exploring_GLM_results_for_spokesig_computation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "32d7ea86",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from paths import *\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "efce3eee",
   "metadata": {},
   "outputs": [],
   "source": [
    "sample = \"feces\"\n",
    "compound_type = \"global\"\n",
    "\n",
    "sheet_name_list = [\"Without outlier\", \"Without outlier-MS treated\", \"Without outlier-MS not treated\",\n",
    "                  \"With outlier\", \"With outlier-MStreated\", \"With outlier-MS not treated\"]\n",
    "sel_sheet_index = 0\n",
    "\n",
    "if compound_type == \"targeted\":\n",
    "    GLM_out = pd.read_excel(os.path.join(OUTPUT_PATH, 'GLM_result_targeted_compounds_{}_sample.xlsx'.format(sample)), sheet_name=sheet_name_list[sel_sheet_index], engine='openpyxl')\n",
    "    compound_spoke_map = pd.read_csv(os.path.join(OUTPUT_PATH, \"short_chain_fatty_acid_spoke_map.csv\"))\n",
    "else:\n",
    "    GLM_out = pd.read_excel(os.path.join(OUTPUT_PATH, 'GLM_result_global_compounds_{}_sample.xlsx'.format(sample)), sheet_name=sheet_name_list[sel_sheet_index], engine='openpyxl')\n",
    "    compound_spoke_map = pd.read_csv(os.path.join(OUTPUT_PATH, \"global_metabolomics_compound_spoke_map.csv\"))\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "643e8b3f",
   "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>analyte_name</th>\n",
       "      <th>disease_coeff</th>\n",
       "      <th>pvalue</th>\n",
       "      <th>CI</th>\n",
       "      <th>model_converged_flag</th>\n",
       "      <th>disease_coeff_normalized</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Isovaleric acid</td>\n",
       "      <td>-0.087882</td>\n",
       "      <td>0.005238</td>\n",
       "      <td>(-0.1495743142690827, -0.026190018251133304)</td>\n",
       "      <td>True</td>\n",
       "      <td>-0.623663</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      analyte_name  disease_coeff    pvalue  \\\n",
       "5  Isovaleric acid      -0.087882  0.005238   \n",
       "\n",
       "                                             CI  model_converged_flag  \\\n",
       "5  (-0.1495743142690827, -0.026190018251133304)                  True   \n",
       "\n",
       "   disease_coeff_normalized  \n",
       "5                 -0.623663  "
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "sample = \"serum\"\n",
    "\n",
    "sel_sheet_index=2\n",
    "\n",
    "GLM_out_targeted = pd.read_excel(os.path.join(OUTPUT_PATH, 'GLM_result_targeted_compounds_{}_sample.xlsx'.format(sample)), sheet_name=sheet_name_list[sel_sheet_index], engine='openpyxl')\n",
    "GLM_out_targeted.dropna(subset=[\"model_converged_flag\"], inplace=True)\n",
    "GLM_out_targeted = GLM_out_targeted[GLM_out_targeted[\"model_converged_flag\"] == 1]\n",
    "# GLM_out_targeted_significant_compounds = GLM_out_targeted[GLM_out_targeted.pvalue < pvalue_thresh]\n",
    "\n",
    "GLM_out_global = pd.read_excel(os.path.join(OUTPUT_PATH, 'GLM_result_global_compounds_{}_sample.xlsx'.format(sample)), sheet_name=sheet_name_list[sel_sheet_index], engine='openpyxl')\n",
    "GLM_out_global.drop(\"chem_id\", axis=1, inplace=True)\n",
    "GLM_out_global.dropna(subset=[\"model_converged_flag\"], inplace=True)\n",
    "GLM_out_global = GLM_out_global[GLM_out_global[\"model_converged_flag\"] == 1]\n",
    "GLM_out_global_significant_compounds = GLM_out_global[GLM_out_global.pvalue < pvalue_thresh]\n",
    "\n",
    "\n",
    "scaler = MinMaxScaler(feature_range=(GLM_out_global_significant_compounds.disease_coeff.min(), GLM_out_global_significant_compounds.disease_coeff.max()))\n",
    "\n",
    "GLM_out_targeted[\"disease_coeff_normalized\"] = scaler.fit_transform(GLM_out_targeted[['disease_coeff']])\n",
    "\n",
    "GLM_out_targeted_significant_compounds = GLM_out_targeted[GLM_out_targeted.pvalue < pvalue_thresh]\n",
    "GLM_out_targeted_significant_compounds\n",
    "\n",
    "# GLM_out_targeted_significant_compounds.drop(\"disease_coeff\", axis=1, inplace=True)\n",
    "\n",
    "# GLM_out_targeted_significant_compounds = GLM_out_targeted_significant_compounds.rename(columns={\"disease_coeff_normalized\": \"disease_coeff\"})\n",
    "\n",
    "# GLM_out_total_significant_compounds = pd.concat([GLM_out_targeted_significant_compounds, GLM_out_global_significant_compounds], ignore_index=True).drop_duplicates(subset=[\"analyte_name\"], keep=\"first\")\n",
    "\n",
    "# compound_spoke_map_targeted = pd.read_csv(os.path.join(OUTPUT_PATH, \"short_chain_fatty_acid_spoke_map.csv\"))\n",
    "# compound_spoke_map_global = pd.read_csv(os.path.join(OUTPUT_PATH, \"global_metabolomics_compound_spoke_map.csv\"))\n",
    "# compound_spoke_map_global.drop(\"CHEM_ID\", axis=1, inplace=True)\n",
    "# compound_spoke_map = pd.concat([compound_spoke_map_targeted, compound_spoke_map_global], ignore_index=True).drop_duplicates()\n",
    "\n",
    "# GLM_out_total_significant_compounds_mapped_to_SPOKE = pd.merge(GLM_out_total_significant_compounds, compound_spoke_map, left_on=\"analyte_name\", right_on=\"name\")[[\"disease_coeff\", \"spoke_identifer\"]]\n",
    "\n",
    "# GLM_out_total_significant_compounds_mapped_to_SPOKE.drop_duplicates(inplace=True)\n",
    "\n",
    "# GLM_out_total_significant_compounds_mapped_to_SPOKE\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "60a47f0c",
   "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>name</th>\n",
       "      <th>spoke_identifer</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2-Methylbutyric acid</td>\n",
       "      <td>inchikey:WLAMNBDJUVNPJU-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Acetic acid</td>\n",
       "      <td>inchikey:QTBSBXVTEAMEQO-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Butyric acid</td>\n",
       "      <td>inchikey:FERIUCNNQQJTOY-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hexanoic acid</td>\n",
       "      <td>inchikey:FUZZWVXGSFPDMH-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Isobutyric acid</td>\n",
       "      <td>inchikey:KQNPFQTWMSNSAP-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1214</th>\n",
       "      <td>linoleoylcholine*</td>\n",
       "      <td>inchikey:FDCFEKFQGUEBOI-UTJQPWESSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1215</th>\n",
       "      <td>dodecenedioate (C12:1-DC)*</td>\n",
       "      <td>inchikey:MAZWDMBCPDUFDJ-VQHVLOKHSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1216</th>\n",
       "      <td>octadecenedioate (C18:1-DC)</td>\n",
       "      <td>inchikey:SBLKVIQSIHEQOF-UPHRSURJSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1217</th>\n",
       "      <td>cholic acid glucuronide</td>\n",
       "      <td>inchikey:RBLDVEUUCHVWMW-SXYQVCRBSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1218</th>\n",
       "      <td>Glimepiride</td>\n",
       "      <td>inchikey:WIGIZIANZCJQQY-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1219 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                             name                       spoke_identifer\n",
       "0            2-Methylbutyric acid  inchikey:WLAMNBDJUVNPJU-UHFFFAOYSA-N\n",
       "1                     Acetic acid  inchikey:QTBSBXVTEAMEQO-UHFFFAOYSA-N\n",
       "2                    Butyric acid  inchikey:FERIUCNNQQJTOY-UHFFFAOYSA-N\n",
       "3                   Hexanoic acid  inchikey:FUZZWVXGSFPDMH-UHFFFAOYSA-N\n",
       "4                 Isobutyric acid  inchikey:KQNPFQTWMSNSAP-UHFFFAOYSA-N\n",
       "...                           ...                                   ...\n",
       "1214            linoleoylcholine*  inchikey:FDCFEKFQGUEBOI-UTJQPWESSA-N\n",
       "1215   dodecenedioate (C12:1-DC)*  inchikey:MAZWDMBCPDUFDJ-VQHVLOKHSA-N\n",
       "1216  octadecenedioate (C18:1-DC)  inchikey:SBLKVIQSIHEQOF-UPHRSURJSA-N\n",
       "1217      cholic acid glucuronide  inchikey:RBLDVEUUCHVWMW-SXYQVCRBSA-N\n",
       "1218                  Glimepiride  inchikey:WIGIZIANZCJQQY-UHFFFAOYSA-N\n",
       "\n",
       "[1219 rows x 2 columns]"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compound_spoke_map"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "6697b3c3",
   "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>analyte_name</th>\n",
       "      <th>chem_id</th>\n",
       "      <th>disease_coeff</th>\n",
       "      <th>pvalue</th>\n",
       "      <th>CI</th>\n",
       "      <th>model_converged_flag</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>S-1-pyrroline-5-carboxylate</td>\n",
       "      <td>35</td>\n",
       "      <td>-0.123599</td>\n",
       "      <td>3.187022e-05</td>\n",
       "      <td>(-0.1818359963342539, -0.06536113058295488)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>spermidine</td>\n",
       "      <td>50</td>\n",
       "      <td>-0.551727</td>\n",
       "      <td>1.111902e-21</td>\n",
       "      <td>(-0.6647703393836274, -0.4386837216250864)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>alpha-ketoglutarate</td>\n",
       "      <td>93</td>\n",
       "      <td>-0.262250</td>\n",
       "      <td>1.214642e-08</td>\n",
       "      <td>(-0.3524628670314211, -0.17203753194890986)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>kynurenate</td>\n",
       "      <td>98</td>\n",
       "      <td>-0.431384</td>\n",
       "      <td>5.122301e-12</td>\n",
       "      <td>(-0.5538810961968833, -0.3088859224340815)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3-hydroxy-3-methylglutarate</td>\n",
       "      <td>112</td>\n",
       "      <td>-0.364382</td>\n",
       "      <td>1.453116e-15</td>\n",
       "      <td>(-0.45386772583332136, -0.27489584808617973)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>667</th>\n",
       "      <td>leucylalanine</td>\n",
       "      <td>100003179</td>\n",
       "      <td>-0.138733</td>\n",
       "      <td>3.237945e-03</td>\n",
       "      <td>(-0.23108776112964874, -0.04637777842795697)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>669</th>\n",
       "      <td>phenylalanylglycine</td>\n",
       "      <td>100003588</td>\n",
       "      <td>-0.183883</td>\n",
       "      <td>5.930779e-05</td>\n",
       "      <td>(-0.27363588113643134, -0.09413110883011931)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>672</th>\n",
       "      <td>fructosyllysine</td>\n",
       "      <td>100005373</td>\n",
       "      <td>-0.483586</td>\n",
       "      <td>4.866047e-19</td>\n",
       "      <td>(-0.5898993840907047, -0.37727297835960766)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>linoleoyl-linoleoyl-glycerol (18:2/18:2) [1]*</td>\n",
       "      <td>100010941</td>\n",
       "      <td>-0.177933</td>\n",
       "      <td>1.257848e-02</td>\n",
       "      <td>(-0.31768295881409764, -0.03818384004747116)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>676</th>\n",
       "      <td>dodecenedioate (C12:1-DC)*</td>\n",
       "      <td>100019972</td>\n",
       "      <td>-0.299087</td>\n",
       "      <td>2.571458e-08</td>\n",
       "      <td>(-0.40435996446721456, -0.19381355330974206)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>497 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                      analyte_name    chem_id  disease_coeff  \\\n",
       "0                      S-1-pyrroline-5-carboxylate         35      -0.123599   \n",
       "1                                       spermidine         50      -0.551727   \n",
       "3                              alpha-ketoglutarate         93      -0.262250   \n",
       "4                                       kynurenate         98      -0.431384   \n",
       "6                      3-hydroxy-3-methylglutarate        112      -0.364382   \n",
       "..                                             ...        ...            ...   \n",
       "667                                  leucylalanine  100003179      -0.138733   \n",
       "669                            phenylalanylglycine  100003588      -0.183883   \n",
       "672                                fructosyllysine  100005373      -0.483586   \n",
       "675  linoleoyl-linoleoyl-glycerol (18:2/18:2) [1]*  100010941      -0.177933   \n",
       "676                     dodecenedioate (C12:1-DC)*  100019972      -0.299087   \n",
       "\n",
       "           pvalue                                            CI  \\\n",
       "0    3.187022e-05   (-0.1818359963342539, -0.06536113058295488)   \n",
       "1    1.111902e-21    (-0.6647703393836274, -0.4386837216250864)   \n",
       "3    1.214642e-08   (-0.3524628670314211, -0.17203753194890986)   \n",
       "4    5.122301e-12    (-0.5538810961968833, -0.3088859224340815)   \n",
       "6    1.453116e-15  (-0.45386772583332136, -0.27489584808617973)   \n",
       "..            ...                                           ...   \n",
       "667  3.237945e-03  (-0.23108776112964874, -0.04637777842795697)   \n",
       "669  5.930779e-05  (-0.27363588113643134, -0.09413110883011931)   \n",
       "672  4.866047e-19   (-0.5898993840907047, -0.37727297835960766)   \n",
       "675  1.257848e-02  (-0.31768295881409764, -0.03818384004747116)   \n",
       "676  2.571458e-08  (-0.40435996446721456, -0.19381355330974206)   \n",
       "\n",
       "     model_converged_flag  \n",
       "0                     1.0  \n",
       "1                     1.0  \n",
       "3                     1.0  \n",
       "4                     1.0  \n",
       "6                     1.0  \n",
       "..                    ...  \n",
       "667                   1.0  \n",
       "669                   1.0  \n",
       "672                   1.0  \n",
       "675                   1.0  \n",
       "676                   1.0  \n",
       "\n",
       "[497 rows x 6 columns]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GLM_out.dropna(subset=[\"model_converged_flag\"], inplace=True)\n",
    "\n",
    "GLM_out = GLM_out[GLM_out[\"model_converged_flag\"] == 1]\n",
    "GLM_out"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "8fc0ed65",
   "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>analyte_name</th>\n",
       "      <th>chem_id</th>\n",
       "      <th>disease_coeff</th>\n",
       "      <th>pvalue</th>\n",
       "      <th>CI</th>\n",
       "      <th>model_converged_flag</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>(N(1) + N(8))-acetylspermidine</td>\n",
       "      <td>100016038</td>\n",
       "      <td>-0.854618</td>\n",
       "      <td>4.962440e-34</td>\n",
       "      <td>(-0.9923453215861263, -0.7168903935592731)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>267</th>\n",
       "      <td>5-acetylamino-6-formylamino-3-methyluracil</td>\n",
       "      <td>100001402</td>\n",
       "      <td>-0.850864</td>\n",
       "      <td>2.681812e-30</td>\n",
       "      <td>(-0.9966561132020401, -0.7050710983826632)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>517</th>\n",
       "      <td>glycerophosphoserine*</td>\n",
       "      <td>100015666</td>\n",
       "      <td>-0.580587</td>\n",
       "      <td>4.003463e-24</td>\n",
       "      <td>(-0.6929028616045391, -0.4682714061850518)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>105</th>\n",
       "      <td>pantothenate</td>\n",
       "      <td>1024</td>\n",
       "      <td>-0.413031</td>\n",
       "      <td>4.163303e-23</td>\n",
       "      <td>(-0.49480120261761745, -0.33126046608255194)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>317</th>\n",
       "      <td>dimethylarginine (SDMA + ADMA)</td>\n",
       "      <td>100001810</td>\n",
       "      <td>-0.620646</td>\n",
       "      <td>4.424373e-23</td>\n",
       "      <td>(-0.7435950850378227, -0.4976973248629072)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132</th>\n",
       "      <td>N1-methyladenosine</td>\n",
       "      <td>1242</td>\n",
       "      <td>-0.118753</td>\n",
       "      <td>4.217094e-02</td>\n",
       "      <td>(-0.23330501484887248, -0.00420025138468777)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>553</th>\n",
       "      <td>tetradecadienoate (14:2)*</td>\n",
       "      <td>100020343</td>\n",
       "      <td>-0.121905</td>\n",
       "      <td>4.252465e-02</td>\n",
       "      <td>(-0.23969984037867936, -0.0041099752680854446)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122</th>\n",
       "      <td>urate</td>\n",
       "      <td>1134</td>\n",
       "      <td>-0.097551</td>\n",
       "      <td>4.402650e-02</td>\n",
       "      <td>(-0.19249160078015265, -0.002609685604058165)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>304</th>\n",
       "      <td>ectoine</td>\n",
       "      <td>100001635</td>\n",
       "      <td>0.113364</td>\n",
       "      <td>4.479667e-02</td>\n",
       "      <td>(0.0026324448469607215, 0.2240950054272905)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>383</th>\n",
       "      <td>oleoyl-linoleoyl-glycerol (18:1/18:2) [1]</td>\n",
       "      <td>100002989</td>\n",
       "      <td>-0.151572</td>\n",
       "      <td>4.666311e-02</td>\n",
       "      <td>(-0.30090606878313436, -0.002238621564164378)</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>384 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   analyte_name    chem_id  disease_coeff  \\\n",
       "539              (N(1) + N(8))-acetylspermidine  100016038      -0.854618   \n",
       "267  5-acetylamino-6-formylamino-3-methyluracil  100001402      -0.850864   \n",
       "517                       glycerophosphoserine*  100015666      -0.580587   \n",
       "105                                pantothenate       1024      -0.413031   \n",
       "317              dimethylarginine (SDMA + ADMA)  100001810      -0.620646   \n",
       "..                                          ...        ...            ...   \n",
       "132                          N1-methyladenosine       1242      -0.118753   \n",
       "553                   tetradecadienoate (14:2)*  100020343      -0.121905   \n",
       "122                                       urate       1134      -0.097551   \n",
       "304                                     ectoine  100001635       0.113364   \n",
       "383   oleoyl-linoleoyl-glycerol (18:1/18:2) [1]  100002989      -0.151572   \n",
       "\n",
       "           pvalue                                              CI  \\\n",
       "539  4.962440e-34      (-0.9923453215861263, -0.7168903935592731)   \n",
       "267  2.681812e-30      (-0.9966561132020401, -0.7050710983826632)   \n",
       "517  4.003463e-24      (-0.6929028616045391, -0.4682714061850518)   \n",
       "105  4.163303e-23    (-0.49480120261761745, -0.33126046608255194)   \n",
       "317  4.424373e-23      (-0.7435950850378227, -0.4976973248629072)   \n",
       "..            ...                                             ...   \n",
       "132  4.217094e-02    (-0.23330501484887248, -0.00420025138468777)   \n",
       "553  4.252465e-02  (-0.23969984037867936, -0.0041099752680854446)   \n",
       "122  4.402650e-02   (-0.19249160078015265, -0.002609685604058165)   \n",
       "304  4.479667e-02     (0.0026324448469607215, 0.2240950054272905)   \n",
       "383  4.666311e-02   (-0.30090606878313436, -0.002238621564164378)   \n",
       "\n",
       "     model_converged_flag  \n",
       "539                   1.0  \n",
       "267                   1.0  \n",
       "517                   1.0  \n",
       "105                   1.0  \n",
       "317                   1.0  \n",
       "..                    ...  \n",
       "132                   1.0  \n",
       "553                   1.0  \n",
       "122                   1.0  \n",
       "304                   1.0  \n",
       "383                   1.0  \n",
       "\n",
       "[384 rows x 6 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pvalue_thresh = 0.05\n",
    "\n",
    "GLM_out_significant_compounds = GLM_out[GLM_out.pvalue < pvalue_thresh].sort_values(by=\"pvalue\")\n",
    "\n",
    "GLM_out_significant_compounds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "57b5987d",
   "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_coeff</th>\n",
       "      <th>spoke_identifer</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.854618</td>\n",
       "      <td>inchikey:MQTAVJHICJWXBR-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.850864</td>\n",
       "      <td>inchikey:RDZNZFGKEVDNPK-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.580587</td>\n",
       "      <td>inchikey:ZWZWYGMENQVNFU-AKGZTFGVSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.413031</td>\n",
       "      <td>inchikey:GHOKWGTUZJEAQD-ZETCQYMHSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.620646</td>\n",
       "      <td>inchikey:YDGMGEXADBMOMJ-LURJTMIESA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>375</th>\n",
       "      <td>-0.118753</td>\n",
       "      <td>inchikey:GFYLSDSUCHVORB-IOSLPCCCSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>376</th>\n",
       "      <td>-0.121905</td>\n",
       "      <td>inchikey:HXHZGHRLVRFQDR-HZJYTTRNSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>377</th>\n",
       "      <td>-0.097551</td>\n",
       "      <td>inchikey:LEHOTFFKMJEONL-UHFFFAOYSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>378</th>\n",
       "      <td>0.113364</td>\n",
       "      <td>inchikey:WQXNXVUDBPYKBA-YFKPBYRVSA-N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>379</th>\n",
       "      <td>-0.151572</td>\n",
       "      <td>inchikey:BLZVZPYMHLXLHG-RQOIEFAZSA-N</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>380 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     disease_coeff                       spoke_identifer\n",
       "0        -0.854618  inchikey:MQTAVJHICJWXBR-UHFFFAOYSA-N\n",
       "1        -0.850864  inchikey:RDZNZFGKEVDNPK-UHFFFAOYSA-N\n",
       "2        -0.580587  inchikey:ZWZWYGMENQVNFU-AKGZTFGVSA-N\n",
       "3        -0.413031  inchikey:GHOKWGTUZJEAQD-ZETCQYMHSA-N\n",
       "4        -0.620646  inchikey:YDGMGEXADBMOMJ-LURJTMIESA-N\n",
       "..             ...                                   ...\n",
       "375      -0.118753  inchikey:GFYLSDSUCHVORB-IOSLPCCCSA-N\n",
       "376      -0.121905  inchikey:HXHZGHRLVRFQDR-HZJYTTRNSA-N\n",
       "377      -0.097551  inchikey:LEHOTFFKMJEONL-UHFFFAOYSA-N\n",
       "378       0.113364  inchikey:WQXNXVUDBPYKBA-YFKPBYRVSA-N\n",
       "379      -0.151572  inchikey:BLZVZPYMHLXLHG-RQOIEFAZSA-N\n",
       "\n",
       "[380 rows x 2 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GLM_out_significant_compounds_mapped_to_SPOKE = pd.merge(GLM_out_significant_compounds, compound_spoke_map, left_on=\"analyte_name\", right_on=\"name\")[[\"disease_coeff\", \"spoke_identifer\"]]\n",
    "\n",
    "GLM_out_significant_compounds_mapped_to_SPOKE.drop_duplicates(inplace=True)\n",
    "\n",
    "GLM_out_significant_compounds_mapped_to_SPOKE\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5f6a949",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}