174 lines (173 with data), 4.5 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from tqdm.notebook import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "omics = [\"proteomics\",\n",
    "        \"metabolomics\",\n",
    "        \"drugresponse\",\n",
    "        \"crisprcas9\",\n",
    "        \"methylation\",\n",
    "        \"transcriptomics\",\n",
    "        \"copynumber\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "TIMESTAMP = \"20241210_000556\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>Sample_ID</th>\n",
       "      <th>target_name</th>\n",
       "      <th>omics_feature</th>\n",
       "      <th>Shap_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>42644</th>\n",
       "      <td>SIDM00001</td>\n",
       "      <td>Latent_1</td>\n",
       "      <td>proteomics_ABHD14B</td>\n",
       "      <td>0.000240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42645</th>\n",
       "      <td>SIDM00003</td>\n",
       "      <td>Latent_1</td>\n",
       "      <td>proteomics_ABHD14B</td>\n",
       "      <td>-0.000120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42646</th>\n",
       "      <td>SIDM00005</td>\n",
       "      <td>Latent_1</td>\n",
       "      <td>proteomics_ABHD14B</td>\n",
       "      <td>-0.000593</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42647</th>\n",
       "      <td>SIDM00006</td>\n",
       "      <td>Latent_1</td>\n",
       "      <td>proteomics_ABHD14B</td>\n",
       "      <td>0.000908</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42648</th>\n",
       "      <td>SIDM00007</td>\n",
       "      <td>Latent_1</td>\n",
       "      <td>proteomics_ABHD14B</td>\n",
       "      <td>0.000113</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Sample_ID target_name       omics_feature  Shap_value\n",
       "42644  SIDM00001    Latent_1  proteomics_ABHD14B    0.000240\n",
       "42645  SIDM00003    Latent_1  proteomics_ABHD14B   -0.000120\n",
       "42646  SIDM00005    Latent_1  proteomics_ABHD14B   -0.000593\n",
       "42647  SIDM00006    Latent_1  proteomics_ABHD14B    0.000908\n",
       "42648  SIDM00007    Latent_1  proteomics_ABHD14B    0.000113"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for omic in tqdm(omics[1:]):\n",
    "    df = pd.read_feather(\n",
    "        f\"/home/scai/E0160_P01_PhenPred/reports/vae/files/20231023_092657_shap_values_{omic}.feather\"\n",
    "    )\n",
    "    df.iloc[:, 1:] = df.iloc[:, 1:].abs()\n",
    "    df_sum = df.groupby(\"target_name\").sum()\n",
    "    df_sum.to_csv(\n",
    "        f\"/home/scai/E0160_P01_PhenPred/reports/vae/files/{omic}_shap_values.csv.gz\"\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "mosa",
   "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}