{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import json\n",
    "# import os\n",
    "\n",
    "# # Read in the organ to conditions mapping JSON file\n",
    "# with open(\"clin-oracle-tahoe-hack-2025/data/organ_to_conditions_mapping.json\", \"r\") as f:\n",
    "#     organ_to_conditions = json.load(f)\n",
    "    \n",
    "# # Display basic information about the mapping\n",
    "# print(f\"Loaded organ to conditions mapping with {len(organ_to_conditions)} organs\")\n",
    "# print(f\"Sample organ: {list(organ_to_conditions.keys())[0]}\")\n",
    "# print(f\"Sample conditions: {organ_to_conditions[list(organ_to_conditions.keys())[0]][:3]}...\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "drug_metadata = pd.DataFrame(load_dataset(\"tahoebio/Tahoe-100M\",\"drug_metadata\", split=\"train\"))\n",
    "drug_metadata = drug_metadata.loc[drug_metadata[\"targets\"].notna()]\n",
    "target_to_drug = dict(zip(drug_metadata[\"targets\"], drug_metadata[\"drug\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"/home/ubuntu/tahoe/clin-oracle-tahoe-hack-2025/indication_to_organ_mapping_confident.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "indic = pd.read_csv(\"genetic_support/data/indic.tsv\", sep='\\t')\n",
    "assoc = pd.read_csv(\"genetic_support/data/assoc.tsv.gz\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "assoc = assoc.merge(df, left_on=\"mesh_term\", right_on=\"indication_mesh_term\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "189"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(target_to_drug)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "assoc[\"drug\"] = assoc[\"gene\"].map(target_to_drug)\n",
    "assoc[\"drug_organ\"] = assoc[\"drug\"] + \"_\" + assoc[\"organ\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "assoc = assoc.loc[assoc[\"drug_organ\"].notna()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "assoc[[\"drug_organ\",]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "arow                                                                 3885\n",
       "gene                                                                 ABL1\n",
       "mesh_id                                                           D014012\n",
       "source                                                                OTG\n",
       "original_trait          Tinnitus / tiniitis | non-cancer illness code,...\n",
       "original_link           https://genetics.opentargets.org/study/NEALE2_...\n",
       "extra_info                                                            NaN\n",
       "l2g_rank                                                              4.0\n",
       "l2g_share                                                            0.12\n",
       "pval                                                                  0.0\n",
       "year                                                               2018.0\n",
       "beta                                                                  NaN\n",
       "odds_ratio                                                       4.072184\n",
       "pic_qtl_pval                                                          NaN\n",
       "pic_h4                                                                NaN\n",
       "af_gnomad_nfe                                                     0.02489\n",
       "mesh_term                                                        Tinnitus\n",
       "indication_mesh_term                                             Tinnitus\n",
       "organ                                                           CNS/Brain\n",
       "drug                                                Flumatinib (mesylate)\n",
       "drug_organ                                Flumatinib (mesylate)_CNS/Brain\n",
       "Name: 234, dtype: object"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "assoc.iloc[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "assoc[\"is_associated_with_indication\"] = 1\n",
    "assoc[[\"drug_organ\",\"is_associated_with_indication\"]].to_csv(\"/home/ubuntu/tahoe/clin-oracle-tahoe-hack-2025/data_for_classifier/assoc_drug_organ_label.tsv\", sep='\\t', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.12.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}