Extract.gene.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "from google.cloud import bigquery as bq"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "cancer_gene = set([line. rstrip('\\n') for line in open(\"./preliminary/sig-DMD.cancer.genes\")])\n",
    "trip_gene = set([line. rstrip('\\n') for line in open(\"./preliminary/sig-DMD.trip.genes\")])\n",
    "nontrip_gene = set([line. rstrip('\\n') for line in open(\"./preliminary/sig-DMD.nontrip.genes\")])\n",
    "err_gene = set([line. rstrip('\\n') for line in open(\"./preliminary/sig-DMD.err.genes\")])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3518"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "union_gene = cancer_gene.union(trip_gene, nontrip_gene, err_gene)\n",
    "len(union_gene)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3518, 1)\n"
     ]
    },
    {
     "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>gene_symbol</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A1CF</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AACS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AARS2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AASS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AATF</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  gene_symbol\n",
       "0        A1CF\n",
       "1        AACS\n",
       "2       AARS2\n",
       "3        AASS\n",
       "4        AATF"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gene_df = pd.DataFrame()\n",
    "gene_df['gene_symbol'] = sorted(list(union_gene))\n",
    "print(gene_df.shape)\n",
    "gene_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "gene_df['BRCA'] = gene_df['gene_symbol'].apply(lambda x: \"Yes\" if x in cancer_gene else \"No\")\n",
    "gene_df['TN-BRCA'] = gene_df['gene_symbol'].apply(lambda x: \"Yes\" if x in trip_gene else \"No\")\n",
    "gene_df['nonTN-BRCA'] = gene_df['gene_symbol'].apply(lambda x: \"Yes\" if x in nontrip_gene else \"No\")\n",
    "gene_df['EndoR-BRCA'] = gene_df['gene_symbol'].apply(lambda x: \"Yes\" if x in err_gene else \"No\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>gene_symbol</th>\n",
       "      <th>BRCA</th>\n",
       "      <th>TN-BRCA</th>\n",
       "      <th>nonTN-BRCA</th>\n",
       "      <th>EndoR-BRCA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A1CF</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AACS</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AARS2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AASS</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AATF</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  gene_symbol BRCA TN-BRCA nonTN-BRCA EndoR-BRCA\n",
       "0        A1CF  Yes      No         No        Yes\n",
       "1        AACS  Yes      No         No         No\n",
       "2       AARS2  Yes      No         No         No\n",
       "3        AASS  Yes     Yes        Yes         No\n",
       "4        AATF  Yes      No         No         No"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gene_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of genes associated with subtype-specific signatures:\n",
      "3470\n",
      "Number of genes associated with endocrine resistance signatures:\n",
      "229\n"
     ]
    }
   ],
   "source": [
    "print(\"Number of genes associated with subtype-specific signatures:\")\n",
    "l = gene_df.loc[(gene_df['BRCA']==\"Yes\") | (gene_df['TN-BRCA']==\"Yes\") | (gene_df['nonTN-BRCA']==\"Yes\")].shape[0]\n",
    "print(l)\n",
    "print(\"Number of genes associated with endocrine resistance signatures:\")\n",
    "l = gene_df.loc[gene_df['EndoR-BRCA']==\"Yes\"].shape[0]\n",
    "print(l)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "gene_df.to_csv(\"./metadata/associated_genes_list.tsv\", sep=\"\\t\", index=False)"
   ]
  }
 ],
 "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}