final code

.ipynb_checkpoints/6.1 Triplets with target- genes-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "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\n",
+    "from sklearn.metrics import jaccard_score\n",
+    "from numpy import logical_and as l_and, logical_not as l_not"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_dummies(data,col_index,col_col):\n",
+    "    \n",
+    "    df_final= pd.get_dummies(data.set_index(col_index),col_col).reset_index()\n",
+    "    df_final=df_final.drop_duplicates()\n",
+    "    df_final=df_final.groupby(col_index).sum().reset_index()\n",
+    "    \n",
+    "    return df_final\n",
+    "\n",
+    "def convert(lista):\n",
+    "    return tuple(i for i in lista)\n",
+    "\n",
+    "\n",
+    "def get_normal_diseases(rare_disease):\n",
+    "    '''\n",
+    "    Esta funcion devuelve un dataframe con la enfermedad, los medicamentos y los targets que son utiles\n",
+    "    para la enfermedad rara que se le pase como parametro'''\n",
+    "    \n",
+    "    \n",
+    "    q= f'''SELECT DISTINCT\n",
+    "        ds.disease_id, drug_name,dg.gene_id\n",
+    "        FROM\n",
+    "        disnet_biolayer.disease_gene dg \n",
+    "            JOIN disnet_biolayer.disease ds ON ds.disease_id = dg.disease_id\n",
+    "            JOIN disnet_biolayer.encodes e ON dg.gene_id = e.gene_id\n",
+    "            JOIN disnet_drugslayer.target_has_code hc ON hc.code_id = e.protein_id\n",
+    "            JOIN disnet_drugslayer.drug_target dt ON hc.target_id = dt.target_id\n",
+    "            JOIN disnet_drugslayer.drug d ON dt.drug_id = d.drug_id\n",
+    "        WHERE\n",
+    "            \n",
+    "            ds.ddf_type = \"disease\"\n",
+    "        AND dg.gene_id in (SELECT distinct(gene_id) FROM disnet_biolayer.disease_gene\n",
+    "        where disease_id = \"{rare_disease}\")\n",
+    "        ;'''\n",
+    "    \n",
+    "    df = pd.read_sql(q, con=disnet_db_ares)\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rare_diseases= ['C0011195', 'C0023944', 'C0024054', 'C0024901', 'C0027877', 'C0036391', 'C0265202', 'C0268059', \n",
+    "                'C0549463', 'C0751337', 'C1852146', 'C0796280']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "for disease in rare_diseases:\n",
+    "    matrix_jac_gen = pd.read_excel(\"./file/Input_6/m_jacc_gen_name.xlsx\",engine='openpyxl')\n",
+    "    # get useful diseases (disease that shares genes) for a rare disease \n",
+    "    df_useful_diseases = get_normal_diseases(disease)\n",
+    "    useful_diseases = df_useful_diseases['disease_id'].drop_duplicates().tolist()\n",
+    "    df = matrix_jac_gen[matrix_jac_gen.rare_dis_id == disease]\n",
+    "    df_useful = df[['rare_dis_id'] + useful_diseases].set_index('rare_dis_id').transpose()\n",
+    "    df_normal_dis_jacc=pd.DataFrame(df_useful[disease].nlargest(5)).reset_index().rename(columns={'index':'disease_id', disease:'jacc_idx'})\n",
+    "    df_normal_dis_jacc.to_excel(f\"{disease}_jacc.xlsx\")\n",
+    "    df_normal_rare_drug=pd.merge(df_useful_diseases,df_normal_dis_jacc,on=\"disease_id\",how=\"inner\")\n",
+    "    df_normal_rare_drug=df_normal_rare_drug.drop_duplicates()\n",
+    "    drug_dis=df_normal_rare_drug.groupby('drug_name').count()\n",
+    "    drug_dis.to_excel(f\"{disease}_drugs_dr.xlsx\")\n",
+    "    # Drug repositioning direct for each rare disease\n",
+    "    drug_direct=df_normal_rare_drug[df_normal_rare_drug[\"disease_id\"]== disease]\n",
+    "    drug_direct.to_csv(f\"{disease}_drugs_dr_direct.csv\")"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/6.2 Triplets with target-sym-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "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",
+    "from pandas import DataFrame\n",
+    "from sklearn.metrics import jaccard_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_dummies(data,col_index,col_col):\n",
+    "    \n",
+    "    df_final= pd.get_dummies(data.set_index(col_index),col_col).reset_index()\n",
+    "    df_final=df_final.drop_duplicates()\n",
+    "    df_final=df_final.groupby(col_index).sum().reset_index()\n",
+    "    \n",
+    "    return df_final\n",
+    "\n",
+    "def convert(lista):\n",
+    "    return tuple(i for i in lista)\n",
+    "\n",
+    "\n",
+    "def get_normal_diseases(rare_disease_dis):\n",
+    "    '''\n",
+    "    Esta funcion devuelve un dataframe con la enfermedad, los medicamentos y los targets que son utiles\n",
+    "    para la enfermedad rara que se le pase como parametro'''\n",
+    "    \n",
+    "    \n",
+    "    q= f'''SELECT DISTINCT\n",
+    "        ds.disease_id, drug_name,dg.gene_id,lm.disnet_id\n",
+    "        FROM\n",
+    "        disnet_biolayer.disease_gene dg \n",
+    "            JOIN disnet_biolayer.disease ds ON ds.disease_id = dg.disease_id\n",
+    "            JOIN edsssdb.layersmappings lm on dg.disease_id = lm.cui\n",
+    "            JOIN edsssdb.disease_symptom dsy ON lm.disnet_id = dsy.disease_id\n",
+    "            JOIN edsssdb.symptom s ON dsy.cui = s.cui\n",
+    "            JOIN disnet_biolayer.encodes e ON dg.gene_id = e.gene_id\n",
+    "            JOIN disnet_drugslayer.has_code hc ON hc.code = e.protein_id\n",
+    "            JOIN disnet_drugslayer.drug_target dt ON hc.id = dt.target_id\n",
+    "            JOIN disnet_drugslayer.drug d ON dt.drug_id = d.drug_id\n",
+    "            \n",
+    "        WHERE\n",
+    "             hc.entity_id = 3\n",
+    "             and ds.ddf_type = \"disease\"\n",
+    "        AND dg.gene_id in (SELECT distinct(gene_id) FROM disnet_biolayer.disease_gene\n",
+    "        where disease_id = \"{rare_disease_dis}\")\n",
+    "      \n",
+    "        ;'''\n",
+    "    \n",
+    "    df = pd.read_sql(q, con=disnet_db_ares)\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rare_diseases= ['C0011195', 'C0023944', 'C0024054', 'C0024901', 'C0027877', 'C0036391', 'C0265202', 'C0268059', 'C0549463', 'C0751337', 'C0869083', 'C1852146', 'C0796280']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for disease in rare_diseases:\n",
+    "    matrix_jac_syn = pd.read_excel((\"./file/Input_6/mat_jacc_syn_cuis.xlsx\"),engine='openpyxl')\n",
+    "    # get useful diseases (disease that shares genes) for a rare disease \n",
+    "    df_useful_diseases = get_normal_diseases(disease)\n",
+    "    useful_diseases = df_useful_diseases['disease_id'].drop_duplicates().tolist()\n",
+    "    df = matrix_jac_syn[matrix_jac_syn.rare_dis_id == disease]\n",
+    "    df_useful = df[['rare_dis_id'] + useful_diseases].set_index('rare_dis_id').transpose()\n",
+    "    df_normal_dis_jacc=pd.DataFrame(df_useful[disease].nlargest(5)).reset_index().rename(columns={'index':'disease_id', disease:'jacc_idx'})\n",
+    "    df_normal_dis_jacc.to_excel(f\"{disease}_jacc.xlsx\")\n",
+    "    df_normal_rare_drug=pd.merge(df_useful_diseases,df_normal_dis_jacc,on=\"disease_id\",how=\"inner\")\n",
+    "    df_normal_rare_drug=df_normal_rare_drug.drop_duplicates()\n",
+    "    drug_dis=df_normal_rare_drug.groupby('drug_name').count()\n",
+    "    drug_dis.to_excel(f\"{disease}_drugs_dr.xlsx\")\n",
+    "    # Drug repositioning direct for each rare disease\n",
+    "    drug_direct=df_normal_rare_drug[df_normal_rare_drug[\"disease_id\"]== disease]\n",
+    "    drug_direct.to_excel(f\"{disease}_drugs_dr_direct.xlsx\")"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/6.3 Triplets with target-pw-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "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",
+    "from pandas import DataFrame\n",
+    "from sklearn.metrics import jaccard_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_dummies(data,col_index,col_col):\n",
+    "    \n",
+    "    df_final= pd.get_dummies(data.set_index(col_index),col_col).reset_index()\n",
+    "    df_final=df_final.drop_duplicates()\n",
+    "    df_final=df_final.groupby(col_index).sum().reset_index()\n",
+    "    \n",
+    "    return df_final\n",
+    "\n",
+    "def convert(lista):\n",
+    "    return tuple(i for i in lista)\n",
+    "\n",
+    "\n",
+    "def get_normal_diseases(rare_disease):\n",
+    "    '''\n",
+    "    Esta funcion devuelve un dataframe con la enfermedad, los medicamentos y los targets que son utiles\n",
+    "    para la enfermedad rara que se le pase como parametro'''\n",
+    "    \n",
+    "    \n",
+    "    q= f'''SELECT DISTINCT\n",
+    "        ds.disease_id, drug_name,dg.gene_id\n",
+    "        FROM disnet_biolayer.gene_pathway gp\n",
+    "            JOIN disnet_biolayer.pathway p on gp.pathway_id = p.pathway_id\n",
+    "            JOIN disnet_biolayer.disease_gene dg ON gp.gene_id = dg.gene_id\n",
+    "            JOIN disnet_biolayer.disease ds ON ds.disease_id = dg.disease_id\n",
+    "            JOIN disnet_biolayer.encodes e ON dg.gene_id = e.gene_id\n",
+    "            JOIN disnet_drugslayer.has_code hc ON hc.code = e.protein_id\n",
+    "            JOIN disnet_drugslayer.drug_target dt ON hc.id = dt.target_id\n",
+    "            JOIN disnet_drugslayer.drug d ON dt.drug_id = d.drug_id\n",
+    "        WHERE\n",
+    "             hc.entity_id = 3\n",
+    "             and ds.ddf_type = \"disease\"\n",
+    "        AND dg.gene_id in (SELECT distinct(gene_id) FROM disnet_biolayer.disease_gene \n",
+    "        where disease_id = \"{rare_disease}\")\n",
+    "        ;'''\n",
+    "    \n",
+    "    df = pd.read_sql(q, con=disnet_db_ares)\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "rare_diseases= ['C0011195', 'C0023944', 'C0024054', 'C0024901', 'C0027877', 'C0036391', 'C0265202', 'C0268059', 'C0549463', 'C0751337', 'C0869083', 'C1852146', 'C0796280']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for disease in rare_diseases:\n",
+    "    matrix_jac_pw = pd.read_excel((\"./file/Input_6/m_jacc_pw_name.xlsx\"),engine='openpyxl')\n",
+    "    # get useful diseases (disease that shares genes) for a rare disease \n",
+    "    df_useful_diseases = get_normal_diseases(disease)\n",
+    "    useful_diseases = df_useful_diseases['disease_id'].drop_duplicates().tolist()\n",
+    "    df = matrix_jac_pw[matrix_jac_pw.rare_dis_id == disease]\n",
+    "    df_useful = df[['rare_dis_id'] + useful_diseases].set_index('rare_dis_id').transpose()\n",
+    "    df_normal_dis_jacc=pd.DataFrame(df_useful[disease].nlargest(5)).reset_index().rename(columns={'index':'disease_id', disease:'jacc_idx'})\n",
+    "    df_normal_dis_jacc.to_excel(f\"{disease}_jacc.xlsx\")\n",
+    "    df_normal_rare_drug=pd.merge(df_useful_diseases,df_normal_dis_jacc,on=\"disease_id\",how=\"inner\")\n",
+    "    df_normal_rare_drug=df_normal_rare_drug.drop_duplicates()\n",
+    "    drug_dis=df_normal_rare_drug.groupby('drug_name').count()\n",
+    "    drug_dis.to_excel(f\"{disease}_drugs_dr.xlsx\")\n",
+    "    # Drug repositioning direct for each rare disease\n",
+    "    drug_direct=df_normal_rare_drug[df_normal_rare_drug[\"disease_id\"]== disease]\n",
+    "    drug_direct.to_excel(f\"{disease}_drugs_dr_direct.xlsx\")"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/6.4 Triplets with target-ppi-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "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",
+    "from pandas import DataFrame\n",
+    "from sklearn.metrics import jaccard_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_dummies(data,col_index,col_col):\n",
+    "    \n",
+    "    df_final= pd.get_dummies(data.set_index(col_index),col_col).reset_index()\n",
+    "    df_final=df_final.drop_duplicates()\n",
+    "    df_final=df_final.groupby(col_index).sum().reset_index()\n",
+    "    \n",
+    "    return df_final\n",
+    "\n",
+    "def convert(lista):\n",
+    "    return tuple(i for i in lista)\n",
+    "\n",
+    "\n",
+    "def get_normal_diseases(rare_disease):\n",
+    "    '''\n",
+    "    Esta funcion devuelve un dataframe con la enfermedad, los medicamentos y los targets que son utiles\n",
+    "    para la enfermedad rara que se le pase como parametro'''\n",
+    "    \n",
+    "    \n",
+    "    q= f'''SELECT DISTINCT\n",
+    "        ds.disease_id, drug_name,dg.gene_id\n",
+    "        FROM\n",
+    "        disnet_biolayer.disease_gene dg \n",
+    "        JOIN disnet_biolayer.disease ds ON ds.disease_id = dg.disease_id\n",
+    "        JOIN disnet_biolayer.encodes e_uno ON dg.gene_id = e_uno.gene_id\n",
+    "        JOIN disnet_drugslayer.has_code hc ON hc.code = e_uno.protein_id\n",
+    "        JOIN disnet_biolayer.ppi ppi on ppi.protein1_id = e_uno.protein_id\n",
+    "        JOIN disnet_biolayer.encodes e_dos on e_dos.protein_id = ppi.protein2_id\n",
+    "        JOIN disnet_drugslayer.drug_target dt ON hc.id = dt.target_id\n",
+    "        JOIN disnet_drugslayer.drug d ON dt.drug_id = d.drug_id\n",
+    "        WHERE\n",
+    "             hc.entity_id = 3\n",
+    "             \n",
+    "        and ds.ddf_type = \"disease\"\n",
+    "        and ppi.quality = \"GOLD\"\n",
+    "        AND dg.gene_id in (SELECT distinct(gene_id) FROM disnet_biolayer.disease_gene\n",
+    "        where disease_id = \"{rare_disease}\")\n",
+    "        ;'''\n",
+    "    \n",
+    "    df = pd.read_sql(q, con=disnet_db_ares)\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rare_diseases= ['C0011195', 'C0023944', 'C0024054', 'C0024901', 'C0027877', 'C0036391', 'C0265202', 'C0268059', 'C0549463', 'C0751337', 'C0869083', 'C1852146', 'C0796280']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for disease in rare_diseases:\n",
+    "    matrix_jac_ppi = pd.read_excel((\"./file/Input_6/mat_jacc_pip.xlsx\"),engine='openpyxl')\n",
+    "    # get useful diseases (disease that shares genes) for a rare disease \n",
+    "    df_useful_diseases = get_normal_diseases(disease)\n",
+    "    useful_diseases = df_useful_diseases['disease_id'].drop_duplicates().tolist()\n",
+    "    df = matrix_jac_ppi[matrix_jac_ppi.rare_dis_id == disease]\n",
+    "    df_useful = df[['rare_dis_id'] + useful_diseases].set_index('rare_dis_id').transpose()\n",
+    "    df_normal_dis_jacc=pd.DataFrame(df_useful[disease].nlargest(5)).reset_index().rename(columns={'index':'disease_id', disease:'jacc_idx'})\n",
+    "    df_normal_dis_jacc.to_excel(f\"{disease}_jacc.xlsx\")\n",
+    "    df_normal_rare_drug=pd.merge(df_useful_diseases,df_normal_dis_jacc,on=\"disease_id\",how=\"inner\")\n",
+    "    df_normal_rare_drug=df_normal_rare_drug.drop_duplicates()\n",
+    "    drug_dis=df_normal_rare_drug.groupby('drug_name').count()\n",
+    "    drug_dis.to_excel(f\"{disease}_drugs_dr.xlsx\")\n",
+    "    # Drug repositioning direct for each rare disease\n",
+    "    drug_direct=df_normal_rare_drug[df_normal_rare_drug[\"disease_id\"]== disease]\n",
+    "    drug_direct.to_excel(f\"{disease}_drugs_dr_direct.xlsx\")"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/6.5 Triplets with target-variant-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "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",
+    "from pandas import DataFrame\n",
+    "from sklearn.metrics import jaccard_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_dummies(data,col_index,col_col):\n",
+    "    \n",
+    "    df_final= pd.get_dummies(data.set_index(col_index),col_col).reset_index()\n",
+    "    df_final=df_final.drop_duplicates()\n",
+    "    df_final=df_final.groupby(col_index).sum().reset_index()\n",
+    "    \n",
+    "    return df_final\n",
+    "\n",
+    "def convert(lista):\n",
+    "    return tuple(i for i in lista)\n",
+    "\n",
+    "\n",
+    "def get_normal_diseases(rare_disease):\n",
+    "    '''\n",
+    "    Esta funcion devuelve un dataframe con la enfermedad, los medicamentos y los targets que son utiles\n",
+    "    para la enfermedad rara que se le pase como parametro'''\n",
+    "    \n",
+    "    \n",
+    "    q= f'''SELECT DISTINCT\n",
+    "        d.disease_id, drug_name,dg.gene_id\n",
+    "        FROM\n",
+    "        disnet_biolayer.disease_variant dv\n",
+    "            JOIN disnet_biolayer.disease d on dv.disease_id = d.disease_id\n",
+    "            JOIN disnet_biolayer.variant v on v.variant_id = dv.variant_id\n",
+    "            JOIN disnet_biolayer.disease_gene dg ON d.disease_id = dg.disease_id\n",
+    "            JOIN disnet_biolayer.encodes e ON dg.gene_id = e.gene_id\n",
+    "            JOIN disnet_drugslayer.has_code hc ON hc.code = e.protein_id\n",
+    "            JOIN disnet_drugslayer.drug_target dt ON hc.id = dt.target_id\n",
+    "            JOIN disnet_drugslayer.drug d ON dt.drug_id = d.drug_id\n",
+    "        WHERE\n",
+    "             hc.entity_id = 3\n",
+    "             and v.chromosome is not null\n",
+    "        and d.ddf_type = \"disease\"\n",
+    "        AND dg.gene_id in (SELECT distinct(gene_id) FROM disnet_biolayer.disease_gene\n",
+    "        where disease_id = \"{rare_disease}\")\n",
+    "        ;'''\n",
+    "    \n",
+    "    df = pd.read_sql(q, con=disnet_db_ares)\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rare_diseases= ['C0011195', 'C0023944', 'C0024054', 'C0024901', 'C0027877', 'C0036391', 'C0265202', 'C0268059', 'C0549463', 'C0751337', 'C0869083', 'C1852146', 'C0796280']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for disease in rare_diseases:\n",
+    "    matrix_jac_var = pd.read_excel((\"./file/Input_6/mat_jacc_variant.xlsx\"),engine='openpyxl')\n",
+    "    # get useful diseases (disease that shares genes) for a rare disease \n",
+    "    df_useful_diseases = get_normal_diseases(disease)\n",
+    "    useful_diseases = df_useful_diseases['disease_id'].drop_duplicates().tolist()\n",
+    "    df = matrix_jac_var[matrix_jac_var.rare_dis_id == disease]\n",
+    "    df_useful = df[['rare_dis_id'] + useful_diseases].set_index('rare_dis_id').transpose()\n",
+    "    df_normal_dis_jacc=pd.DataFrame(df_useful[disease].nlargest(5)).reset_index().rename(columns={'index':'disease_id', disease:'jacc_idx'})\n",
+    "    df_normal_dis_jacc.to_excel(f\"{disease}_jacc.xlsx\")\n",
+    "    df_normal_rare_drug=pd.merge(df_useful_diseases,df_normal_dis_jacc,on=\"disease_id\",how=\"inner\")\n",
+    "    df_normal_rare_drug=df_normal_rare_drug.drop_duplicates()\n",
+    "    drug_dis=df_normal_rare_drug.groupby('drug_name').count()\n",
+    "    drug_dis.to_excel(f\"{disease}_drugs_dr.xlsx\")\n",
+    "    # Drug repositioning direct for each rare disease\n",
+    "    drug_direct=df_normal_rare_drug[df_normal_rare_drug[\"disease_id\"]== disease]\n",
+    "    drug_direct.to_excel(f\"{disease}_drugs_dr_direct.xlsx\")"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/7.DRUGS IN COMMON TRIPLETS WITHOUT TARGET -checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from pandas import DataFrame"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# LOAD DATA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "syn = pd.read_excel((\"./file/Input_7/SYN/drugs_C0549463_sintarget_syn.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen =pd.read_excel((\"./file/Input_7/GEN/drug_sintarget_C0265202.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ppi=pd.read_excel((\"./file/Input_7/PPI/drugs_sintar_ppi_C0869083.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "var=pd.read_excel((\"./file/Input_7/VAR/drugs_C1852146_sintarget_var.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "syn= syn['drug_name'].apply(str)\n",
+    "syn= syn.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen= gen['drug_name'].apply(str)\n",
+    "gen= gen.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ppi= ppi['drug_name'].apply(str)\n",
+    "ppi= ppi.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "var= var['drug_name'].apply(str)\n",
+    "var= var.tolist()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# DRUGS IN COMMON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_uno = list(set.intersection(*map(set, [syn,gen])))\n",
+    "drugs_in_all_enf_uno = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_uno.to_excel(\"drug_in_common_enfC0023944_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_dos = list(set.intersection(*map(set, [syn,gen,ppi])))\n",
+    "drugs_in_all_enf_dos = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_dos.to_excel(\"drug_in_common_enfC0024901_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_tres = list(set.intersection(*map(set, [syn,var,ppi])))\n",
+    "drugs_in_all_enf_tres = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_tres.to_excel(\"drug_in_common_enfC0751337_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_cua = list(set.intersection(*map(set, [syn,var,ppi,pw,gen])))\n",
+    "drugs_in_all_enf_cua = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_cua.to_excel(\"drug_in_common_en95_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_cin = list(set.intersection(*map(set, [syn,var,pw,gen])))\n",
+    "drugs_in_all_enf_cin = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_cin.to_excel(\"drug_in_common_enC0027877_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_seis = list(set.intersection(*map(set, [syn,var,pw])))\n",
+    "drugs_in_all_enf_seis = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_seis.to_excel(\"drug_in_common_enfC1852146_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_sie = list(set.intersection(*map(set, [syn,gen,ppi])))\n",
+    "drugs_in_all_enf_sie = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_sie.to_excel(\"drug_in_common_enfC0265202_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_ocho = list(set.intersection(*map(set, [syn,gen,ppi,var])))\n",
+    "drugs_in_all_enf_ocho = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_ocho.to_excel(\"drug_in_common_enfC0869083_sintarget.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_nue = list(set.intersection(*map(set, [syn,var,ppi])))\n",
+    "drugs_in_all_enf_nue = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_nue.to_excel(\"drug_in_common_enfC0549463_sintarget.xlsx\")"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/8.DRUGS IN COMMON TRIPLETS WITH TARGET -checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from pandas import DataFrame"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# DATA LOAD"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "syn = pd.read_excel((\"./file/Input_8/SYMPTOM/drugs_all_C0549463_syn.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen =pd.read_excel((\"./file/Input_8/GENES/drugs_all_C0549463_gen.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ppi=pd.read_excel((\"./file/Input_8/PPI/drugs_all_C0549463_ppi.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pw=pd.read_excel((\"./file/Input_8/PATHWAY/drugs_C0549463_pw.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "var=pd.read_excel((\"./file/Input_8/VARIANT/drugs_all_C0549463_v.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen= gen['drug_name'].apply(str)\n",
+    "gen= gen.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "syn= syn['drug_name'].apply(str)\n",
+    "syn= syn.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ppi= ppi['drug_name'].apply(str)\n",
+    "ppi= ppi.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "var= var['drug_name'].apply(str)\n",
+    "var= var.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pw= pw['drug_name'].apply(str)\n",
+    "pw= pw.tolist()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# DRUGS IN COMMON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_uno = list(set.intersection(*map(set, [syn,gen,ppi,pw,var])))\n",
+    "drugs_in_all_enf_uno = pd.DataFrame(drugs_in_all_enf_uno)\n",
+    "#drugs_in_all_enf_uno.to_excel(\"drug_in_common_enf_C0011195_target.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_dos = list(set.intersection(*map(set, [syn,gen,ppi,pw,var])))\n",
+    "drugs_in_all_enf_dos = pd.DataFrame(drugs_in_all_enf_dos)\n",
+    "#drugs_in_all_enf_dos.to_excel(\"drug_in_common_enf_C0036391_target.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_tres = list(set.intersection(*map(set, [syn,ppi,pw])))\n",
+    "drugs_in_all_enf_tres = pd.DataFrame(drugs_in_all_enf_tres)\n",
+    "#drugs_in_all_enf_tres.to_excel(\"drug_in_common_enf_C0869083_target.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_cuatro = list(set.intersection(*map(set, [syn,gen,ppi,pw])))\n",
+    "drugs_in_all_enf_cuatro = pd.DataFrame(drugs_in_all_enf_cuatro)\n",
+    "#drugs_in_all_enf_cuatro.to_excel(\"drug_in_common_enf_C0265202_target.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf_cinco = list(set.intersection(*map(set, [syn,gen,ppi,pw,var])))\n",
+    "drugs_in_all_enf_cinco = pd.DataFrame(drugs_in_all_enf_cinco)\n",
+    "#drugs_in_all_enf_cinco.to_excel(\"drug_in_common_enf_C0549463_target.xlsx\")"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/9.DRUGS IN COMMON PATHS_TRIPLETS_TRIPLETS_WITH_TARGET-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from pandas import DataFrame"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# DATA LOAD"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "paths = pd.read_csv(\"./file/Input_9/Paths/enf_uno_drugs.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplet_with =pd.read_excel((\"./file/Input_9/With_tar/drug_in_common_enf_C0011195_target_NEW.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplet_without=pd.read_excel((\"./file/Input_9/Without_tar/drug_in_common_en95_sintarget.xlsx\"),engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "paths= paths['drug_name'].apply(str)\n",
+    "paths= paths.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplet_with= triplet_with['drug_name'].apply(str)\n",
+    "triplet_with= triplet_with.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplet_without= triplet_without['drug_name'].apply(str)\n",
+    "triplet_without= triplet_without.tolist()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# DRUGS IN COMMON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drugs_in_all_enf = list(set.intersection(*map(set, [triplet_with,paths,triplet_without])))\n",
+    "drugs_in_all_enf = pd.DataFrame(drugs_in_all_enf)\n",
+    "drugs_in_all_enf.to_excel(\"enf_uno_drugs_P-TC_new.xlsx\")"
+   ]
+  }
+ ],
+ "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
+}

6.1 Triplets with target- genes.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "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\n",
+    "from sklearn.metrics import jaccard_score\n",
+    "from numpy import logical_and as l_and, logical_not as l_not"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_dummies(data,col_index,col_col):\n",
+    "    \n",
+    "    df_final= pd.get_dummies(data.set_index(col_index),col_col).reset_index()\n",
+    "    df_final=df_final.drop_duplicates()\n",
+    "    df_final=df_final.groupby(col_index).sum().reset_index()\n",
+    "    \n",
+    "    return df_final\n",
+    "\n",
+    "def convert(lista):\n",
+    "    return tuple(i for i in lista)\n",
+    "\n",
+    "\n",
+    "def get_normal_diseases(rare_disease):\n",
+    "    '''\n",
+    "    Esta funcion devuelve un dataframe con la enfermedad, los medicamentos y los targets que son utiles\n",
+    "    para la enfermedad rara que se le pase como parametro'''\n",
+    "    \n",
+    "    \n",
+    "    q= f'''SELECT DISTINCT\n",
+    "        ds.disease_id, drug_name,dg.gene_id\n",
+    "        FROM\n",
+    "        disnet_biolayer.disease_gene dg \n",
+    "            JOIN disnet_biolayer.disease ds ON ds.disease_id = dg.disease_id\n",
+    "            JOIN disnet_biolayer.encodes e ON dg.gene_id = e.gene_id\n",
+    "            JOIN disnet_drugslayer.target_has_code hc ON hc.code_id = e.protein_id\n",
+    "            JOIN disnet_drugslayer.drug_target dt ON hc.target_id = dt.target_id\n",
+    "            JOIN disnet_drugslayer.drug d ON dt.drug_id = d.drug_id\n",
+    "        WHERE\n",
+    "            \n",
+    "            ds.ddf_type = \"disease\"\n",
+    "        AND dg.gene_id in (SELECT distinct(gene_id) FROM disnet_biolayer.disease_gene\n",
+    "        where disease_id = \"{rare_disease}\")\n",
+    "        ;'''\n",
+    "    \n",
+    "    df = pd.read_sql(q, con=disnet_db_ares)\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rare_diseases= ['C0011195', 'C0023944', 'C0024054', 'C0024901', 'C0027877', 'C0036391', 'C0265202', 'C0268059', \n",
+    "                'C0549463', 'C0751337', 'C1852146', 'C0796280']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "for disease in rare_diseases:\n",
+    "    matrix_jac_gen = pd.read_excel(\"./file/Input_6/m_jacc_gen_name.xlsx\",engine='openpyxl')\n",
+    "    # get useful diseases (disease that shares genes) for a rare disease \n",
+    "    df_useful_diseases = get_normal_diseases(disease)\n",
+    "    useful_diseases = df_useful_diseases['disease_id'].drop_duplicates().tolist()\n",
+    "    df = matrix_jac_gen[matrix_jac_gen.rare_dis_id == disease]\n",
+    "    df_useful = df[['rare_dis_id'] + useful_diseases].set_index('rare_dis_id').transpose()\n",
+    "    df_normal_dis_jacc=pd.DataFrame(df_useful[disease].nlargest(5)).reset_index().rename(columns={'index':'disease_id', disease:'jacc_idx'})\n",
+    "    df_normal_dis_jacc.to_excel(f\"{disease}_jacc.xlsx\")\n",
+    "    df_normal_rare_drug=pd.merge(df_useful_diseases,df_normal_dis_jacc,on=\"disease_id\",how=\"inner\")\n",
+    "    df_normal_rare_drug=df_normal_rare_drug.drop_duplicates()\n",
+    "    drug_dis=df_normal_rare_drug.groupby('drug_name').count()\n",
+    "    drug_dis.to_excel(f\"{disease}_drugs_dr.xlsx\")\n",
+    "    # Drug repositioning direct for each rare disease\n",
+    "    drug_direct=df_normal_rare_drug[df_normal_rare_drug[\"disease_id\"]== disease]\n",
+    "    drug_direct.to_csv(f\"{disease}_drugs_dr_direct.csv\")"
+   ]
+  }
+ ],
+ "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
+}