[k][2] # display name
        RMSE = d2[k][3]
        #s1 += '<a href=\'%s\' title=\'%s\'>%s</a> <a href=\'%s\'>%s</a><br/>' % (info_page, RMSE, t.rjust(12, '_'), name, n)
        lst = n.split()
        geneid = lst[0]
        genename = '-'
        if len(lst) > 1:
            genename = lst[1]
        regulatee_dict_lst.append({'strength': '<a href=%s title=%s>%s</a>' % (info_page, RMSE, t.rjust(12, '_')), 'geneid': '<a href=%s>%s</a>' % (name, geneid), 'genename': '%s' % (genename), 'metric': '%4.2f' % (d1[k])})


    d1 = {}
    d2 = {}
    for n in predecessors:
        name = n.split()[0] + '.html'
        d = G.get_edge_data(n, node)
        for k in d.keys():
            t = d[k]['action']
            t = int(np.abs(d[k]['weight'])*10) * t # edge strength
            R = '  '.join(d[k]['conditionR'])
            C = '  '.join(d[k]['conditionC'])
            RMSE = d[k]['rmse']
            edge_date = d[k]['edge_date']
            subset = d[k]['subset']            
            info_page = get_id(n) + '_' + get_id(node) + '_' + str(k) + '.html' # n is TF, node is target
            info_page_path = os.path.join(os.path.dirname(fname), info_page)
            tf_name = get_name(n, agi2name_dict)
            target_name = get_name(node, agi2name_dict)            
            #if not os.path.exists(info_page_path):  # tf->target may already exits, if so don't need to make it again
            #make_html_page_for_condition(info_page_path, tf_name, target_name, R, C, edge_date, subset)  # CHANGE ***

            d1[info_page]  = float(d[k]['metric'])
            display_name = n + ' ' + ('' if tf_name == n else tf_name)
            d2[info_page] = (t, name, display_name, RMSE)

    # order edges by strength
    regulator_dict_lst = []
    for tpl in sorted(d1.items(), key=operator.itemgetter(1), reverse=True):        
        k = tpl[0]
        info_page = k
        t = d2[k][0]
        name = d2[k][1]
        n = d2[k][2]
        RMSE = d2[k][3]
        lst = n.split()
        geneid = lst[0]
        genename = '-'
        if len(lst) > 1:
            genename = lst[1]
        regulator_dict_lst.append({'strength': '<a href=%s title=%s>%s</a>' % (info_page, RMSE, t.rjust(12, '_')), 'geneid': '<a href=%s>%s</a>' % (name, geneid), 'genename': '%s' % (genename), 'metric': '%4.2f' % (d1[k])})

    make_w2ui_table_page(fname, gene_str, download_str, regulatee_dict_lst, regulator_dict_lst) # ***


def num_lines(fname):
    ''' Return number of lines in file fname. '''
    f = open(fname)
    n = len(f.readlines())
    f.close()
    return n


## main program
parser = OptionParser()
parser.add_option('-f', '--file', dest='edge_file', help='edge file', metavar='FILE')
parser.add_option('-r', '--rnaseqinfo', dest='rna_seq_info_file', default='', help='RNA-seq information file', metavar='FILE')
parser.add_option('-c', '--chipseqinfo', dest='chip_seq_info_file', default='', help='ChIP-seq information file', metavar='FILE')
parser.add_option('-n', '--networkpara', dest='network_para_file', default='', help='Network parameter file', metavar='FILE')
parser.add_option('-i', '--includeedgetype', dest='include',  default='all', help='include edge types')
parser.add_option('-s', '--showcondition', dest='cond',  action="store_true", default=False, help='show correlated conditions')
(options, args) = parser.parse_args()

glb_param_dict = make_global_param_dict(options.network_para_file)

agi2name_dict = make_gene_name_AGI_map_dict(glb_param_dict['GENE_ID_AND_GENE_NAME'])

total_num_edges = num_lines(options.edge_file)


# Make summary.html page
G = build_network_from_file(options.edge_file)
if not os.path.isdir(DIR_NAME):
    os.makedirs(DIR_NAME)

# Make RNA-seq information page
if options.rna_seq_info_file != '':
    glb_rna_seq_info_dict = make_rna_seq_info_dict(options.rna_seq_info_file)
    make_rna_seq_info_html_page(os.path.join(DIR_NAME, RNA_SEQ_INFO_HTML_PAGE), glb_rna_seq_info_dict)

# Make ChIP-seq information page
if options.chip_seq_info_file != '':
    glb_chip_seq_info_dict = make_chip_seq_info_dict(options.chip_seq_info_file)
    make_chip_seq_info_html_page(os.path.join(DIR_NAME, CHIP_SEQ_INFO_HTML_PAGE), glb_chip_seq_info_dict)

# Fill in static index page
findex = open(INDEX_PAGE, 'w')
findex.write('<html><head><style> body {font-family:\"HelveticaNeue-Light\", \"Helvetica Neue Light\", \"Helvetica neue\"} table {table-layout: fixed; width: 800px;}</style></head><body>')
curr_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
s = '<h2>All genes considered</h2>'
s +=  '<p>Last updated at %s. A total of %d edges.</p>' % (curr_time, total_num_edges)
for n in sorted(G.nodes()): # for each node in the network, find its neighbours.
    t = n.split()[0] + '.html'
    filepath = os.path.join(DIR_NAME, t)

    successors = list(G.successors(n))
    predecessors = list(G.predecessors(n))

    s1 = ''
    for sn in successors:
        t1 = sn.split()[0] + '.html'
        filepath1 = os.path.join(DIR_NAME.split('/')[-1], t1)
        s1 += '<a href=\'%s\'>%s</a><br>' % (filepath1, sn)

    s2 = ''
    for pn in predecessors:
        t2 = pn.split()[0] + '.html'
        filepath2 = os.path.join(DIR_NAME.split('/')[-1], t2)
        s2 += '<a href=\'%s\'>%s</a><br>' % (filepath2, pn)
    
    s += '<p>Gene:<a href=\'%s\'>%s</a><br>' % (filepath, n)
    s += '<table border=1><tr><td width=400px>Regulated by %d</td><td width=400px>Regulates %d</td></tr>' % (len(predecessors), len(successors))
    s += '<tr> <td valign=\"top\">%s</td> <td valign=\"top\">%s</td></tr>' % (s2, s1)
    s += '</table>'
    s += '</p>'
    s = '<p>Not implemented.</p>' # don't want full-fledged summary.html
    
    make_html_page(n, G, filepath, agi2name_dict)

findex.write(s)
findex.write('</body></html>')
findex.close()

# copy auxiliary folders and files
print('[html_network.py] Copy auxiliary folders and files.')
if os.path.isdir(JSON_DIR):
    cmd = 'cp -r %s %s' % (JSON_DIR, DIR_NAME)
    os.system(cmd)
else:
    print('[WARNING] html_network.py: Omit JSON directory (for displaying gene expression).')

if os.path.isdir(JSON_DIR2):
    cmd = 'cp -r %s %s' % (JSON_DIR2, DIR_NAME)
    os.system(cmd)
else:
    print('[WARNING] html_network.py: Omit JSON directory 2 (for displaying binding).')

if os.path.exists(RNA_SEQ_INFO_DATABASE_JSON):
    cmd = 'cp %s %s' % (RNA_SEQ_INFO_DATABASE_JSON, DIR_NAME)
    os.system(cmd)
else:
    print('[WARNING] html_network.py: %s does not exists. Scatterplots may not work properly.' % (RNA_SEQ_INFO_DATABASE_JSON))

for fname in C3_FILES:
    fpath = os.path.join(C3_DIR, fname)
    if os.path.exists(fpath):
        cmd = 'cp %s %s' % (fpath, DIR_NAME)
        os.system(cmd)
    else:
        print('[WARNING] html_network.py: Omitted %s. Scatter plot may not work without this file. ' % (fpath))

for fname in W2UI_FILES:
    fpath = os.path.join(W2UI_DIR, fname)
    if os.path.exists(fpath):
        cmd = 'cp %s %s' % (fpath, DIR_NAME)
        os.system(cmd)
    else:
        print('[WARNING] html_network.py: Omit %s. Table may not work without this file. ' % (fpath))
        
print('[html_network.py] Done!')