Introduction

Entrez Summary is available from http://www.ncbi.nlm.nih.gov/sites/entrez

Details

A ruby script was used. It reads a file "geneIDs.txt" that is generated from a simple generif query:

select distinct(geneID) from generif order by geneid;

The package REXML was used to parse xml.

#!/usr/bin/env ruby
require 'net/http'
require 'rexml/document'
include REXML
host = "eutils.ncbi.nlm.nih.gov"  
path = "/entrez/eutils/efetch.fcgi?db=gene&tool=genequad&retmode=xml&id="
http = Net::HTTP.new(host)

myIDs = File.open("geneIDs.txt").read

myIDs.each{ |line|
	id = line.strip
	response, = http.get(path + id)
	result = response.body
	doc = Document.new(result)
	root = doc.root
	geneID =  root.elements[1].elements[1].elements[1].elements[1].to_a[0]
	description = root.elements[1].elements[6].to_a[0]
	puts "GeneID" 
	puts geneID
	puts description
}

This .cpp was used to get the results. In the future, it will insert the data in a table in the database.

#include <stdio.h>
#include <iostream>
#include <fstream>
#include <string>

using namespace std;

int main(){
  ifstream in("temp.txt");
  string s;
  int count=0;
  int fileID=0;
  getline(in,s);
  while(s=="GeneID"){
    getline(in,s);
    printf("GeneId = %s\n",s.c_str());
    getline(in,s);
    printf("Description = %s\n\n",s.c_str());
    while(getline(in,s)){
      if(s=="GeneID") break;
    }
  }
}