diff options
| -rw-r--r-- | Readme.md | 15 | ||||
| -rwxr-xr-x | topGene_step1_cnt_abstracts.py | 37 |
2 files changed, 52 insertions, 0 deletions
@@ -10,8 +10,23 @@ This app searches PubMed to find sentences that contain the query terms (e.g., g Live searches are conducted through PubMed to get relevant PMIDs, which are then used to retrieve the abstracts from a local archive. The relationships are presented as an interactive cytoscape graph. The nodes can be moved around to better reveal the connections. Clicking on the links will bring up the corresponding sentences in a new browser window. +## top addiction related genes + +0. extract gene symbol, alias and name from NCBI gene_info for taxid 9606. +``` +grep ^9606 ~/Downloads/gene_info |cut -f 3,5,12|sed "s/\t-//"|sed "s/\t/|/2"|sed "s/\t-//"|grep -v ^LOC|grep -v -i pseudogene|sed "s/(|)\// /g" |sort >ncbi_gene_symb_syno_name_txid9606.txt +``` + +1. search PubMed to get a count of these names/alias, with addiction keywords and drug name +2. sort the genes with top counts, retrieve the abstracts and extract sentences with the 1) symbols and alias and 2) one of the keywords. manually check if there are stop words need to be removed. +3. sort the genes based on the number of abstracts with useful sentences. +4. generate the final list, include symbol, alias, and name + ## dependencies * [local copy of PubMed](https://dataguide.nlm.nih.gov/edirect/archive.html) * python flask * python nltk + +## planned +* NLP analysis of the senences (topic modeling, ranking, etc.) diff --git a/topGene_step1_cnt_abstracts.py b/topGene_step1_cnt_abstracts.py new file mode 100755 index 0000000..0880aff --- /dev/null +++ b/topGene_step1_cnt_abstracts.py @@ -0,0 +1,37 @@ +#!/bin/env python3 +import os +import re +import time +from ratspub import * + +def gene_addiction_cnt(gene): + q="\"(" + addiction.replace("|", "[tiab] OR ") + ") AND (" + drug.replace("|", "[tiab] OR ", ) + ") AND (" + gene + ")\"" + count=os.popen('esearch -db pubmed -query ' + q + ' | xtract -pattern ENTREZ_DIRECT -element Count ').read() + if (len(count)==0): + print("pause") + time.sleep(15) + return gene_addiction_cnt(gene) + else: + return (count) + +out=open("gene_addiction_abstract_cnt_result.tab", "w+") + +with open ("./ncbi_gene_symb_syno_name_txid9606.txt", "r") as f: + for line in f: + line=re.sub(r"\)|\(|\[|\]|\*|\'","",line.strip()) + if "\t" in line: + (gene, synostring)=line.strip().split("\t") + if "|" in synostring: + synos=synostring.split("|") + elif len(synostring)>3: + synos=synostring + for syno in synos: + if len(syno)>3: + gene+="|"+syno + else: + gene=line.strip() + gene_q=gene.replace("|", " [tiab] OR ") + gene_q+="[tiab]" + count=gene_addiction_cnt(gene_q) + print(gene+"\t"+count) + out.write(gene+"\t"+count) |