{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Looking up genes by KEGG\n",
    "\n",
    "V quick query for JP, not well documented!\n",
    "https://github.com/monarch-initiative/operations/issues/91#issuecomment-308893761"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from ontobio.ontol_factory import OntologyFactory\n",
    "ofactory= OntologyFactory()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<ontobio.config.Config at 0x108c61a90>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# For SciGraph we need to use a config file that maps the SciGraph\n",
    "# handle onto a URL\n",
    "from ontobio.config import set_config\n",
    "set_config('../conf/config.yaml')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "sgo = ofactory.create('scigraph:data')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['KEGG-path:map00061']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "matches = sgo.search('Fatty acid biosynthesis')\n",
    "matches"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from ontobio.golr.golr_query import GolrAssociationQuery"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "q = GolrAssociationQuery(subject_category='gene', object=matches[0], subject_taxon='NCBITaxon:9606')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "assocs = q.exec()['associations']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "NCBIGene:31 ACACA\n",
      "NCBIGene:27349 MCAT\n",
      "NCBIGene:2194 FASN\n",
      "NCBIGene:55301 OLAH\n",
      "NCBIGene:54995 OXSM\n",
      "NCBIGene:32 ACACB\n"
     ]
    }
   ],
   "source": [
    "for a in assocs:\n",
    "    gene = a['subject']\n",
    "    print(\"{} {}\".format(gene['id'], gene['label']))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}