src/merge_diets.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Merge the diets\n",
    "\n",
    "Here we will take the individual diets and convert it to a merged medium definition."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>metabolite</th>\n",
       "      <th>flux</th>\n",
       "      <th>name</th>\n",
       "      <th>hmdb</th>\n",
       "      <th>kegg.compound</th>\n",
       "      <th>pubchem.compound</th>\n",
       "      <th>inchi</th>\n",
       "      <th>chebi</th>\n",
       "      <th>reaction</th>\n",
       "      <th>global_id</th>\n",
       "      <th>ethnic_group</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>reaction</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>EX_ala_L_m</th>\n",
       "      <td>ala_L</td>\n",
       "      <td>0.106968</td>\n",
       "      <td>L-alanine</td>\n",
       "      <td>HMDB00161</td>\n",
       "      <td>C00041</td>\n",
       "      <td>5950.0</td>\n",
       "      <td>InChI=1S/C3H7NO2/c1-2(4)3(5)6/h2H,4H2,1H3,(H,5...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_ala_L_m</td>\n",
       "      <td>EX_ala_L(e)</td>\n",
       "      <td>Hadza</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>EX_arg_L_m</th>\n",
       "      <td>arg_L</td>\n",
       "      <td>0.942406</td>\n",
       "      <td>L-argininium(1+)</td>\n",
       "      <td>HMDB00517</td>\n",
       "      <td>C00062</td>\n",
       "      <td>6322.0</td>\n",
       "      <td>InChI=1S/C6H14N4O2/c7-4(5(11)12)2-1-3-10-6(8)9...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_arg_L_m</td>\n",
       "      <td>EX_arg_L(e)</td>\n",
       "      <td>Hadza</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>EX_asn_L_m</th>\n",
       "      <td>asn_L</td>\n",
       "      <td>1.666412</td>\n",
       "      <td>L-asparagine</td>\n",
       "      <td>HMDB00168</td>\n",
       "      <td>C00152</td>\n",
       "      <td>6267.0</td>\n",
       "      <td>InChI=1S/C4H8N2O3/c5-2(4(8)9)1-3(6)7/h2H,1,5H2...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_asn_L_m</td>\n",
       "      <td>EX_asn_L(e)</td>\n",
       "      <td>Hadza</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>EX_asp_L_m</th>\n",
       "      <td>asp_L</td>\n",
       "      <td>0.790868</td>\n",
       "      <td>L-aspartate(1-)</td>\n",
       "      <td>HMDB00191</td>\n",
       "      <td>C00049</td>\n",
       "      <td>5960.0</td>\n",
       "      <td>InChI=1S/C4H7NO4/c5-2(4(8)9)1-3(6)7/h2H,1,5H2,...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_asp_L_m</td>\n",
       "      <td>EX_asp_L(e)</td>\n",
       "      <td>Hadza</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>EX_ca2_m</th>\n",
       "      <td>ca2</td>\n",
       "      <td>0.677634</td>\n",
       "      <td>calcium(2+)</td>\n",
       "      <td>HMDB00464</td>\n",
       "      <td>C00076</td>\n",
       "      <td>NaN</td>\n",
       "      <td>InChI=1S/Ca/q+2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_ca2_m</td>\n",
       "      <td>EX_ca2(e)</td>\n",
       "      <td>Hadza</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           metabolite      flux              name       hmdb kegg.compound  \\\n",
       "reaction                                                                     \n",
       "EX_ala_L_m      ala_L  0.106968         L-alanine  HMDB00161        C00041   \n",
       "EX_arg_L_m      arg_L  0.942406  L-argininium(1+)  HMDB00517        C00062   \n",
       "EX_asn_L_m      asn_L  1.666412      L-asparagine  HMDB00168        C00152   \n",
       "EX_asp_L_m      asp_L  0.790868   L-aspartate(1-)  HMDB00191        C00049   \n",
       "EX_ca2_m          ca2  0.677634       calcium(2+)  HMDB00464        C00076   \n",
       "\n",
       "            pubchem.compound  \\\n",
       "reaction                       \n",
       "EX_ala_L_m            5950.0   \n",
       "EX_arg_L_m            6322.0   \n",
       "EX_asn_L_m            6267.0   \n",
       "EX_asp_L_m            5960.0   \n",
       "EX_ca2_m                 NaN   \n",
       "\n",
       "                                                        inchi  chebi  \\\n",
       "reaction                                                               \n",
       "EX_ala_L_m  InChI=1S/C3H7NO2/c1-2(4)3(5)6/h2H,4H2,1H3,(H,5...    NaN   \n",
       "EX_arg_L_m  InChI=1S/C6H14N4O2/c7-4(5(11)12)2-1-3-10-6(8)9...    NaN   \n",
       "EX_asn_L_m  InChI=1S/C4H8N2O3/c5-2(4(8)9)1-3(6)7/h2H,1,5H2...    NaN   \n",
       "EX_asp_L_m  InChI=1S/C4H7NO4/c5-2(4(8)9)1-3(6)7/h2H,1,5H2,...    NaN   \n",
       "EX_ca2_m                                      InChI=1S/Ca/q+2    NaN   \n",
       "\n",
       "              reaction    global_id ethnic_group  \n",
       "reaction                                          \n",
       "EX_ala_L_m  EX_ala_L_m  EX_ala_L(e)        Hadza  \n",
       "EX_arg_L_m  EX_arg_L_m  EX_arg_L(e)        Hadza  \n",
       "EX_asn_L_m  EX_asn_L_m  EX_asn_L(e)        Hadza  \n",
       "EX_asp_L_m  EX_asp_L_m  EX_asp_L(e)        Hadza  \n",
       "EX_ca2_m      EX_ca2_m    EX_ca2(e)        Hadza  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from micom.qiime_formats import load_qiime_medium\n",
    "\n",
    "media = {\n",
    "    \"Hadza\": \"../data/baobab_honey_antelope.qza\",\n",
    "    \"Me’Phaa\": \"../data/guerrero_mountains.qza\",\n",
    "    \"Chepang\": \"../data/himalaya.qza\"\n",
    "}\n",
    "\n",
    "diets = []\n",
    "for group in media:\n",
    "    d = load_qiime_medium(media[group])\n",
    "    d[\"ethnic_group\"] = group\n",
    "    d.flux /= 4.0  # to get growth rates comparbale with the unmtached diet\n",
    "    diets.append(d)\n",
    "diets = pd.concat(diets)\n",
    "diets.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we we will read the sample metadata and merge with the diets."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>id</th>\n",
       "      <th>ethnic_group</th>\n",
       "      <th>lifestyle_food</th>\n",
       "      <th>country</th>\n",
       "      <th>reference</th>\n",
       "      <th>metabolite</th>\n",
       "      <th>flux</th>\n",
       "      <th>name</th>\n",
       "      <th>hmdb</th>\n",
       "      <th>kegg.compound</th>\n",
       "      <th>pubchem.compound</th>\n",
       "      <th>inchi</th>\n",
       "      <th>chebi</th>\n",
       "      <th>reaction</th>\n",
       "      <th>global_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>hadza1</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>Hunter-gatherer</td>\n",
       "      <td>Tanzania</td>\n",
       "      <td>https://doi.org/10.1126/science.aan4834</td>\n",
       "      <td>ala_L</td>\n",
       "      <td>0.106968</td>\n",
       "      <td>L-alanine</td>\n",
       "      <td>HMDB00161</td>\n",
       "      <td>C00041</td>\n",
       "      <td>5950.0</td>\n",
       "      <td>InChI=1S/C3H7NO2/c1-2(4)3(5)6/h2H,4H2,1H3,(H,5...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_ala_L_m</td>\n",
       "      <td>EX_ala_L(e)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>hadza1</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>Hunter-gatherer</td>\n",
       "      <td>Tanzania</td>\n",
       "      <td>https://doi.org/10.1126/science.aan4834</td>\n",
       "      <td>arg_L</td>\n",
       "      <td>0.942406</td>\n",
       "      <td>L-argininium(1+)</td>\n",
       "      <td>HMDB00517</td>\n",
       "      <td>C00062</td>\n",
       "      <td>6322.0</td>\n",
       "      <td>InChI=1S/C6H14N4O2/c7-4(5(11)12)2-1-3-10-6(8)9...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_arg_L_m</td>\n",
       "      <td>EX_arg_L(e)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>hadza1</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>Hunter-gatherer</td>\n",
       "      <td>Tanzania</td>\n",
       "      <td>https://doi.org/10.1126/science.aan4834</td>\n",
       "      <td>asn_L</td>\n",
       "      <td>1.666412</td>\n",
       "      <td>L-asparagine</td>\n",
       "      <td>HMDB00168</td>\n",
       "      <td>C00152</td>\n",
       "      <td>6267.0</td>\n",
       "      <td>InChI=1S/C4H8N2O3/c5-2(4(8)9)1-3(6)7/h2H,1,5H2...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_asn_L_m</td>\n",
       "      <td>EX_asn_L(e)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>hadza1</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>Hunter-gatherer</td>\n",
       "      <td>Tanzania</td>\n",
       "      <td>https://doi.org/10.1126/science.aan4834</td>\n",
       "      <td>asp_L</td>\n",
       "      <td>0.790868</td>\n",
       "      <td>L-aspartate(1-)</td>\n",
       "      <td>HMDB00191</td>\n",
       "      <td>C00049</td>\n",
       "      <td>5960.0</td>\n",
       "      <td>InChI=1S/C4H7NO4/c5-2(4(8)9)1-3(6)7/h2H,1,5H2,...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_asp_L_m</td>\n",
       "      <td>EX_asp_L(e)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>hadza1</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>Hunter-gatherer</td>\n",
       "      <td>Tanzania</td>\n",
       "      <td>https://doi.org/10.1126/science.aan4834</td>\n",
       "      <td>ca2</td>\n",
       "      <td>0.677634</td>\n",
       "      <td>calcium(2+)</td>\n",
       "      <td>HMDB00464</td>\n",
       "      <td>C00076</td>\n",
       "      <td>NaN</td>\n",
       "      <td>InChI=1S/Ca/q+2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EX_ca2_m</td>\n",
       "      <td>EX_ca2(e)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       id ethnic_group   lifestyle_food   country  \\\n",
       "0  hadza1        Hadza  Hunter-gatherer  Tanzania   \n",
       "1  hadza1        Hadza  Hunter-gatherer  Tanzania   \n",
       "2  hadza1        Hadza  Hunter-gatherer  Tanzania   \n",
       "3  hadza1        Hadza  Hunter-gatherer  Tanzania   \n",
       "4  hadza1        Hadza  Hunter-gatherer  Tanzania   \n",
       "\n",
       "                                 reference metabolite      flux  \\\n",
       "0  https://doi.org/10.1126/science.aan4834      ala_L  0.106968   \n",
       "1  https://doi.org/10.1126/science.aan4834      arg_L  0.942406   \n",
       "2  https://doi.org/10.1126/science.aan4834      asn_L  1.666412   \n",
       "3  https://doi.org/10.1126/science.aan4834      asp_L  0.790868   \n",
       "4  https://doi.org/10.1126/science.aan4834        ca2  0.677634   \n",
       "\n",
       "               name       hmdb kegg.compound  pubchem.compound  \\\n",
       "0         L-alanine  HMDB00161        C00041            5950.0   \n",
       "1  L-argininium(1+)  HMDB00517        C00062            6322.0   \n",
       "2      L-asparagine  HMDB00168        C00152            6267.0   \n",
       "3   L-aspartate(1-)  HMDB00191        C00049            5960.0   \n",
       "4       calcium(2+)  HMDB00464        C00076               NaN   \n",
       "\n",
       "                                               inchi  chebi    reaction  \\\n",
       "0  InChI=1S/C3H7NO2/c1-2(4)3(5)6/h2H,4H2,1H3,(H,5...    NaN  EX_ala_L_m   \n",
       "1  InChI=1S/C6H14N4O2/c7-4(5(11)12)2-1-3-10-6(8)9...    NaN  EX_arg_L_m   \n",
       "2  InChI=1S/C4H8N2O3/c5-2(4(8)9)1-3(6)7/h2H,1,5H2...    NaN  EX_asn_L_m   \n",
       "3  InChI=1S/C4H7NO4/c5-2(4(8)9)1-3(6)7/h2H,1,5H2,...    NaN  EX_asp_L_m   \n",
       "4                                    InChI=1S/Ca/q+2    NaN    EX_ca2_m   \n",
       "\n",
       "     global_id  \n",
       "0  EX_ala_L(e)  \n",
       "1  EX_arg_L(e)  \n",
       "2  EX_asn_L(e)  \n",
       "3  EX_asp_L(e)  \n",
       "4    EX_ca2(e)  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "meta = pd.read_csv(\"../data/metadata.tsv\", sep=\"\\t\")\n",
    "merged = meta.merge(diets, on=\"ethnic_group\")\n",
    "merged.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lets check that we merged correctly."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "assert diets.shape[0] * 3 == merged.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Finally we rename and save the merged diet table."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "merged.rename(columns={\"id\": \"sample_id\"}, inplace=True)\n",
    "merged.to_csv(\"../data/per_sample_media.csv\", index=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.7 ('micom')",
   "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": "3.10.7"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "c991a7ed881363492957ff225bb30af9d5174cd8515a21cbef71fcaa303e4050"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}