Skip to content

D
DREBIOP_DR_Pathways-based
Commit e4456ac6 authored by Belen Otero Carrasco's avatar Belen Otero Carrasco
Browse files
Options

code

parent 50e8fe6e
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 24694 additions and 11407 deletions
Data/Input/Drug Repurposing/repoDB_all_disdru.tsv deleted 100644 → 0
View file @ 50e8fe6e
This diff is collapsed.
Data/Input/Drug Repurposing/triples_filter_repodb_final.tsv 0 → 100644
View file @ e4456ac6
This diff is collapsed.
Notebooks/Processed data/2. Processed data DREGE.ipynb deleted 100644 → 0
View file @ 50e8fe6e
{
"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": 8,
"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>disease_id</th>\n",
" <th>pathway_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>C0020538</td>\n",
" <td>WP554</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>C0018799</td>\n",
" <td>WP1544</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>C0018799</td>\n",
" <td>WP1528</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>C0027947</td>\n",
" <td>WP229</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>C0013369</td>\n",
" <td>WP229</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>659</th>\n",
" <td>C0268274</td>\n",
" <td>WP4153</td>\n",
" </tr>\n",
" <tr>\n",
" <th>660</th>\n",
" <td>C0085131</td>\n",
" <td>WP4153</td>\n",
" </tr>\n",
" <tr>\n",
" <th>661</th>\n",
" <td>C0036161</td>\n",
" <td>WP4153</td>\n",
" </tr>\n",
" <tr>\n",
" <th>662</th>\n",
" <td>C0268275</td>\n",
" <td>WP4153</td>\n",
" </tr>\n",
" <tr>\n",
" <th>663</th>\n",
" <td>C0162666</td>\n",
" <td>WP4236</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>664 rows × 2 columns</p>\n",
"</div>"
],
"text/plain": [
" disease_id pathway_id\n",
"0 C0020538 WP554\n",
"1 C0018799 WP1544\n",
"2 C0018799 WP1528\n",
"3 C0027947 WP229\n",
"4 C0013369 WP229\n",
".. ... ...\n",
"659 C0268274 WP4153\n",
"660 C0085131 WP4153\n",
"661 C0036161 WP4153\n",
"662 C0268275 WP4153\n",
"663 C0162666 WP4236\n",
"\n",
"[664 rows x 2 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dis_path_direct = pd.read_csv('./Data/Input/DISNET/disease_pathway.tsv', sep='\\t')\n",
"dis_path_direct"
]
},
{
"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": 48,
"metadata": {},
"outputs": [],
"source": [
"dis_drug_gen_sinfil = dis_gen_sinfil.merge(drug_gen, how =\"inner\", on = \"gene_id\")"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"duplas_target_repodb = dis_drug_path_fil.merge(dis_drug_gen_sinfil, how = \"inner\", on =[\"disease_id\",\"drug_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [],
"source": [
"cases_repodb_target = duples_repodb.merge(duplas_target_repodb,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [],
"source": [
"cases_repodb_target.to_csv(\"cases_repodb_target.tsv\", sep =\"\\t\")"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.27445783132529894"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cases_repodb_target[\"score\"].mean()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### JOIN CSBJ"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
"duplas_target_csbj = dis_drug_path_csbj_fil.merge(dis_drug_gen_sinfil, how = \"inner\", on =[\"disease_id\",\"drug_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {},
"outputs": [],
"source": [
"cases_csbj_target = duples_csbj.merge(duplas_target_csbj,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {},
"outputs": [],
"source": [
"cases_csbj_target.to_csv(\"cases_csbj_target.tsv\", sep =\"\\t\")"
]
}
],
"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
}
Notebooks/Processed data/2.1 Target gene-based treated disease _CSBJ-DREGE.ipynb deleted 100644 → 0
View file @ 50e8fe6e
{
"cells": [
{
"cell_type": "code",
"execution_count": 45,
"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": 46,
"metadata": {},
"outputs": [],
"source": [
"cases_csbj_target = pd.read_csv(\"./Data/Input/DISNET/cases_csbj_target.tsv\", sep =\"\\t\")\n",
"cases_csbj = cases_csbj_target.drop([\"Unnamed: 0\"],axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"22"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(cases_csbj[\"disease_id\"].unique())"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"triplets_csbj = pd.read_excel(\"./Data/Input/DISNET/triplets_chembl_disnet.xlsx\",engine='openpyxl')"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
"triplets_csbj =triplets_csbj.drop([\"Unnamed: 0\"],axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"triplets_csbj =triplets_csbj.rename(columns={\"Original Condition CUI\": \"disease_id\"})"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"join_csbj = cases_csbj.merge(triplets_csbj,how = \"inner\",on = [\"drug_id\",\"disease_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"13"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(join_csbj[\"disease_id\"].unique())"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"join_csbj_drug = join_csbj.drop([\"gene_id\",\"score\",\"Original Condition\",\"New Condition\",\"New Condition CUI\",\"Drugs\"],axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"join_csbj_drug =join_csbj_drug.drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"join_csbj_diseases = join_csbj[\"New Condition CUI\"]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"join_csbj_diseases = pd.DataFrame(join_csbj_diseases).drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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": 15,
"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": 62,
"metadata": {},
"outputs": [],
"source": [
"gen_dise_join = join_csbj_diseases.merge(dis_gen,how = \"inner\",on = \"disease_id\")"
]
},
{
"cell_type": "code",
"execution_count": 64,
"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": 68,
"metadata": {},
"outputs": [],
"source": [
"gen_dise_join_dru = gen_dise_join.merge(drug_gen,how = \"inner\",on = \"gene_id\")"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [],
"source": [
"score_gdas_csbj = gen_dise_join_dru.merge(join_csbj ,how = \"inner\",on = [\"drug_id\",\"disease_id\",\"score\",\"gene_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 72,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.28196850393700795"
]
},
"execution_count": 72,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"score_gdas_csbj[\"score\"].mean()"
]
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {},
"outputs": [],
"source": [
"score_gdas_csbj.to_csv(\"score_gdas_csbj_target_filtergen.tsv\", sep='\\t')"
]
}
],
"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
}
Notebooks/Processed data/2.2 Target gene-based treated disease_REPODB-DREGE.ipynb deleted 100644 → 0
View file @ 50e8fe6e
{
"cells": [
{
"cell_type": "code",
"execution_count": 74,
"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": 75,
"metadata": {},
"outputs": [],
"source": [
"cases_repodb = pd.read_csv(\"./Data/Input/DISNET/cases_repodb_target.tsv\", sep='\\t')\n",
"cases_repodb = cases_repodb.drop([\"Unnamed: 0\"],axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 78,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"34"
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(cases_repodb[\"disease_id\"].unique())"
]
},
{
"cell_type": "code",
"execution_count": 79,
"metadata": {},
"outputs": [],
"source": [
"triplets_repodb = pd.read_csv('./Data/Input/DISNET/repodb_all_triples.tsv', sep='\\t')"
]
},
{
"cell_type": "code",
"execution_count": 82,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"550"
]
},
"execution_count": 82,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(triplets_repodb[\"disease1\"].unique())"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {},
"outputs": [],
"source": [
"triplets_repodb_one = triplets_repodb.rename(columns={\"disease1\": \"disease_id\",\"drug\":\"drug_id\"})"
]
},
{
"cell_type": "code",
"execution_count": 84,
"metadata": {},
"outputs": [],
"source": [
"triplets_repodb_one = triplets_repodb_one.drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 86,
"metadata": {},
"outputs": [],
"source": [
"triplets_repodb_two = triplets_repodb.rename(columns={\"disease2\": \"disease_id\",\"drug\":\"drug_id\"})"
]
},
{
"cell_type": "code",
"execution_count": 87,
"metadata": {},
"outputs": [],
"source": [
"triplets_repodb_two = triplets_repodb_two.drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 89,
"metadata": {},
"outputs": [],
"source": [
"join_one = cases_repodb.merge(triplets_repodb_one,how = \"inner\",on = [\"drug_id\",\"disease_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 91,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"27"
]
},
"execution_count": 91,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(join_one[\"disease_id\"].unique())"
]
},
{
"cell_type": "code",
"execution_count": 92,
"metadata": {},
"outputs": [],
"source": [
"join_two = cases_repodb.merge(triplets_repodb_two,how = \"inner\",on = [\"drug_id\",\"disease_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 93,
"metadata": {},
"outputs": [],
"source": [
"join_two = join_two.drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 95,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"32"
]
},
"execution_count": 95,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(join_two[\"disease_id\"].unique())"
]
},
{
"cell_type": "code",
"execution_count": 111,
"metadata": {},
"outputs": [],
"source": [
"triples_repo_all = pd.concat([joinone_csbj_diseases,jointwo_csbj_diseases])"
]
},
{
"cell_type": "code",
"execution_count": 114,
"metadata": {},
"outputs": [],
"source": [
"triples_repo_all = triples_repo_all.drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 113,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"32"
]
},
"execution_count": 113,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(triples_repo_all[\"disease_id\"].unique())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1. DRUG - GENE - TARGET"
]
},
{
"cell_type": "code",
"execution_count": 115,
"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": 117,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.13747265487982685"
]
},
"execution_count": 117,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dis_gen[\"score\"].mean()"
]
},
{
"cell_type": "code",
"execution_count": 119,
"metadata": {},
"outputs": [],
"source": [
"gen_dise_join = triples_repo_all.merge(dis_gen,how = \"inner\",on = [\"disease_id\",\"gene_id\",\"score\"])"
]
},
{
"cell_type": "code",
"execution_count": 121,
"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": 123,
"metadata": {},
"outputs": [],
"source": [
"gen_dise_join_dru = gen_dise_join.merge(drug_gen,how = \"inner\",on = [\"gene_id\",\"drug_id\"])"
]
},
{
"cell_type": "code",
"execution_count": 128,
"metadata": {},
"outputs": [],
"source": [
"score_gdas_repodb_target = gen_dise_join_dru.merge(triples_repo_all ,how = \"inner\",on = [\"drug_id\",\"disease_id\",\"score\",\"gene_id\",\"disease_new\"])"
]
},
{
"cell_type": "code",
"execution_count": 131,
"metadata": {},
"outputs": [],
"source": [
"score_gdas_repodb_target = score_gdas_repodb_target.drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 134,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.21210059171595477"
]
},
"execution_count": 134,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"score_gdas_repodb_target[\"score\"].mean()"
]
},
{
"cell_type": "code",
"execution_count": 135,
"metadata": {},
"outputs": [],
"source": [
"score_gdas_repodb_target.to_csv(\"score_gdas_repodb_target_final.tsv\", sep='\\t')"
]
}
],
"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
}
Notebooks/Results/3.1 Type of drugs - MESHPA.ipynb
View file @ e4456ac6
This source diff could not be displayed because it is too large. You can view the blob instead.
Notebooks/Results/3.2 Types of drugs - ATC.ipynb
View file @ e4456ac6
This source diff could not be displayed because it is too large. You can view the blob instead.
Notebooks/Results/4.1 Types of diseases - DREGE.ipynb
View file @ e4456ac6
This source diff could not be displayed because it is too large. You can view the blob instead.
Notebooks/Results/4.2 Types of diseases - DREBIOP.ipynb
View file @ e4456ac6
This source diff could not be displayed because it is too large. You can view the blob instead.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment