{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sqlalchemy import create_engine\n",
    "from sklearn import preprocessing\n",
    "import mysql.connector\n",
    "from pandas import DataFrame"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "duples_repodb = pd.read_csv(\"./Data/Input/Drug Repurposing/repoDB_all_disdru.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "duples_csbj = pd.read_csv(\"./Data/Input/Drug Repurposing/duplas_CSBJ.tsv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "duples_csbj = duples_csbj.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "duples_csbj = duples_csbj.rename(columns={\"Disease CUI\": \"disease_id\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_path_direct = pd.read_csv('./Data/Input/DISNET/disease_pathway.tsv', sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "drug_gen = pd.read_csv('./Data/Input/DISNET/drug_gen.tsv', sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_gen = pd.read_csv('./Data/Input/DISNET/dis_genes_gda.tsv', sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_gen_sinfil = pd.read_csv('./Data/Input/DISNET/dis_genes.tsv', sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_gen_sinfil = dis_gen_sinfil.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### JOIN REPODB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_path = duples_repodb.merge(dis_path_direct, how='inner', on='disease_id')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_path_fil = dis_drug_path.drop([\"pathway_id\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_path_fil = dis_drug_path_fil.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_gen = dis_gen.merge(drug_gen, how =\"inner\", on = \"gene_id\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_gen = dis_drug_gen.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_original = dis_drug_path_fil.merge(dis_drug_gen, how = \"outer\", on =[\"disease_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug =dis_drug_original.drop_duplicates()[['disease_id','drug_id']].drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb_gda = duples_repodb.merge(dis_drug,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb_gda.to_csv(\"cases_repodb_gda.tsv\", sep =\"\\t\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### JOIN CSBJ"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_path_csbj = duples_csbj.merge(dis_path_direct , how = \"inner\", on = \"disease_id\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_path_csbj_fil = dis_drug_path_csbj.drop([\"pathway_id\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_original_csbj = dis_drug_path_csbj_fil.merge(dis_drug_gen, how = \"outer\", on =[\"disease_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_csbj =dis_drug_original_csbj.drop_duplicates()[['disease_id','drug_id']].drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj = duples_csbj.merge(dis_drug_csbj,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj.to_csv(\"cases_csbj.tsv\", sep=\"\\t\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Join pathway-disease with pathway-drug"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb = pd.read_csv(\"./Data/Input/DISNET/cases_repodb_gda.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "55"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(cases_repodb[\"disease_id\"].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(cases_repodb[\"disease_id\"].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_path_num = dis_drug_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "51"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(dis_drug_path_num[\"disease_id\"].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "drug_gen_pw = pd.read_csv(\"./Data/Input/DISNET/drug_gen_pw.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "drug_gen_pw = drug_gen_pw.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## 1º Join pws-based DR cases with their pathways"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "pw_based_DR_pw = cases_repodb.merge(dis_drug_path_num,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "51"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(pw_based_DR_pw[\"disease_id\"].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## 2º Join with drug and pathway-target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "final = pw_based_DR_pw.merge(drug_gen_pw,how = \"inner\",on = [\"pathway_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_cases_repodb =final.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_drug_path_num = dis_drug_path_num.groupby(['disease_id', 'drug_id']).count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_cases_repodb.to_csv(\"final_cases_repodb.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_cases_repodb = pd.read_csv(\"./Data/Input/DISNET/final_cases_repodb.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj = pd.read_csv(\"./Data/Input/DISNET/cases_csbj_gda.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj = cases_csbj.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "pw_based_DR_pw_csbj = cases_csbj.merge(dis_drug_path_num,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_csbj = pw_based_DR_pw_csbj.merge(drug_gen_pw,how = \"inner\",on = [\"pathway_id\",\"drug_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_csbj.to_csv(\"final_cases_csbj.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. Number of pathways shared between disease and drug "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj = pd.read_csv(\"./Data/Input/DISNET/final_cases_csbj.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj = cases_csbj.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj_num = cases_csbj.groupby(['disease_id', 'drug_id']).count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb = pd.read_csv(\"./Data/Input/DISNET/final_cases_repodb.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb = cases_repodb.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb_pw = cases_repodb.drop([\"gene_id\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb_pw = cases_repodb_pw.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb_pw_num = cases_repodb_pw.groupby(['disease_id', 'drug_id']).count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb_pw_num.to_csv(\"cases_repodb_pw_num.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_repodb_pw_num = pd.read_csv(\"./Data/Input/DISNET/cases_repodb_pw_num.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.4565217391304348"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cases_repodb_pw_num[\"pathway_id\"].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pathway_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>46.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.456522</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.503610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       pathway_id\n",
       "count   46.000000\n",
       "mean     1.456522\n",
       "std      0.503610\n",
       "min      1.000000\n",
       "25%      1.000000\n",
       "50%      1.000000\n",
       "75%      2.000000\n",
       "max      2.000000"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cases_repodb_pw_num.describe()"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}