{
 "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": [
    "# Load data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "cases_csbj = pd.read_csv(\"./Data/Input/DISNET/final_cases_csbj.tsv\", sep='\\t')\n",
    "cases_csbj = cases_csbj.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "triplets_csbj = pd.read_excel(\"./Data/Input/DISNET/triplets_chembl_disnet.xlsx\",engine='openpyxl')\n",
    "triplets_csbj =triplets_csbj.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "triplets_csbj =triplets_csbj.rename(columns={\"Original Condition CUI\": \"disease_id\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "join_csbj = cases_csbj.merge(triplets_csbj,how = \"inner\",on = [\"drug_id\",\"disease_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "join_csbj_diseases = join_csbj[\"New Condition CUI\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "join_csbj_diseases = pd.DataFrame(join_csbj_diseases).drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "join_csbj_diseases =join_csbj_diseases.rename(columns={\"New Condition CUI\": \"disease_id\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. DRUG - GENE - TARGET"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_gen = pd.read_csv('./Data/Input/DISNET/dis_genes.tsv', sep='\\t')\n",
    "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "gen_dise_join = join_csbj_diseases.merge(dis_gen,how = \"inner\",on = \"disease_id\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "drug_gen = pd.read_csv('./Data/Input/DISNET/drug_gen.tsv', sep='\\t')\n",
    "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "gen_dise_join_dru = gen_dise_join.merge(drug_gen,how = \"inner\",on = \"gene_id\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "score_gdas_csbj = gen_dise_join_dru[gen_dise_join_dru[\"drug_id\"]== \"CHEMBL1581\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "score_gdas_csbj.to_csv(\"score_gdas_csbj.tsv\", sep='\\t')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.PATHWAYS"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 2.1 Pathways direct "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_path_direct = pd.read_csv('./Data/Input/DISNET/disease_pathway.tsv', sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "direct_dise_pw = join_csbj_diseases.merge(dis_path_direct,how = \"inner\",on = \"disease_id\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 2.2 Pathways via genes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "dis_gen_pw = pd.read_csv('./Data/Input/DISNET/dis_gen_pw.tsv', sep='\\t')\n",
    "dis_gen_pw = dis_gen_pw.drop([\"Unnamed: 0\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "join_csbj_filter = join_csbj.drop(columns = [\"disease_id\",\"drug_id\",\"gene_id\",\"Original Condition\",\"Drugs\",\"New Condition\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [],
   "source": [
    "join_csbj_filter = join_csbj_filter.rename(columns={\"New Condition CUI\": \"disease_id\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [],
   "source": [
    "pws_via_gen = join_csbj_filter.merge(dis_gen_pw,how = \"inner\",on = [\"disease_id\",\"pathway_id\"])"
   ]
  }
 ],
 "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
}