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
|
#!/bin/env python3
import os
import re
import time
from nltk.tokenize import sent_tokenize
from ratspub_keywords import *
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, genes):
abstracts = os.popen("esearch -db pubmed -query " + query + " | efetch -format uid |fetch-pubmed -path /run/media/hao/PubMed/Archive/ | xtract -pattern PubmedArticle -element MedlineCitation/PMID,ArticleTitle,AbstractText|sed \"s/-/ /g\"").read()
gene_syno=genes.split("|")
symb=gene_syno[0]
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:
for gene in gene_syno:
if findWholeWord(gene)(sent):
sent=re.sub(r'\b(%s)\b' % gene, r'<strong>\1</strong>', sent, flags=re.I)
for drug0 in drug_d:
if findWholeWord(drug_d[drug0])(sent) :
sent=sent.replace("<b>","").replace("</b>","")
sent=re.sub(r'\b(%s)\b' % drug_d[drug0], r'<b>\1</b>', sent, flags=re.I)
out+=symb+"\t"+"drug\t" + drug0+"\t"+pmid+"\t"+sent+"\n"
for add0 in addiction_d:
if findWholeWord(addiction_d[add0])(sent) :
sent=sent.replace("<b>","").replace("</b>","")
sent=re.sub(r'\b(%s)\b' % addiction_d[add0], r'<b>\1</b>', sent, flags=re.I)
out+=symb+"\t"+"addiction\t"+add0+"\t"+pmid+"\t"+sent+"\n"
return(out)
addiction=undic(addiction_d)
drug=undic(drug_d)
out=open("gene_addiction_sentences.tab", "w+")
cnt=0
with open ("./ncbi_gene_symb_syno_name_txid9606_absCnt_sorted_absCnt_sorted_absCnt_sorted.txt", "r") as f:
for line in f:
(genes, abstractCount)=line.strip().split("\t")
if int(abstractCount)>20:
symb=genes.split("|")[0]
print(symb+"-->"+genes)
q="\'(\"" + addiction.replace("|", "\"[tiab] OR \"") + "\") AND (\"" + drug.replace("|", "\"[tiab] OR \"", ) + "\") AND (\"" + genes.replace("|", "\"[tiab] OR \"", ) + "\")\'"
sentences=getSentences(q,genes)
out.write(sentences)
out.close()
os.system("cut -f 1,4 gene_addiction_sentences.tab |uniq |cut -f 1 |uniq -c |sort -rn > topGeneAbstractCount.tab")
|
