# 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=\'/brain/edges/%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=/brain/edges/%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=/brain/edges/%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!')