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
|
#!/bin/env python3
from nltk.tokenize import sent_tokenize
import os
import re
from ratspub_keywords import *
global function_d, brain_d, drug_d, addiction_d, brain_query_term, pubmed_path
## turn dictionary (synonyms) to regular expression
def undic(dic):
return "|".join(dic.values())
def findWholeWord(w):
return re.compile(r'\b({0})\b'.format(w), flags=re.IGNORECASE).search
def getSentences(query, gene):
abstracts = os.popen("esearch -db pubmed -query " + query + " | efetch -format uid |fetch-pubmed -path "+ pubmed_path + " | xtract -pattern PubmedArticle -element MedlineCitation/PMID,ArticleTitle,AbstractText|sed \"s/-/ /g\"").read()
out=str()
for row in abstracts.split("\n"):
tiab=row.split("\t")
pmid = tiab.pop(0)
tiab= " ".join(tiab)
sentences = sent_tokenize(tiab)
## keep the sentence only if it contains the gene
for sent in sentences:
if findWholeWord(gene)(sent):
sent=re.sub(r'\b(%s)\b' % gene, r'<strong>\1</strong>', sent, flags=re.I)
out+=pmid+"\t"+sent+"\n"
return(out)
def gene_category(gene, cat_d, query, cat):
#e.g. BDNF, addiction_d, undic(addiction_d) "addiction"
q="\"(" + query.replace("|", " OR ") + ") AND " + gene + "\""
sents=getSentences(q, gene)
out=str()
for sent in sents.split("\n"):
for key in cat_d:
if findWholeWord(cat_d[key])(sent) :
sent=sent.replace("<b>","").replace("</b>","") # remove other highlights
sent=re.sub(r'\b(%s)\b' % cat_d[key], r'<b>\1</b>', sent, flags=re.I) # highlight keyword
out+=gene+"\t"+ cat + "\t"+key+"\t"+sent+"\n"
return(out)
def generate_nodes(nodes_d, nodetype):
# include all search terms even if there are no edges, just to show negative result
json0 =str()
for node in nodes_d:
json0 += "{ data: { id: '" + node + "', nodecolor: '" + nodecolor[nodetype] + "', nodetype: '"+nodetype + "', url:'/shownode?nodetype=" + nodetype + "&node="+node+"' } },\n"
return(json0)
def generate_edges(data, filename):
json0=str()
edgeCnts={}
for line in data.split("\n"):
if len(line.strip())!=0:
(source, cat, target, pmid, sent) = line.split("\t")
edgeID=filename+"|"+source+"|"+target
if edgeID in edgeCnts:
edgeCnts[edgeID]+=1
else:
edgeCnts[edgeID]=1
for edgeID in edgeCnts:
(filename, source,target)=edgeID.split("|")
json0+="{ data: { id: '" + edgeID + "', source: '" + source + "', target: '" + target + "', sentCnt: " + str(edgeCnts[edgeID]) + ", url:'/sentences?edgeID=" + edgeID + "' } },\n"
return(json0)
def searchArchived(sets, query):
if sets=='topGene':
dataFile="topGene_addiction_sentences.tab"
nodes= "{ data: { id: '" + query + "', nodecolor: '" + "#2471A3" + "', fontweight:700, url:'/progress?query="+query+"' } },\n"
elif sets=='gwas':
dataFile="gwas_addiction.tab"
nodes=str()
with open(dataFile, "r") as sents:
catCnt={}
for sent in sents:
(symb, cat0, cat1, pmid, sent)=sent.split("\t")
if (symb.upper() == query.upper()) :
if cat1 in catCnt.keys():
catCnt[cat1]+=1
else:
catCnt[cat1]=1
nodes= "{ data: { id: '" + query + "', nodecolor: '" + "#2471A3" + "', fontweight:700, url:'/progress?query="+query+"' } },\n"
edges=str()
for key in catCnt.keys():
if sets=='gwas':
nc=nodecolor["gwas"]
nodes += "{ data: { id: '" + key + "', nodecolor: '" + nc + "', url:'https://www.ebi.ac.uk/gwas/search?query="+key.replace("_GWAS","")+"' } },\n"
elif key in drug_d.keys():
nc=nodecolor["drug"]
nodes += "{ data: { id: '" + key + "', nodecolor: '" + nc + "', url:'/shownode?node="+key+"' } },\n"
else:
nc=nodecolor["addiction"]
nodes += "{ data: { id: '" + key + "', nodecolor: '" + nc + "', url:'/shownode?node="+key+"' } },\n"
edgeID=dataFile+"|"+query+"|"+key
edges+="{ data: { id: '" + edgeID+ "', source: '" + query + "', target: '" + key + "', sentCnt: " + str(catCnt[key]) + ", url:'/sentences?edgeID=" + edgeID + "' } },\n"
return(nodes+edges)
# brain region has too many short acronyms to just use the undic function, so search PubMed using the following
brain_query_term="cortex|accumbens|striatum|amygadala|hippocampus|tegmental|mesolimbic|infralimbic|prelimbic|habenula"
function=undic(function_d)
addiction=undic(addiction_d)
drug=undic(drug_d)
nodecolor={'function':"#A9CCE3", 'addiction': "#D7BDE2", 'drug': "#F9E79F", 'brain':"#A3E4D7", 'gwas':"#AEB6BF", 'stress':"#EDBB99", 'psychiatric':"#F5B7B1"}
#https://htmlcolorcodes.com/ third column down
n0=generate_nodes(function_d, 'function')
n1=generate_nodes(addiction_d, 'addiction')
n2=generate_nodes(drug_d, 'drug')
n3=generate_nodes(brain_d, 'brain')
n4=generate_nodes(stress_d, 'stress')
n5=generate_nodes(psychiatric_d, 'psychiatric')
default_nodes=n0+n1+n2+n3+n4+n5
host= os.popen('hostname').read().strip()
if host=="x1":
pubmed_path="/run/media/hao/PubMed/Archive/"
elif host=="hchen3":
pubmed_path="/media/hao/2d554499-6c5b-462d-85f3-5c49b25f4ac8/PubMed/Archive"
elif host=="penguin2":
pubmed_path="/export2/PubMed/Archive"
|
