{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import pathlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Metadata_Source</th>\n",
       "      <th>Metadata_Plate</th>\n",
       "      <th>Metadata_Well</th>\n",
       "      <th>Metadata_JCP2022</th>\n",
       "      <th>Cells_AreaShape_Area</th>\n",
       "      <th>Cells_AreaShape_BoundingBoxArea</th>\n",
       "      <th>Cells_AreaShape_BoundingBoxMaximum_X</th>\n",
       "      <th>Cells_AreaShape_BoundingBoxMaximum_Y</th>\n",
       "      <th>Cells_AreaShape_BoundingBoxMinimum_X</th>\n",
       "      <th>Cells_AreaShape_BoundingBoxMinimum_Y</th>\n",
       "      <th>...</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_10_02_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_10_03_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_3_00_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_3_01_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_3_02_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_3_03_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_5_00_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_5_01_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_5_02_256</th>\n",
       "      <th>Nuclei_Texture_Variance_RNA_5_03_256</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>source_2</td>\n",
       "      <td>1053597806</td>\n",
       "      <td>A01</td>\n",
       "      <td>JCP2022_085227</td>\n",
       "      <td>-0.988041</td>\n",
       "      <td>-0.907001</td>\n",
       "      <td>0.096069</td>\n",
       "      <td>0.323007</td>\n",
       "      <td>0.146602</td>\n",
       "      <td>0.534867</td>\n",
       "      <td>...</td>\n",
       "      <td>1.605010</td>\n",
       "      <td>1.693312</td>\n",
       "      <td>1.615753</td>\n",
       "      <td>1.604152</td>\n",
       "      <td>1.624943</td>\n",
       "      <td>1.612151</td>\n",
       "      <td>1.589302</td>\n",
       "      <td>1.594195</td>\n",
       "      <td>1.627130</td>\n",
       "      <td>1.610461</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>source_2</td>\n",
       "      <td>1053597806</td>\n",
       "      <td>K22</td>\n",
       "      <td>JCP2022_049123</td>\n",
       "      <td>-0.247098</td>\n",
       "      <td>-0.389633</td>\n",
       "      <td>-0.828097</td>\n",
       "      <td>0.727857</td>\n",
       "      <td>-0.708414</td>\n",
       "      <td>0.887224</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.696735</td>\n",
       "      <td>-0.547206</td>\n",
       "      <td>-0.737023</td>\n",
       "      <td>-0.739017</td>\n",
       "      <td>-0.741798</td>\n",
       "      <td>-0.741577</td>\n",
       "      <td>-0.724849</td>\n",
       "      <td>-0.714124</td>\n",
       "      <td>-0.755699</td>\n",
       "      <td>-0.729048</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>source_2</td>\n",
       "      <td>1053597806</td>\n",
       "      <td>K21</td>\n",
       "      <td>JCP2022_025146</td>\n",
       "      <td>0.882814</td>\n",
       "      <td>0.635229</td>\n",
       "      <td>-0.866758</td>\n",
       "      <td>1.593473</td>\n",
       "      <td>-0.798442</td>\n",
       "      <td>1.682966</td>\n",
       "      <td>...</td>\n",
       "      <td>0.427341</td>\n",
       "      <td>0.699385</td>\n",
       "      <td>0.506531</td>\n",
       "      <td>0.478770</td>\n",
       "      <td>0.518382</td>\n",
       "      <td>0.476467</td>\n",
       "      <td>0.454404</td>\n",
       "      <td>0.473200</td>\n",
       "      <td>0.500973</td>\n",
       "      <td>0.484033</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>source_2</td>\n",
       "      <td>1053597806</td>\n",
       "      <td>K20</td>\n",
       "      <td>JCP2022_109006</td>\n",
       "      <td>1.551945</td>\n",
       "      <td>1.409719</td>\n",
       "      <td>-0.624934</td>\n",
       "      <td>-1.552434</td>\n",
       "      <td>-0.634504</td>\n",
       "      <td>-1.846982</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.016852</td>\n",
       "      <td>0.321772</td>\n",
       "      <td>0.019403</td>\n",
       "      <td>-0.023218</td>\n",
       "      <td>0.025426</td>\n",
       "      <td>-0.020011</td>\n",
       "      <td>-0.036913</td>\n",
       "      <td>-0.064012</td>\n",
       "      <td>-0.037481</td>\n",
       "      <td>-0.048811</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>source_2</td>\n",
       "      <td>1053597806</td>\n",
       "      <td>K19</td>\n",
       "      <td>JCP2022_040739</td>\n",
       "      <td>0.782228</td>\n",
       "      <td>0.394115</td>\n",
       "      <td>0.016284</td>\n",
       "      <td>0.335031</td>\n",
       "      <td>0.009199</td>\n",
       "      <td>0.228013</td>\n",
       "      <td>...</td>\n",
       "      <td>0.549137</td>\n",
       "      <td>0.589808</td>\n",
       "      <td>0.643868</td>\n",
       "      <td>0.616816</td>\n",
       "      <td>0.655204</td>\n",
       "      <td>0.615139</td>\n",
       "      <td>0.594326</td>\n",
       "      <td>0.588221</td>\n",
       "      <td>0.632808</td>\n",
       "      <td>0.615094</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 3184 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Metadata_Source Metadata_Plate Metadata_Well Metadata_JCP2022  \\\n",
       "0        source_2     1053597806           A01   JCP2022_085227   \n",
       "1        source_2     1053597806           K22   JCP2022_049123   \n",
       "2        source_2     1053597806           K21   JCP2022_025146   \n",
       "3        source_2     1053597806           K20   JCP2022_109006   \n",
       "4        source_2     1053597806           K19   JCP2022_040739   \n",
       "\n",
       "   Cells_AreaShape_Area  Cells_AreaShape_BoundingBoxArea  \\\n",
       "0             -0.988041                        -0.907001   \n",
       "1             -0.247098                        -0.389633   \n",
       "2              0.882814                         0.635229   \n",
       "3              1.551945                         1.409719   \n",
       "4              0.782228                         0.394115   \n",
       "\n",
       "   Cells_AreaShape_BoundingBoxMaximum_X  Cells_AreaShape_BoundingBoxMaximum_Y  \\\n",
       "0                              0.096069                              0.323007   \n",
       "1                             -0.828097                              0.727857   \n",
       "2                             -0.866758                              1.593473   \n",
       "3                             -0.624934                             -1.552434   \n",
       "4                              0.016284                              0.335031   \n",
       "\n",
       "   Cells_AreaShape_BoundingBoxMinimum_X  Cells_AreaShape_BoundingBoxMinimum_Y  \\\n",
       "0                              0.146602                              0.534867   \n",
       "1                             -0.708414                              0.887224   \n",
       "2                             -0.798442                              1.682966   \n",
       "3                             -0.634504                             -1.846982   \n",
       "4                              0.009199                              0.228013   \n",
       "\n",
       "   ...  Nuclei_Texture_Variance_RNA_10_02_256  \\\n",
       "0  ...                               1.605010   \n",
       "1  ...                              -0.696735   \n",
       "2  ...                               0.427341   \n",
       "3  ...                              -0.016852   \n",
       "4  ...                               0.549137   \n",
       "\n",
       "   Nuclei_Texture_Variance_RNA_10_03_256  \\\n",
       "0                               1.693312   \n",
       "1                              -0.547206   \n",
       "2                               0.699385   \n",
       "3                               0.321772   \n",
       "4                               0.589808   \n",
       "\n",
       "   Nuclei_Texture_Variance_RNA_3_00_256  Nuclei_Texture_Variance_RNA_3_01_256  \\\n",
       "0                              1.615753                              1.604152   \n",
       "1                             -0.737023                             -0.739017   \n",
       "2                              0.506531                              0.478770   \n",
       "3                              0.019403                             -0.023218   \n",
       "4                              0.643868                              0.616816   \n",
       "\n",
       "   Nuclei_Texture_Variance_RNA_3_02_256  Nuclei_Texture_Variance_RNA_3_03_256  \\\n",
       "0                              1.624943                              1.612151   \n",
       "1                             -0.741798                             -0.741577   \n",
       "2                              0.518382                              0.476467   \n",
       "3                              0.025426                             -0.020011   \n",
       "4                              0.655204                              0.615139   \n",
       "\n",
       "   Nuclei_Texture_Variance_RNA_5_00_256  Nuclei_Texture_Variance_RNA_5_01_256  \\\n",
       "0                              1.589302                              1.594195   \n",
       "1                             -0.724849                             -0.714124   \n",
       "2                              0.454404                              0.473200   \n",
       "3                             -0.036913                             -0.064012   \n",
       "4                              0.594326                              0.588221   \n",
       "\n",
       "   Nuclei_Texture_Variance_RNA_5_02_256  Nuclei_Texture_Variance_RNA_5_03_256  \n",
       "0                              1.627130                              1.610461  \n",
       "1                             -0.755699                             -0.729048  \n",
       "2                              0.500973                              0.484033  \n",
       "3                             -0.037481                             -0.048811  \n",
       "4                              0.632808                              0.615094  \n",
       "\n",
       "[5 rows x 3184 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "path = pathlib.Path(\"/home/ubuntu/giovanni/data\")\n",
    "\n",
    "df = pd.read_parquet(path / 'profiles_var_mad_int.parquet')\n",
    "\n",
    "df.head()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<StringArray>\n",
       "[ 'source_2',  'source_6',  'source_8',  'source_5',  'source_3',  'source_7',\n",
       " 'source_11', 'source_10',  'source_9',  'source_1']\n",
       "Length: 10, dtype: string"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Metadata_Source.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Downloading data from 'https://zenodo.org/records/12211976/files/babel.db' to file '/home/ubuntu/.cache/pooch/2eaa6a2f4915f72d7100683f53982ed8-babel.db'.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Metadata_Source', 'Metadata_Plate', 'Metadata_Well', 'Metadata_JCP2022', 'Cells_AreaShape_Area', 'Cells_AreaShape_BoundingBoxArea']\n"
     ]
    }
   ],
   "source": [
    "import polars as pl\n",
    "from broad_babel.query import get_mapper\n",
    "\n",
    "INDEX_FILE = \"https://raw.githubusercontent.com/jump-cellpainting/datasets/50cd2ab93749ccbdb0919d3adf9277c14b6343dd/manifests/profile_index.csv\"\n",
    "CRISPR_URL = pl.read_csv(INDEX_FILE).filter(pl.col(\"subset\") == \"compound_interpretable\").item(0, \"url\")\n",
    "profiles = pl.scan_parquet(CRISPR_URL)\n",
    "print(profiles.collect_schema().names()[:6])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "jcp_ids = (\n",
    "    profiles.select(pl.col(\"Metadata_JCP2022\")).unique().collect().to_series().sort()\n",
    ")\n",
    "subsample = jcp_ids.sample(10, seed=42)\n",
    "subsample = (*subsample, \"JCP2022_800002\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "name_mapper = get_mapper(\n",
    "    (*subsample, \"JCP2022_800002\"),\n",
    "    input_column=\"JCP2022\",\n",
    "    output_columns=\"JCP2022,standard_key\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'JCP2022_028278': 'GWTBXQQPVRNIPZ-UHFFFAOYSA-N',\n",
       " 'JCP2022_027032': 'GPXONAQDNOJZDS-UHFFFAOYSA-N',\n",
       " 'JCP2022_062945': 'OCQUGGYNYZAZCD-UHFFFAOYSA-N',\n",
       " 'JCP2022_034511': 'IEGWXHZAERRPAA-UHFFFAOYSA-N',\n",
       " 'JCP2022_011184': 'CHOCUHAMWSTXQB-UHFFFAOYSA-N',\n",
       " 'JCP2022_035521': 'IJXNECHDDWQPST-UHFFFAOYSA-N',\n",
       " 'JCP2022_037172': 'ISRUTBYDVYWAGL-UHFFFAOYSA-N',\n",
       " 'JCP2022_001698': 'AIYDZKWHEKBPBD-UHFFFAOYSA-N',\n",
       " 'JCP2022_017646': 'DQUXSWDRCMFRKS-UHFFFAOYSA-N',\n",
       " 'JCP2022_018617': 'DWHZCHWSVPXJNC-UHFFFAOYSA-N',\n",
       " 'JCP2022_800002': 'non-targeting'}"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "name_mapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "import anndata as ad\n",
    "adata = ad.read_h5ad(path / '20250417.diff_vision_scores_pseudobulk.public.h5ad')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>plate</th>\n",
       "      <th>Cell_Name_Vevo</th>\n",
       "      <th>Cell_ID_Cellosaur</th>\n",
       "      <th>drug</th>\n",
       "      <th>concentration</th>\n",
       "      <th>concentration_unit</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4</td>\n",
       "      <td>A549</td>\n",
       "      <td>CVCL_0023</td>\n",
       "      <td>8-Hydroxyquinoline</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>HS-578T</td>\n",
       "      <td>CVCL_0332</td>\n",
       "      <td>8-Hydroxyquinoline</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>HCT15</td>\n",
       "      <td>CVCL_0292</td>\n",
       "      <td>8-Hydroxyquinoline</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>HOP62</td>\n",
       "      <td>CVCL_1285</td>\n",
       "      <td>8-Hydroxyquinoline</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>SK-MEL-2</td>\n",
       "      <td>CVCL_0069</td>\n",
       "      <td>8-Hydroxyquinoline</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</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>60771</th>\n",
       "      <td>12</td>\n",
       "      <td>hTERT-HPNE</td>\n",
       "      <td>CVCL_C466</td>\n",
       "      <td>Adagrasib</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60772</th>\n",
       "      <td>12</td>\n",
       "      <td>NCI-H23</td>\n",
       "      <td>CVCL_1547</td>\n",
       "      <td>Adagrasib</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60773</th>\n",
       "      <td>12</td>\n",
       "      <td>NCI-H1792</td>\n",
       "      <td>CVCL_1495</td>\n",
       "      <td>Adagrasib</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60774</th>\n",
       "      <td>12</td>\n",
       "      <td>NCI-H2030</td>\n",
       "      <td>CVCL_1517</td>\n",
       "      <td>Adagrasib</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60775</th>\n",
       "      <td>12</td>\n",
       "      <td>LOX-IMVI</td>\n",
       "      <td>CVCL_1381</td>\n",
       "      <td>Adagrasib</td>\n",
       "      <td>0.05</td>\n",
       "      <td>uM</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>60776 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       plate Cell_Name_Vevo Cell_ID_Cellosaur                drug  \\\n",
       "0          4           A549         CVCL_0023  8-Hydroxyquinoline   \n",
       "1          4        HS-578T         CVCL_0332  8-Hydroxyquinoline   \n",
       "2          4          HCT15         CVCL_0292  8-Hydroxyquinoline   \n",
       "3          4          HOP62         CVCL_1285  8-Hydroxyquinoline   \n",
       "4          4       SK-MEL-2         CVCL_0069  8-Hydroxyquinoline   \n",
       "...      ...            ...               ...                 ...   \n",
       "60771     12     hTERT-HPNE         CVCL_C466           Adagrasib   \n",
       "60772     12        NCI-H23         CVCL_1547           Adagrasib   \n",
       "60773     12      NCI-H1792         CVCL_1495           Adagrasib   \n",
       "60774     12      NCI-H2030         CVCL_1517           Adagrasib   \n",
       "60775     12       LOX-IMVI         CVCL_1381           Adagrasib   \n",
       "\n",
       "       concentration concentration_unit  \n",
       "0               0.05                 uM  \n",
       "1               0.05                 uM  \n",
       "2               0.05                 uM  \n",
       "3               0.05                 uM  \n",
       "4               0.05                 uM  \n",
       "...              ...                ...  \n",
       "60771           0.05                 uM  \n",
       "60772           0.05                 uM  \n",
       "60773           0.05                 uM  \n",
       "60774           0.05                 uM  \n",
       "60775           0.05                 uM  \n",
       "\n",
       "[60776 rows x 6 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "adata.obs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e505761d4f584228ae80a33867c6ba22",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Resolving data files:   0%|          | 0/3388 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "drug_metadata =  load_dataset(\"tahoebio/Tahoe-100M\",\"drug_metadata\", split=\"train\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "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>drug</th>\n",
       "      <th>targets</th>\n",
       "      <th>moa-broad</th>\n",
       "      <th>moa-fine</th>\n",
       "      <th>human-approved</th>\n",
       "      <th>clinical-trials</th>\n",
       "      <th>gpt-notes-approval</th>\n",
       "      <th>canonical_smiles</th>\n",
       "      <th>pubchem_cid</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Talc</td>\n",
       "      <td>None</td>\n",
       "      <td>unclear</td>\n",
       "      <td>unclear</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Talc used in pharma and cosmetics; safety unde...</td>\n",
       "      <td>[OH-].[OH-].[O-][Si]12O[Si]3(O[Si](O1)(O[Si](O...</td>\n",
       "      <td>165411828.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bortezomib</td>\n",
       "      <td>PSMB5</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>Proteasome inhibitor</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Approved for multiple myeloma and mantle cell ...</td>\n",
       "      <td>B(C(CC(C)C)NC(=O)C(CC1=CC=CC=C1)NC(=O)C2=NC=CN...</td>\n",
       "      <td>387447.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ixazomib</td>\n",
       "      <td>PSMB5</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>Proteasome inhibitor</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Approved for multiple myeloma treatment.</td>\n",
       "      <td>B(C(CC(C)C)NC(=O)CNC(=O)C1=C(C=CC(=C1)Cl)Cl)(O)O</td>\n",
       "      <td>25183872.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ixazomib citrate</td>\n",
       "      <td>PSMB1, PSMB2, PSMB5</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>Proteasome inhibitor</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Approved for multiple myeloma treatment as par...</td>\n",
       "      <td>B1(OC(=O)C(O1)(CC(=O)O)CC(=O)O)C(CC(C)C)NC(=O)...</td>\n",
       "      <td>56844015.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Lactate (calcium)</td>\n",
       "      <td>None</td>\n",
       "      <td>unclear</td>\n",
       "      <td>unclear</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Used in medical settings, but not specifically...</td>\n",
       "      <td>C.CC(C(=O)[O-])O.[Ca+2]</td>\n",
       "      <td>168311648.0</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>374</th>\n",
       "      <td>Verteporfin</td>\n",
       "      <td>YAP1</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>unclear</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Used in photodynamic therapy for macular degen...</td>\n",
       "      <td>None</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>375</th>\n",
       "      <td>Quinidine (15% dihydroquinidine)</td>\n",
       "      <td>KCNH2</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>unclear</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Approved for arrhythmias as part of quinine al...</td>\n",
       "      <td>COC1=CC2=C(C=CN=C2C=C1)[C@@H]([C@H]3C[C@@H]4CC...</td>\n",
       "      <td>441074.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>376</th>\n",
       "      <td>Canagliflozin (hemihydrate)</td>\n",
       "      <td>SLC5A2</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>Glucose transporter inhibitor</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Approved for type 2 diabetes.</td>\n",
       "      <td>CC1=C(C=C(C=C1)[C@H]2[C@@H]([C@H]([C@@H]([C@H]...</td>\n",
       "      <td>24997615.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>377</th>\n",
       "      <td>Osimertinib (mesylate)</td>\n",
       "      <td>EGFR</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>EGFR/ERBB inhibitor</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>Approved for non-small cell lung cancer treatm...</td>\n",
       "      <td>CN1C=C(C2=CC=CC=C21)C3=NC(=NC=C3)NC4=C(C=C(C(=...</td>\n",
       "      <td>78357807.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>378</th>\n",
       "      <td>γ-Oryzanol</td>\n",
       "      <td>None</td>\n",
       "      <td>inhibitor/antagonist</td>\n",
       "      <td>DNA methyltransferase inhibitor</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>Used in supplements; limited human data.</td>\n",
       "      <td>C[C@H](CCC=C(C)C)[C@H]1CC[C@@]2([C@@]1(CC[C@]3...</td>\n",
       "      <td>5282164.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>379 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 drug              targets  \\\n",
       "0                                Talc                 None   \n",
       "1                          Bortezomib                PSMB5   \n",
       "2                            Ixazomib                PSMB5   \n",
       "3                    Ixazomib citrate  PSMB1, PSMB2, PSMB5   \n",
       "4                   Lactate (calcium)                 None   \n",
       "..                                ...                  ...   \n",
       "374                       Verteporfin                 YAP1   \n",
       "375  Quinidine (15% dihydroquinidine)                KCNH2   \n",
       "376       Canagliflozin (hemihydrate)               SLC5A2   \n",
       "377            Osimertinib (mesylate)                 EGFR   \n",
       "378                        γ-Oryzanol                 None   \n",
       "\n",
       "                moa-broad                         moa-fine human-approved  \\\n",
       "0                 unclear                          unclear            yes   \n",
       "1    inhibitor/antagonist             Proteasome inhibitor            yes   \n",
       "2    inhibitor/antagonist             Proteasome inhibitor            yes   \n",
       "3    inhibitor/antagonist             Proteasome inhibitor            yes   \n",
       "4                 unclear                          unclear            yes   \n",
       "..                    ...                              ...            ...   \n",
       "374  inhibitor/antagonist                          unclear            yes   \n",
       "375  inhibitor/antagonist                          unclear            yes   \n",
       "376  inhibitor/antagonist    Glucose transporter inhibitor            yes   \n",
       "377  inhibitor/antagonist              EGFR/ERBB inhibitor            yes   \n",
       "378  inhibitor/antagonist  DNA methyltransferase inhibitor             no   \n",
       "\n",
       "    clinical-trials                                 gpt-notes-approval  \\\n",
       "0               yes  Talc used in pharma and cosmetics; safety unde...   \n",
       "1               yes  Approved for multiple myeloma and mantle cell ...   \n",
       "2               yes           Approved for multiple myeloma treatment.   \n",
       "3               yes  Approved for multiple myeloma treatment as par...   \n",
       "4               yes  Used in medical settings, but not specifically...   \n",
       "..              ...                                                ...   \n",
       "374             yes  Used in photodynamic therapy for macular degen...   \n",
       "375             yes  Approved for arrhythmias as part of quinine al...   \n",
       "376             yes                      Approved for type 2 diabetes.   \n",
       "377             yes  Approved for non-small cell lung cancer treatm...   \n",
       "378             yes           Used in supplements; limited human data.   \n",
       "\n",
       "                                      canonical_smiles  pubchem_cid  \n",
       "0    [OH-].[OH-].[O-][Si]12O[Si]3(O[Si](O1)(O[Si](O...  165411828.0  \n",
       "1    B(C(CC(C)C)NC(=O)C(CC1=CC=CC=C1)NC(=O)C2=NC=CN...     387447.0  \n",
       "2     B(C(CC(C)C)NC(=O)CNC(=O)C1=C(C=CC(=C1)Cl)Cl)(O)O   25183872.0  \n",
       "3    B1(OC(=O)C(O1)(CC(=O)O)CC(=O)O)C(CC(C)C)NC(=O)...   56844015.0  \n",
       "4                              C.CC(C(=O)[O-])O.[Ca+2]  168311648.0  \n",
       "..                                                 ...          ...  \n",
       "374                                               None          NaN  \n",
       "375  COC1=CC2=C(C=CN=C2C=C1)[C@@H]([C@H]3C[C@@H]4CC...     441074.0  \n",
       "376  CC1=C(C=C(C=C1)[C@H]2[C@@H]([C@H]([C@@H]([C@H]...   24997615.0  \n",
       "377  CN1C=C(C2=CC=CC=C21)C3=NC(=NC=C3)NC4=C(C=C(C(=...   78357807.0  \n",
       "378  C[C@H](CCC=C(C)C)[C@H]1CC[C@@]2([C@@]1(CC[C@]3...    5282164.0  \n",
       "\n",
       "[379 rows x 9 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "drug_metadata.to_pandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "mapper = get_mapper(query=\"compound\", input_column=\"plate_type\", output_columns=\"JCP2022,pert_type\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'JCP2022_014696': 'trt',\n",
       " 'JCP2022_040501': 'trt',\n",
       " 'JCP2022_051313': 'trt',\n",
       " 'JCP2022_061545': 'trt',\n",
       " 'JCP2022_062817': 'trt',\n",
       " 'JCP2022_043906': 'trt',\n",
       " 'JCP2022_027359': 'trt',\n",
       " 'JCP2022_026224': 'trt',\n",
       " 'JCP2022_052479': 'trt',\n",
       " 'JCP2022_071231': 'trt',\n",
       " 'JCP2022_072172': 'trt',\n",
       " 'JCP2022_103039': 'trt',\n",
       " 'JCP2022_090879': 'trt',\n",
       " 'JCP2022_080043': 'trt',\n",
       " 'JCP2022_070637': 'trt',\n",
       " 'JCP2022_102613': 'trt',\n",
       " 'JCP2022_008834': 'trt',\n",
       " 'JCP2022_095349': 'trt',\n",
       " 'JCP2022_002648': 'trt',\n",
       " 'JCP2022_035724': 'trt',\n",
       " 'JCP2022_081339': 'trt',\n",
       " 'JCP2022_022059': 'trt',\n",
       " 'JCP2022_025846': 'trt',\n",
       " 'JCP2022_018782': 'trt',\n",
       " 'JCP2022_026446': 'trt',\n",
       " 'JCP2022_063737': 'trt',\n",
       " 'JCP2022_041599': 'trt',\n",
       " 'JCP2022_043335': 'trt',\n",
       " 'JCP2022_000492': 'trt',\n",
       " 'JCP2022_079186': 'trt',\n",
       " 'JCP2022_088316': 'trt',\n",
       " 'JCP2022_011773': 'trt',\n",
       " 'JCP2022_092722': 'trt',\n",
       " 'JCP2022_041977': 'trt',\n",
       " 'JCP2022_047220': 'trt',\n",
       " 'JCP2022_047933': 'trt',\n",
       " 'JCP2022_065216': 'trt',\n",
       " 'JCP2022_099000': 'trt',\n",
       " 'JCP2022_103357': 'trt',\n",
       " 'JCP2022_000339': 'trt',\n",
       " 'JCP2022_107140': 'trt',\n",
       " 'JCP2022_013430': 'trt',\n",
       " 'JCP2022_087201': 'trt',\n",
       " 'JCP2022_011595': 'trt',\n",
       " 'JCP2022_070630': 'trt',\n",
       " 'JCP2022_092179': 'trt',\n",
       " 'JCP2022_069828': 'trt',\n",
       " 'JCP2022_055904': 'trt',\n",
       " 'JCP2022_017996': 'trt',\n",
       " 'JCP2022_061637': 'trt',\n",
       " 'JCP2022_096916': 'trt',\n",
       " 'JCP2022_006582': 'trt',\n",
       " 'JCP2022_097431': 'trt',\n",
       " 'JCP2022_024598': 'trt',\n",
       " 'JCP2022_078000': 'trt',\n",
       " 'JCP2022_045620': 'trt',\n",
       " 'JCP2022_046625': 'trt',\n",
       " 'JCP2022_071459': 'trt',\n",
       " 'JCP2022_103790': 'trt',\n",
       " 'JCP2022_105517': 'trt',\n",
       " 'JCP2022_025925': 'trt',\n",
       " 'JCP2022_060110': 'trt',\n",
       " 'JCP2022_066901': 'trt',\n",
       " 'JCP2022_103655': 'trt',\n",
       " 'JCP2022_106824': 'trt',\n",
       " 'JCP2022_035319': 'trt',\n",
       " 'JCP2022_011446': 'trt',\n",
       " 'JCP2022_043907': 'trt',\n",
       " 'JCP2022_061080': 'trt',\n",
       " 'JCP2022_005050': 'trt',\n",
       " 'JCP2022_050618': 'trt',\n",
       " 'JCP2022_112725': 'trt',\n",
       " 'JCP2022_007904': 'trt',\n",
       " 'JCP2022_005187': 'trt',\n",
       " 'JCP2022_108465': 'trt',\n",
       " 'JCP2022_111105': 'trt',\n",
       " 'JCP2022_046857': 'trt',\n",
       " 'JCP2022_034742': 'trt',\n",
       " 'JCP2022_089724': 'trt',\n",
       " 'JCP2022_097397': 'trt',\n",
       " 'JCP2022_068156': 'trt',\n",
       " 'JCP2022_114874': 'trt',\n",
       " 'JCP2022_116168': 'trt',\n",
       " 'JCP2022_070693': 'trt',\n",
       " 'JCP2022_036849': 'trt',\n",
       " 'JCP2022_043036': 'trt',\n",
       " 'JCP2022_017100': 'trt',\n",
       " 'JCP2022_101475': 'trt',\n",
       " 'JCP2022_053420': 'trt',\n",
       " 'JCP2022_088757': 'trt',\n",
       " 'JCP2022_031073': 'trt',\n",
       " 'JCP2022_025273': 'trt',\n",
       " 'JCP2022_109840': 'trt',\n",
       " 'JCP2022_033250': 'trt',\n",
       " 'JCP2022_052425': 'trt',\n",
       " 'JCP2022_097670': 'trt',\n",
       " 'JCP2022_113391': 'trt',\n",
       " 'JCP2022_060489': 'trt',\n",
       " 'JCP2022_114914': 'trt',\n",
       " 'JCP2022_034056': 'trt',\n",
       " 'JCP2022_028881': 'trt',\n",
       " 'JCP2022_025776': 'trt',\n",
       " 'JCP2022_064707': 'trt',\n",
       " 'JCP2022_033186': 'trt',\n",
       " 'JCP2022_062055': 'trt',\n",
       " 'JCP2022_056918': 'trt',\n",
       " 'JCP2022_064165': 'trt',\n",
       " 'JCP2022_099195': 'trt',\n",
       " 'JCP2022_100208': 'trt',\n",
       " 'JCP2022_021185': 'trt',\n",
       " 'JCP2022_102862': 'trt',\n",
       " 'JCP2022_049008': 'trt',\n",
       " 'JCP2022_050716': 'trt',\n",
       " 'JCP2022_045889': 'trt',\n",
       " 'JCP2022_110901': 'trt',\n",
       " 'JCP2022_053830': 'trt',\n",
       " 'JCP2022_004472': 'trt',\n",
       " 'JCP2022_007609': 'trt',\n",
       " 'JCP2022_077576': 'trt',\n",
       " 'JCP2022_049700': 'trt',\n",
       " 'JCP2022_019472': 'trt',\n",
       " 'JCP2022_035089': 'trt',\n",
       " 'JCP2022_071756': 'trt',\n",
       " 'JCP2022_078384': 'trt',\n",
       " 'JCP2022_108990': 'trt',\n",
       " 'JCP2022_049374': 'trt',\n",
       " 'JCP2022_014308': 'trt',\n",
       " 'JCP2022_032354': 'trt',\n",
       " 'JCP2022_043173': 'trt',\n",
       " 'JCP2022_042464': 'trt',\n",
       " 'JCP2022_116448': 'trt',\n",
       " 'JCP2022_011189': 'trt',\n",
       " 'JCP2022_011654': 'trt',\n",
       " 'JCP2022_040936': 'trt',\n",
       " 'JCP2022_077185': 'trt',\n",
       " 'JCP2022_043104': 'trt',\n",
       " 'JCP2022_056544': 'trt',\n",
       " 'JCP2022_104693': 'trt',\n",
       " 'JCP2022_051791': 'trt',\n",
       " 'JCP2022_050200': 'trt',\n",
       " 'JCP2022_037517': 'trt',\n",
       " 'JCP2022_025635': 'trt',\n",
       " 'JCP2022_073793': 'trt',\n",
       " 'JCP2022_065546': 'trt',\n",
       " 'JCP2022_083345': 'trt',\n",
       " 'JCP2022_049798': 'trt',\n",
       " 'JCP2022_085073': 'trt',\n",
       " 'JCP2022_045349': 'trt',\n",
       " 'JCP2022_088325': 'trt',\n",
       " 'JCP2022_078793': 'trt',\n",
       " 'JCP2022_002312': 'trt',\n",
       " 'JCP2022_113310': 'trt',\n",
       " 'JCP2022_038578': 'trt',\n",
       " 'JCP2022_042376': 'trt',\n",
       " 'JCP2022_099157': 'trt',\n",
       " 'JCP2022_061490': 'trt',\n",
       " 'JCP2022_030054': 'trt',\n",
       " 'JCP2022_039891': 'trt',\n",
       " 'JCP2022_111672': 'trt',\n",
       " 'JCP2022_029111': 'trt',\n",
       " 'JCP2022_031787': 'trt',\n",
       " 'JCP2022_039131': 'trt',\n",
       " 'JCP2022_055303': 'trt',\n",
       " 'JCP2022_015348': 'trt',\n",
       " 'JCP2022_009924': 'trt',\n",
       " 'JCP2022_013726': 'trt',\n",
       " 'JCP2022_050505': 'trt',\n",
       " 'JCP2022_116376': 'trt',\n",
       " 'JCP2022_034923': 'trt',\n",
       " 'JCP2022_085592': 'trt',\n",
       " 'JCP2022_011493': 'trt',\n",
       " 'JCP2022_104744': 'trt',\n",
       " 'JCP2022_076384': 'trt',\n",
       " 'JCP2022_088480': 'trt',\n",
       " 'JCP2022_029234': 'trt',\n",
       " 'JCP2022_072059': 'trt',\n",
       " 'JCP2022_101584': 'trt',\n",
       " 'JCP2022_101742': 'trt',\n",
       " 'JCP2022_042355': 'trt',\n",
       " 'JCP2022_110916': 'trt',\n",
       " 'JCP2022_055174': 'trt',\n",
       " 'JCP2022_033836': 'trt',\n",
       " 'JCP2022_049717': 'trt',\n",
       " 'JCP2022_012579': 'trt',\n",
       " 'JCP2022_068661': 'trt',\n",
       " 'JCP2022_069548': 'trt',\n",
       " 'JCP2022_084237': 'trt',\n",
       " 'JCP2022_038115': 'trt',\n",
       " 'JCP2022_083136': 'trt',\n",
       " 'JCP2022_055445': 'trt',\n",
       " 'JCP2022_038586': 'trt',\n",
       " 'JCP2022_090077': 'trt',\n",
       " 'JCP2022_036557': 'trt',\n",
       " 'JCP2022_035327': 'trt',\n",
       " 'JCP2022_093748': 'trt',\n",
       " 'JCP2022_043525': 'trt',\n",
       " 'JCP2022_077504': 'trt',\n",
       " 'JCP2022_012371': 'trt',\n",
       " 'JCP2022_072791': 'trt',\n",
       " 'JCP2022_005067': 'trt',\n",
       " 'JCP2022_037710': 'trt',\n",
       " 'JCP2022_096999': 'trt',\n",
       " 'JCP2022_011709': 'trt',\n",
       " 'JCP2022_091449': 'trt',\n",
       " 'JCP2022_072317': 'trt',\n",
       " 'JCP2022_002024': 'trt',\n",
       " 'JCP2022_076125': 'trt',\n",
       " 'JCP2022_081171': 'trt',\n",
       " 'JCP2022_063286': 'trt',\n",
       " 'JCP2022_074951': 'trt',\n",
       " 'JCP2022_076028': 'trt',\n",
       " 'JCP2022_010466': 'trt',\n",
       " 'JCP2022_014464': 'trt',\n",
       " 'JCP2022_066528': 'trt',\n",
       " 'JCP2022_052986': 'trt',\n",
       " 'JCP2022_102015': 'trt',\n",
       " 'JCP2022_070267': 'trt',\n",
       " 'JCP2022_092413': 'trt',\n",
       " 'JCP2022_014994': 'trt',\n",
       " 'JCP2022_023487': 'trt',\n",
       " 'JCP2022_084110': 'trt',\n",
       " 'JCP2022_114582': 'trt',\n",
       " 'JCP2022_042079': 'trt',\n",
       " 'JCP2022_060265': 'trt',\n",
       " 'JCP2022_067828': 'trt',\n",
       " 'JCP2022_086376': 'trt',\n",
       " 'JCP2022_056108': 'trt',\n",
       " 'JCP2022_043512': 'trt',\n",
       " 'JCP2022_034609': 'trt',\n",
       " 'JCP2022_008266': 'trt',\n",
       " 'JCP2022_061313': 'trt',\n",
       " 'JCP2022_040786': 'trt',\n",
       " 'JCP2022_038166': 'trt',\n",
       " 'JCP2022_048590': 'trt',\n",
       " 'JCP2022_048788': 'trt',\n",
       " 'JCP2022_000245': 'trt',\n",
       " 'JCP2022_042833': 'trt',\n",
       " 'JCP2022_056204': 'trt',\n",
       " 'JCP2022_075266': 'trt',\n",
       " 'JCP2022_032043': 'trt',\n",
       " 'JCP2022_039331': 'trt',\n",
       " 'JCP2022_086284': 'trt',\n",
       " 'JCP2022_013483': 'trt',\n",
       " 'JCP2022_101186': 'trt',\n",
       " 'JCP2022_115362': 'trt',\n",
       " 'JCP2022_026971': 'trt',\n",
       " 'JCP2022_068309': 'trt',\n",
       " 'JCP2022_017253': 'trt',\n",
       " 'JCP2022_100660': 'trt',\n",
       " 'JCP2022_015269': 'trt',\n",
       " 'JCP2022_086620': 'trt',\n",
       " 'JCP2022_065969': 'trt',\n",
       " 'JCP2022_087223': 'trt',\n",
       " 'JCP2022_108164': 'trt',\n",
       " 'JCP2022_077276': 'trt',\n",
       " 'JCP2022_099928': 'trt',\n",
       " 'JCP2022_050396': 'trt',\n",
       " 'JCP2022_000839': 'trt',\n",
       " 'JCP2022_037869': 'trt',\n",
       " 'JCP2022_104053': 'trt',\n",
       " 'JCP2022_078304': 'trt',\n",
       " 'JCP2022_002627': 'trt',\n",
       " 'JCP2022_075520': 'trt',\n",
       " 'JCP2022_070913': 'trt',\n",
       " 'JCP2022_073332': 'trt',\n",
       " 'JCP2022_113013': 'trt',\n",
       " 'JCP2022_078959': 'trt',\n",
       " 'JCP2022_053058': 'trt',\n",
       " 'JCP2022_105437': 'trt',\n",
       " 'JCP2022_094483': 'trt',\n",
       " 'JCP2022_013887': 'trt',\n",
       " 'JCP2022_071983': 'trt',\n",
       " 'JCP2022_039390': 'trt',\n",
       " 'JCP2022_095133': 'trt',\n",
       " 'JCP2022_107260': 'trt',\n",
       " 'JCP2022_056065': 'trt',\n",
       " 'JCP2022_098759': 'trt',\n",
       " 'JCP2022_009986': 'trt',\n",
       " 'JCP2022_100071': 'trt',\n",
       " 'JCP2022_012881': 'trt',\n",
       " 'JCP2022_051552': 'trt',\n",
       " 'JCP2022_078844': 'trt',\n",
       " 'JCP2022_068040': 'trt',\n",
       " 'JCP2022_052843': 'trt',\n",
       " 'JCP2022_059697': 'trt',\n",
       " 'JCP2022_087290': 'trt',\n",
       " 'JCP2022_039626': 'trt',\n",
       " 'JCP2022_067210': 'trt',\n",
       " 'JCP2022_041323': 'trt',\n",
       " 'JCP2022_042218': 'trt',\n",
       " 'JCP2022_102347': 'trt',\n",
       " 'JCP2022_110491': 'trt',\n",
       " 'JCP2022_084037': 'trt',\n",
       " 'JCP2022_011053': 'trt',\n",
       " 'JCP2022_104092': 'trt',\n",
       " 'JCP2022_061514': 'trt',\n",
       " 'JCP2022_035437': 'trt',\n",
       " 'JCP2022_056972': 'trt',\n",
       " 'JCP2022_063024': 'trt',\n",
       " 'JCP2022_006838': 'trt',\n",
       " 'JCP2022_040691': 'trt',\n",
       " 'JCP2022_069998': 'trt',\n",
       " 'JCP2022_071961': 'trt',\n",
       " 'JCP2022_027363': 'trt',\n",
       " 'JCP2022_034415': 'trt',\n",
       " 'JCP2022_060287': 'trt',\n",
       " 'JCP2022_061732': 'trt',\n",
       " 'JCP2022_045634': 'trt',\n",
       " 'JCP2022_011046': 'trt',\n",
       " 'JCP2022_065761': 'trt',\n",
       " 'JCP2022_074483': 'trt',\n",
       " 'JCP2022_076842': 'trt',\n",
       " 'JCP2022_084991': 'trt',\n",
       " 'JCP2022_066202': 'trt',\n",
       " 'JCP2022_015076': 'trt',\n",
       " 'JCP2022_020138': 'trt',\n",
       " 'JCP2022_094524': 'trt',\n",
       " 'JCP2022_044187': 'trt',\n",
       " 'JCP2022_092057': 'trt',\n",
       " 'JCP2022_066182': 'trt',\n",
       " 'JCP2022_082204': 'trt',\n",
       " 'JCP2022_093911': 'trt',\n",
       " 'JCP2022_039651': 'trt',\n",
       " 'JCP2022_018207': 'trt',\n",
       " 'JCP2022_085327': 'trt',\n",
       " 'JCP2022_010340': 'trt',\n",
       " 'JCP2022_045846': 'trt',\n",
       " 'JCP2022_024139': 'trt',\n",
       " 'JCP2022_085274': 'trt',\n",
       " 'JCP2022_097544': 'trt',\n",
       " 'JCP2022_017891': 'trt',\n",
       " 'JCP2022_040583': 'trt',\n",
       " 'JCP2022_012568': 'trt',\n",
       " 'JCP2022_011195': 'trt',\n",
       " 'JCP2022_032978': 'trt',\n",
       " 'JCP2022_067740': 'trt',\n",
       " 'JCP2022_033443': 'trt',\n",
       " 'JCP2022_046437': 'trt',\n",
       " 'JCP2022_067886': 'trt',\n",
       " 'JCP2022_031233': 'trt',\n",
       " 'JCP2022_025705': 'trt',\n",
       " 'JCP2022_007042': 'trt',\n",
       " 'JCP2022_070641': 'trt',\n",
       " 'JCP2022_028147': 'trt',\n",
       " 'JCP2022_053465': 'trt',\n",
       " 'JCP2022_105906': 'trt',\n",
       " 'JCP2022_083060': 'trt',\n",
       " 'JCP2022_028931': 'trt',\n",
       " 'JCP2022_092297': 'trt',\n",
       " 'JCP2022_012718': 'trt',\n",
       " 'JCP2022_054152': 'trt',\n",
       " 'JCP2022_058232': 'trt',\n",
       " 'JCP2022_113073': 'trt',\n",
       " 'JCP2022_092516': 'trt',\n",
       " 'JCP2022_056380': 'trt',\n",
       " 'JCP2022_033361': 'trt',\n",
       " 'JCP2022_087768': 'trt',\n",
       " 'JCP2022_002757': 'trt',\n",
       " 'JCP2022_079054': 'trt',\n",
       " 'JCP2022_116484': 'trt',\n",
       " 'JCP2022_101361': 'trt',\n",
       " 'JCP2022_079306': 'trt',\n",
       " 'JCP2022_081085': 'trt',\n",
       " 'JCP2022_046079': 'trt',\n",
       " 'JCP2022_111433': 'trt',\n",
       " 'JCP2022_099592': 'trt',\n",
       " 'JCP2022_114657': 'trt',\n",
       " 'JCP2022_086514': 'trt',\n",
       " 'JCP2022_101253': 'trt',\n",
       " 'JCP2022_105016': 'trt',\n",
       " 'JCP2022_038124': 'trt',\n",
       " 'JCP2022_050526': 'trt',\n",
       " 'JCP2022_057148': 'trt',\n",
       " 'JCP2022_036007': 'trt',\n",
       " 'JCP2022_028726': 'trt',\n",
       " 'JCP2022_010471': 'trt',\n",
       " 'JCP2022_016914': 'trt',\n",
       " 'JCP2022_082225': 'trt',\n",
       " 'JCP2022_111326': 'trt',\n",
       " 'JCP2022_010703': 'trt',\n",
       " 'JCP2022_020141': 'trt',\n",
       " 'JCP2022_023607': 'trt',\n",
       " 'JCP2022_081977': 'trt',\n",
       " 'JCP2022_015763': 'trt',\n",
       " 'JCP2022_004330': 'trt',\n",
       " 'JCP2022_025866': 'trt',\n",
       " 'JCP2022_052574': 'trt',\n",
       " 'JCP2022_083297': 'trt',\n",
       " 'JCP2022_066199': 'trt',\n",
       " 'JCP2022_013266': 'trt',\n",
       " 'JCP2022_074645': 'trt',\n",
       " 'JCP2022_088193': 'trt',\n",
       " 'JCP2022_061492': 'trt',\n",
       " 'JCP2022_014509': 'trt',\n",
       " 'JCP2022_110117': 'trt',\n",
       " 'JCP2022_081793': 'trt',\n",
       " 'JCP2022_050568': 'trt',\n",
       " 'JCP2022_026118': 'trt',\n",
       " 'JCP2022_097067': 'trt',\n",
       " 'JCP2022_075358': 'trt',\n",
       " 'JCP2022_064279': 'trt',\n",
       " 'JCP2022_020623': 'trt',\n",
       " 'JCP2022_072707': 'trt',\n",
       " 'JCP2022_111008': 'trt',\n",
       " 'JCP2022_052665': 'trt',\n",
       " 'JCP2022_013432': 'trt',\n",
       " 'JCP2022_054610': 'trt',\n",
       " 'JCP2022_066710': 'trt',\n",
       " 'JCP2022_034099': 'trt',\n",
       " 'JCP2022_104897': 'trt',\n",
       " 'JCP2022_076858': 'trt',\n",
       " 'JCP2022_112146': 'trt',\n",
       " 'JCP2022_002670': 'trt',\n",
       " 'JCP2022_029403': 'trt',\n",
       " 'JCP2022_066251': 'trt',\n",
       " 'JCP2022_097926': 'trt',\n",
       " 'JCP2022_112796': 'trt',\n",
       " 'JCP2022_019904': 'trt',\n",
       " 'JCP2022_100545': 'trt',\n",
       " 'JCP2022_086726': 'trt',\n",
       " 'JCP2022_115668': 'trt',\n",
       " 'JCP2022_044721': 'trt',\n",
       " 'JCP2022_111181': 'trt',\n",
       " 'JCP2022_029630': 'trt',\n",
       " 'JCP2022_066457': 'trt',\n",
       " 'JCP2022_062832': 'trt',\n",
       " 'JCP2022_023766': 'trt',\n",
       " 'JCP2022_103588': 'trt',\n",
       " 'JCP2022_086862': 'trt',\n",
       " 'JCP2022_079642': 'trt',\n",
       " 'JCP2022_039507': 'trt',\n",
       " 'JCP2022_037687': 'trt',\n",
       " 'JCP2022_110943': 'trt',\n",
       " 'JCP2022_039704': 'trt',\n",
       " 'JCP2022_041883': 'trt',\n",
       " 'JCP2022_066338': 'trt',\n",
       " 'JCP2022_084747': 'trt',\n",
       " 'JCP2022_003158': 'trt',\n",
       " 'JCP2022_105153': 'trt',\n",
       " 'JCP2022_110102': 'trt',\n",
       " 'JCP2022_098106': 'trt',\n",
       " 'JCP2022_104121': 'trt',\n",
       " 'JCP2022_061215': 'trt',\n",
       " 'JCP2022_009081': 'trt',\n",
       " 'JCP2022_058973': 'trt',\n",
       " 'JCP2022_049523': 'trt',\n",
       " 'JCP2022_093651': 'trt',\n",
       " 'JCP2022_005154': 'trt',\n",
       " 'JCP2022_046936': 'trt',\n",
       " 'JCP2022_040941': 'trt',\n",
       " 'JCP2022_034132': 'trt',\n",
       " 'JCP2022_005747': 'trt',\n",
       " 'JCP2022_064847': 'trt',\n",
       " 'JCP2022_090432': 'trt',\n",
       " 'JCP2022_065898': 'trt',\n",
       " 'JCP2022_056211': 'trt',\n",
       " 'JCP2022_071660': 'trt',\n",
       " 'JCP2022_093984': 'trt',\n",
       " 'JCP2022_041697': 'trt',\n",
       " 'JCP2022_071152': 'trt',\n",
       " 'JCP2022_014617': 'trt',\n",
       " 'JCP2022_109160': 'trt',\n",
       " 'JCP2022_005350': 'trt',\n",
       " 'JCP2022_085240': 'trt',\n",
       " 'JCP2022_109334': 'trt',\n",
       " 'JCP2022_104669': 'trt',\n",
       " 'JCP2022_067465': 'trt',\n",
       " 'JCP2022_094408': 'trt',\n",
       " 'JCP2022_110096': 'trt',\n",
       " 'JCP2022_071623': 'trt',\n",
       " 'JCP2022_061975': 'trt',\n",
       " 'JCP2022_026431': 'trt',\n",
       " 'JCP2022_003976': 'trt',\n",
       " 'JCP2022_116266': 'trt',\n",
       " 'JCP2022_058304': 'trt',\n",
       " 'JCP2022_001623': 'trt',\n",
       " 'JCP2022_057995': 'trt',\n",
       " 'JCP2022_062726': 'trt',\n",
       " 'JCP2022_108851': 'trt',\n",
       " 'JCP2022_018702': 'trt',\n",
       " 'JCP2022_097212': 'trt',\n",
       " 'JCP2022_115218': 'trt',\n",
       " 'JCP2022_057225': 'trt',\n",
       " 'JCP2022_088678': 'trt',\n",
       " 'JCP2022_041912': 'trt',\n",
       " 'JCP2022_083787': 'trt',\n",
       " 'JCP2022_034877': 'trt',\n",
       " 'JCP2022_031810': 'trt',\n",
       " 'JCP2022_006412': 'trt',\n",
       " 'JCP2022_112189': 'trt',\n",
       " 'JCP2022_097581': 'trt',\n",
       " 'JCP2022_093814': 'trt',\n",
       " 'JCP2022_052668': 'trt',\n",
       " 'JCP2022_043591': 'trt',\n",
       " 'JCP2022_113780': 'trt',\n",
       " 'JCP2022_106931': 'trt',\n",
       " 'JCP2022_000279': 'trt',\n",
       " 'JCP2022_098561': 'trt',\n",
       " 'JCP2022_011286': 'trt',\n",
       " 'JCP2022_098600': 'trt',\n",
       " 'JCP2022_060417': 'trt',\n",
       " 'JCP2022_038571': 'trt',\n",
       " 'JCP2022_094361': 'trt',\n",
       " 'JCP2022_028980': 'trt',\n",
       " 'JCP2022_021655': 'trt',\n",
       " 'JCP2022_013087': 'trt',\n",
       " 'JCP2022_107836': 'trt',\n",
       " 'JCP2022_010412': 'trt',\n",
       " 'JCP2022_090232': 'trt',\n",
       " 'JCP2022_067477': 'trt',\n",
       " 'JCP2022_007014': 'trt',\n",
       " 'JCP2022_082725': 'trt',\n",
       " 'JCP2022_109654': 'trt',\n",
       " 'JCP2022_055988': 'trt',\n",
       " 'JCP2022_057382': 'trt',\n",
       " 'JCP2022_029414': 'trt',\n",
       " 'JCP2022_077686': 'trt',\n",
       " 'JCP2022_048663': 'trt',\n",
       " 'JCP2022_013789': 'trt',\n",
       " 'JCP2022_040048': 'trt',\n",
       " 'JCP2022_098992': 'trt',\n",
       " 'JCP2022_001001': 'trt',\n",
       " 'JCP2022_055187': 'trt',\n",
       " 'JCP2022_110127': 'trt',\n",
       " 'JCP2022_095699': 'trt',\n",
       " 'JCP2022_051780': 'trt',\n",
       " 'JCP2022_054737': 'trt',\n",
       " 'JCP2022_025425': 'trt',\n",
       " 'JCP2022_059769': 'trt',\n",
       " 'JCP2022_048065': 'trt',\n",
       " 'JCP2022_113961': 'trt',\n",
       " 'JCP2022_071038': 'trt',\n",
       " 'JCP2022_075682': 'trt',\n",
       " 'JCP2022_098071': 'trt',\n",
       " 'JCP2022_079775': 'trt',\n",
       " 'JCP2022_049324': 'trt',\n",
       " 'JCP2022_008625': 'trt',\n",
       " 'JCP2022_028773': 'trt',\n",
       " 'JCP2022_097959': 'trt',\n",
       " 'JCP2022_054694': 'trt',\n",
       " 'JCP2022_036269': 'trt',\n",
       " 'JCP2022_062719': 'trt',\n",
       " 'JCP2022_095950': 'trt',\n",
       " 'JCP2022_023196': 'trt',\n",
       " 'JCP2022_034584': 'trt',\n",
       " 'JCP2022_052433': 'trt',\n",
       " 'JCP2022_010473': 'trt',\n",
       " 'JCP2022_012168': 'trt',\n",
       " 'JCP2022_066911': 'trt',\n",
       " 'JCP2022_044119': 'trt',\n",
       " 'JCP2022_076089': 'trt',\n",
       " 'JCP2022_105104': 'trt',\n",
       " 'JCP2022_036376': 'trt',\n",
       " 'JCP2022_043982': 'trt',\n",
       " 'JCP2022_047164': 'trt',\n",
       " 'JCP2022_069333': 'trt',\n",
       " 'JCP2022_024384': 'trt',\n",
       " 'JCP2022_015199': 'trt',\n",
       " 'JCP2022_026008': 'trt',\n",
       " 'JCP2022_104562': 'trt',\n",
       " 'JCP2022_017337': 'trt',\n",
       " 'JCP2022_107996': 'trt',\n",
       " 'JCP2022_114134': 'trt',\n",
       " 'JCP2022_015955': 'trt',\n",
       " 'JCP2022_100132': 'trt',\n",
       " 'JCP2022_040953': 'trt',\n",
       " 'JCP2022_101654': 'trt',\n",
       " 'JCP2022_033805': 'trt',\n",
       " 'JCP2022_073884': 'trt',\n",
       " 'JCP2022_089577': 'trt',\n",
       " 'JCP2022_049248': 'trt',\n",
       " 'JCP2022_113366': 'trt',\n",
       " 'JCP2022_092746': 'trt',\n",
       " 'JCP2022_010686': 'trt',\n",
       " 'JCP2022_068210': 'trt',\n",
       " 'JCP2022_008957': 'trt',\n",
       " 'JCP2022_009724': 'trt',\n",
       " 'JCP2022_062629': 'trt',\n",
       " 'JCP2022_010845': 'trt',\n",
       " 'JCP2022_070671': 'trt',\n",
       " 'JCP2022_102265': 'trt',\n",
       " 'JCP2022_047807': 'trt',\n",
       " 'JCP2022_000135': 'trt',\n",
       " 'JCP2022_065317': 'trt',\n",
       " 'JCP2022_011501': 'trt',\n",
       " 'JCP2022_059019': 'trt',\n",
       " 'JCP2022_064895': 'trt',\n",
       " 'JCP2022_011369': 'trt',\n",
       " 'JCP2022_097361': 'trt',\n",
       " 'JCP2022_033182': 'trt',\n",
       " 'JCP2022_098926': 'trt',\n",
       " 'JCP2022_000581': 'trt',\n",
       " 'JCP2022_003832': 'trt',\n",
       " 'JCP2022_010758': 'trt',\n",
       " 'JCP2022_027906': 'trt',\n",
       " 'JCP2022_042578': 'trt',\n",
       " 'JCP2022_086599': 'trt',\n",
       " 'JCP2022_088058': 'trt',\n",
       " 'JCP2022_014359': 'trt',\n",
       " 'JCP2022_110764': 'trt',\n",
       " 'JCP2022_100304': 'trt',\n",
       " 'JCP2022_009174': 'trt',\n",
       " 'JCP2022_041841': 'trt',\n",
       " 'JCP2022_108091': 'trt',\n",
       " 'JCP2022_116079': 'trt',\n",
       " 'JCP2022_029277': 'trt',\n",
       " 'JCP2022_034694': 'trt',\n",
       " 'JCP2022_059040': 'trt',\n",
       " 'JCP2022_032674': 'trt',\n",
       " 'JCP2022_058831': 'trt',\n",
       " 'JCP2022_033952': 'trt',\n",
       " 'JCP2022_084674': 'trt',\n",
       " 'JCP2022_033340': 'trt',\n",
       " 'JCP2022_112507': 'trt',\n",
       " 'JCP2022_093853': 'trt',\n",
       " 'JCP2022_037639': 'trt',\n",
       " 'JCP2022_077500': 'trt',\n",
       " 'JCP2022_098821': 'trt',\n",
       " 'JCP2022_083065': 'trt',\n",
       " 'JCP2022_046822': 'trt',\n",
       " 'JCP2022_012431': 'trt',\n",
       " 'JCP2022_083795': 'trt',\n",
       " 'JCP2022_035440': 'trt',\n",
       " 'JCP2022_103900': 'trt',\n",
       " 'JCP2022_018814': 'trt',\n",
       " 'JCP2022_099837': 'trt',\n",
       " 'JCP2022_085207': 'trt',\n",
       " 'JCP2022_010918': 'trt',\n",
       " 'JCP2022_012934': 'trt',\n",
       " 'JCP2022_027025': 'trt',\n",
       " 'JCP2022_064262': 'trt',\n",
       " 'JCP2022_086278': 'trt',\n",
       " 'JCP2022_092985': 'trt',\n",
       " 'JCP2022_031376': 'trt',\n",
       " 'JCP2022_025634': 'trt',\n",
       " 'JCP2022_042365': 'trt',\n",
       " 'JCP2022_031061': 'trt',\n",
       " 'JCP2022_028486': 'trt',\n",
       " 'JCP2022_098149': 'trt',\n",
       " 'JCP2022_009015': 'trt',\n",
       " 'JCP2022_038019': 'trt',\n",
       " 'JCP2022_090002': 'trt',\n",
       " 'JCP2022_025983': 'trt',\n",
       " 'JCP2022_085066': 'trt',\n",
       " 'JCP2022_087063': 'trt',\n",
       " 'JCP2022_017146': 'trt',\n",
       " 'JCP2022_033882': 'trt',\n",
       " 'JCP2022_100103': 'trt',\n",
       " 'JCP2022_038834': 'trt',\n",
       " 'JCP2022_094504': 'trt',\n",
       " 'JCP2022_087750': 'trt',\n",
       " 'JCP2022_030762': 'trt',\n",
       " 'JCP2022_114289': 'trt',\n",
       " 'JCP2022_046169': 'trt',\n",
       " 'JCP2022_034866': 'trt',\n",
       " 'JCP2022_005665': 'trt',\n",
       " 'JCP2022_026360': 'trt',\n",
       " 'JCP2022_019841': 'trt',\n",
       " 'JCP2022_000674': 'trt',\n",
       " 'JCP2022_060139': 'trt',\n",
       " 'JCP2022_084288': 'trt',\n",
       " 'JCP2022_085354': 'trt',\n",
       " 'JCP2022_059756': 'trt',\n",
       " 'JCP2022_042470': 'trt',\n",
       " 'JCP2022_035980': 'trt',\n",
       " 'JCP2022_014163': 'trt',\n",
       " 'JCP2022_058731': 'trt',\n",
       " 'JCP2022_030284': 'trt',\n",
       " 'JCP2022_068222': 'trt',\n",
       " 'JCP2022_048047': 'trt',\n",
       " 'JCP2022_116520': 'trt',\n",
       " 'JCP2022_038799': 'trt',\n",
       " 'JCP2022_089242': 'trt',\n",
       " 'JCP2022_048004': 'trt',\n",
       " 'JCP2022_057326': 'trt',\n",
       " 'JCP2022_094895': 'trt',\n",
       " 'JCP2022_038256': 'trt',\n",
       " 'JCP2022_027516': 'trt',\n",
       " 'JCP2022_089301': 'trt',\n",
       " 'JCP2022_077441': 'trt',\n",
       " 'JCP2022_044057': 'trt',\n",
       " 'JCP2022_048483': 'trt',\n",
       " 'JCP2022_008265': 'trt',\n",
       " 'JCP2022_090290': 'trt',\n",
       " 'JCP2022_037638': 'trt',\n",
       " 'JCP2022_013669': 'trt',\n",
       " 'JCP2022_087689': 'trt',\n",
       " 'JCP2022_100916': 'trt',\n",
       " 'JCP2022_107760': 'trt',\n",
       " 'JCP2022_102723': 'trt',\n",
       " 'JCP2022_000220': 'trt',\n",
       " 'JCP2022_082837': 'trt',\n",
       " 'JCP2022_028521': 'trt',\n",
       " 'JCP2022_031381': 'trt',\n",
       " 'JCP2022_088628': 'trt',\n",
       " 'JCP2022_112547': 'trt',\n",
       " 'JCP2022_086969': 'trt',\n",
       " 'JCP2022_069081': 'trt',\n",
       " 'JCP2022_086321': 'trt',\n",
       " 'JCP2022_006709': 'trt',\n",
       " 'JCP2022_004082': 'trt',\n",
       " 'JCP2022_017325': 'trt',\n",
       " 'JCP2022_040902': 'trt',\n",
       " 'JCP2022_008756': 'trt',\n",
       " 'JCP2022_044798': 'trt',\n",
       " 'JCP2022_015624': 'trt',\n",
       " 'JCP2022_025798': 'trt',\n",
       " 'JCP2022_004829': 'trt',\n",
       " 'JCP2022_018010': 'trt',\n",
       " 'JCP2022_104664': 'trt',\n",
       " 'JCP2022_100012': 'trt',\n",
       " 'JCP2022_095519': 'trt',\n",
       " 'JCP2022_061655': 'trt',\n",
       " 'JCP2022_115153': 'trt',\n",
       " 'JCP2022_012829': 'trt',\n",
       " 'JCP2022_100424': 'trt',\n",
       " 'JCP2022_017179': 'trt',\n",
       " 'JCP2022_048520': 'trt',\n",
       " 'JCP2022_071640': 'trt',\n",
       " 'JCP2022_009820': 'trt',\n",
       " 'JCP2022_079121': 'trt',\n",
       " 'JCP2022_036275': 'trt',\n",
       " 'JCP2022_115530': 'trt',\n",
       " 'JCP2022_078620': 'trt',\n",
       " 'JCP2022_018341': 'trt',\n",
       " 'JCP2022_080898': 'trt',\n",
       " 'JCP2022_049929': 'trt',\n",
       " 'JCP2022_071063': 'trt',\n",
       " 'JCP2022_101333': 'trt',\n",
       " 'JCP2022_026986': 'trt',\n",
       " 'JCP2022_063363': 'trt',\n",
       " 'JCP2022_076575': 'trt',\n",
       " 'JCP2022_095631': 'trt',\n",
       " 'JCP2022_067047': 'trt',\n",
       " 'JCP2022_080327': 'trt',\n",
       " 'JCP2022_092639': 'trt',\n",
       " 'JCP2022_052090': 'trt',\n",
       " 'JCP2022_009888': 'trt',\n",
       " 'JCP2022_116456': 'trt',\n",
       " 'JCP2022_005031': 'trt',\n",
       " 'JCP2022_080340': 'trt',\n",
       " 'JCP2022_114952': 'trt',\n",
       " 'JCP2022_054304': 'trt',\n",
       " 'JCP2022_095245': 'trt',\n",
       " 'JCP2022_054512': 'trt',\n",
       " 'JCP2022_012723': 'trt',\n",
       " 'JCP2022_015432': 'trt',\n",
       " 'JCP2022_039098': 'trt',\n",
       " 'JCP2022_042391': 'trt',\n",
       " 'JCP2022_068958': 'trt',\n",
       " 'JCP2022_110115': 'trt',\n",
       " 'JCP2022_067114': 'trt',\n",
       " 'JCP2022_053081': 'trt',\n",
       " 'JCP2022_067427': 'trt',\n",
       " 'JCP2022_086679': 'trt',\n",
       " 'JCP2022_068012': 'trt',\n",
       " 'JCP2022_014224': 'trt',\n",
       " 'JCP2022_045339': 'trt',\n",
       " 'JCP2022_060302': 'trt',\n",
       " 'JCP2022_057860': 'trt',\n",
       " 'JCP2022_010030': 'trt',\n",
       " 'JCP2022_052076': 'trt',\n",
       " 'JCP2022_054154': 'trt',\n",
       " 'JCP2022_002887': 'trt',\n",
       " 'JCP2022_013509': 'trt',\n",
       " 'JCP2022_010906': 'trt',\n",
       " 'JCP2022_067368': 'trt',\n",
       " 'JCP2022_088619': 'trt',\n",
       " 'JCP2022_113234': 'trt',\n",
       " 'JCP2022_056919': 'trt',\n",
       " 'JCP2022_021617': 'trt',\n",
       " 'JCP2022_030247': 'trt',\n",
       " 'JCP2022_100677': 'trt',\n",
       " 'JCP2022_085116': 'trt',\n",
       " 'JCP2022_044905': 'trt',\n",
       " 'JCP2022_053165': 'trt',\n",
       " 'JCP2022_077528': 'trt',\n",
       " 'JCP2022_091266': 'trt',\n",
       " 'JCP2022_026968': 'trt',\n",
       " 'JCP2022_007975': 'trt',\n",
       " 'JCP2022_006308': 'trt',\n",
       " 'JCP2022_080146': 'trt',\n",
       " 'JCP2022_060870': 'trt',\n",
       " 'JCP2022_074208': 'trt',\n",
       " 'JCP2022_051242': 'trt',\n",
       " 'JCP2022_084866': 'trt',\n",
       " 'JCP2022_093355': 'trt',\n",
       " 'JCP2022_104304': 'trt',\n",
       " 'JCP2022_112397': 'trt',\n",
       " 'JCP2022_003646': 'trt',\n",
       " 'JCP2022_074511': 'trt',\n",
       " 'JCP2022_078533': 'trt',\n",
       " 'JCP2022_083721': 'trt',\n",
       " 'JCP2022_054506': 'trt',\n",
       " 'JCP2022_084535': 'trt',\n",
       " 'JCP2022_015083': 'trt',\n",
       " 'JCP2022_046222': 'trt',\n",
       " 'JCP2022_039879': 'trt',\n",
       " 'JCP2022_002661': 'trt',\n",
       " 'JCP2022_076060': 'trt',\n",
       " 'JCP2022_003494': 'trt',\n",
       " 'JCP2022_009359': 'trt',\n",
       " 'JCP2022_031931': 'trt',\n",
       " 'JCP2022_050527': 'trt',\n",
       " 'JCP2022_031202': 'trt',\n",
       " 'JCP2022_093058': 'trt',\n",
       " 'JCP2022_048260': 'trt',\n",
       " 'JCP2022_074886': 'trt',\n",
       " 'JCP2022_098519': 'trt',\n",
       " 'JCP2022_045926': 'trt',\n",
       " 'JCP2022_010683': 'trt',\n",
       " 'JCP2022_051664': 'trt',\n",
       " 'JCP2022_028250': 'trt',\n",
       " 'JCP2022_089725': 'trt',\n",
       " 'JCP2022_112999': 'trt',\n",
       " 'JCP2022_031382': 'trt',\n",
       " 'JCP2022_080526': 'trt',\n",
       " 'JCP2022_085091': 'trt',\n",
       " 'JCP2022_004083': 'trt',\n",
       " 'JCP2022_069027': 'trt',\n",
       " 'JCP2022_075510': 'trt',\n",
       " 'JCP2022_096910': 'trt',\n",
       " 'JCP2022_051856': 'trt',\n",
       " 'JCP2022_033038': 'trt',\n",
       " 'JCP2022_094007': 'trt',\n",
       " 'JCP2022_112612': 'trt',\n",
       " 'JCP2022_064592': 'trt',\n",
       " 'JCP2022_001026': 'trt',\n",
       " 'JCP2022_102782': 'trt',\n",
       " 'JCP2022_083643': 'trt',\n",
       " 'JCP2022_038699': 'trt',\n",
       " 'JCP2022_077426': 'trt',\n",
       " 'JCP2022_001935': 'trt',\n",
       " 'JCP2022_046738': 'trt',\n",
       " 'JCP2022_058149': 'trt',\n",
       " 'JCP2022_088323': 'trt',\n",
       " 'JCP2022_065096': 'trt',\n",
       " 'JCP2022_005809': 'trt',\n",
       " 'JCP2022_098464': 'trt',\n",
       " 'JCP2022_071505': 'trt',\n",
       " 'JCP2022_014128': 'trt',\n",
       " 'JCP2022_009535': 'trt',\n",
       " 'JCP2022_095564': 'trt',\n",
       " 'JCP2022_114411': 'trt',\n",
       " 'JCP2022_008987': 'trt',\n",
       " 'JCP2022_039646': 'trt',\n",
       " 'JCP2022_014953': 'trt',\n",
       " 'JCP2022_030979': 'trt',\n",
       " 'JCP2022_038122': 'trt',\n",
       " 'JCP2022_077651': 'trt',\n",
       " 'JCP2022_003341': 'trt',\n",
       " 'JCP2022_083346': 'trt',\n",
       " 'JCP2022_069900': 'trt',\n",
       " 'JCP2022_017759': 'trt',\n",
       " 'JCP2022_042410': 'trt',\n",
       " 'JCP2022_073298': 'trt',\n",
       " 'JCP2022_014452': 'trt',\n",
       " 'JCP2022_048197': 'trt',\n",
       " 'JCP2022_014880': 'trt',\n",
       " 'JCP2022_056538': 'trt',\n",
       " 'JCP2022_081615': 'trt',\n",
       " 'JCP2022_093816': 'trt',\n",
       " 'JCP2022_114618': 'trt',\n",
       " 'JCP2022_028974': 'trt',\n",
       " 'JCP2022_114590': 'trt',\n",
       " 'JCP2022_102219': 'trt',\n",
       " 'JCP2022_038246': 'trt',\n",
       " 'JCP2022_011964': 'trt',\n",
       " 'JCP2022_023118': 'trt',\n",
       " 'JCP2022_060397': 'trt',\n",
       " 'JCP2022_062182': 'trt',\n",
       " 'JCP2022_075202': 'trt',\n",
       " 'JCP2022_023123': 'trt',\n",
       " 'JCP2022_101571': 'trt',\n",
       " 'JCP2022_032009': 'trt',\n",
       " 'JCP2022_060797': 'trt',\n",
       " 'JCP2022_001504': 'trt',\n",
       " 'JCP2022_053837': 'trt',\n",
       " 'JCP2022_111907': 'trt',\n",
       " 'JCP2022_044474': 'trt',\n",
       " 'JCP2022_058318': 'trt',\n",
       " 'JCP2022_026540': 'trt',\n",
       " 'JCP2022_096194': 'trt',\n",
       " 'JCP2022_105537': 'trt',\n",
       " 'JCP2022_008496': 'trt',\n",
       " 'JCP2022_071458': 'trt',\n",
       " 'JCP2022_116268': 'trt',\n",
       " 'JCP2022_034277': 'trt',\n",
       " 'JCP2022_076628': 'trt',\n",
       " 'JCP2022_003789': 'trt',\n",
       " 'JCP2022_036526': 'trt',\n",
       " 'JCP2022_112028': 'trt',\n",
       " 'JCP2022_070554': 'trt',\n",
       " 'JCP2022_110500': 'trt',\n",
       " 'JCP2022_104372': 'trt',\n",
       " 'JCP2022_035515': 'trt',\n",
       " 'JCP2022_036195': 'trt',\n",
       " 'JCP2022_109888': 'trt',\n",
       " 'JCP2022_032868': 'trt',\n",
       " 'JCP2022_088131': 'trt',\n",
       " 'JCP2022_102115': 'trt',\n",
       " 'JCP2022_083591': 'trt',\n",
       " 'JCP2022_079441': 'trt',\n",
       " 'JCP2022_099180': 'trt',\n",
       " 'JCP2022_008624': 'trt',\n",
       " 'JCP2022_106798': 'trt',\n",
       " 'JCP2022_004760': 'trt',\n",
       " 'JCP2022_074921': 'trt',\n",
       " 'JCP2022_070056': 'trt',\n",
       " 'JCP2022_049206': 'trt',\n",
       " 'JCP2022_082067': 'trt',\n",
       " 'JCP2022_067167': 'trt',\n",
       " 'JCP2022_021137': 'trt',\n",
       " 'JCP2022_025791': 'trt',\n",
       " 'JCP2022_104822': 'trt',\n",
       " 'JCP2022_049577': 'trt',\n",
       " 'JCP2022_064164': 'trt',\n",
       " 'JCP2022_007251': 'trt',\n",
       " 'JCP2022_005663': 'trt',\n",
       " 'JCP2022_073453': 'trt',\n",
       " 'JCP2022_000116': 'trt',\n",
       " 'JCP2022_028946': 'trt',\n",
       " 'JCP2022_037719': 'trt',\n",
       " 'JCP2022_104526': 'trt',\n",
       " 'JCP2022_111571': 'trt',\n",
       " 'JCP2022_083098': 'trt',\n",
       " 'JCP2022_038605': 'trt',\n",
       " 'JCP2022_002503': 'trt',\n",
       " 'JCP2022_046355': 'trt',\n",
       " 'JCP2022_021519': 'trt',\n",
       " 'JCP2022_069923': 'trt',\n",
       " 'JCP2022_019798': 'trt',\n",
       " 'JCP2022_081131': 'trt',\n",
       " 'JCP2022_013401': 'trt',\n",
       " 'JCP2022_021129': 'trt',\n",
       " 'JCP2022_040896': 'trt',\n",
       " 'JCP2022_075124': 'trt',\n",
       " 'JCP2022_097341': 'trt',\n",
       " 'JCP2022_000161': 'trt',\n",
       " 'JCP2022_021324': 'trt',\n",
       " 'JCP2022_082184': 'trt',\n",
       " 'JCP2022_045388': 'trt',\n",
       " 'JCP2022_081267': 'trt',\n",
       " 'JCP2022_006990': 'trt',\n",
       " 'JCP2022_083415': 'trt',\n",
       " 'JCP2022_055064': 'trt',\n",
       " 'JCP2022_063534': 'trt',\n",
       " 'JCP2022_036062': 'trt',\n",
       " 'JCP2022_015274': 'trt',\n",
       " 'JCP2022_074683': 'trt',\n",
       " 'JCP2022_062233': 'trt',\n",
       " 'JCP2022_074002': 'trt',\n",
       " 'JCP2022_106895': 'trt',\n",
       " 'JCP2022_033144': 'trt',\n",
       " 'JCP2022_087574': 'trt',\n",
       " 'JCP2022_042689': 'trt',\n",
       " 'JCP2022_014670': 'trt',\n",
       " 'JCP2022_059793': 'trt',\n",
       " 'JCP2022_109368': 'trt',\n",
       " 'JCP2022_005719': 'trt',\n",
       " 'JCP2022_075804': 'trt',\n",
       " 'JCP2022_096528': 'trt',\n",
       " 'JCP2022_078345': 'trt',\n",
       " 'JCP2022_026125': 'trt',\n",
       " 'JCP2022_042434': 'trt',\n",
       " 'JCP2022_097712': 'trt',\n",
       " 'JCP2022_107716': 'trt',\n",
       " 'JCP2022_113104': 'trt',\n",
       " 'JCP2022_017523': 'trt',\n",
       " 'JCP2022_058502': 'trt',\n",
       " 'JCP2022_112425': 'trt',\n",
       " 'JCP2022_081696': 'trt',\n",
       " 'JCP2022_016830': 'trt',\n",
       " 'JCP2022_106659': 'trt',\n",
       " 'JCP2022_042333': 'trt',\n",
       " 'JCP2022_051403': 'trt',\n",
       " 'JCP2022_052770': 'trt',\n",
       " 'JCP2022_008538': 'trt',\n",
       " 'JCP2022_019350': 'trt',\n",
       " 'JCP2022_015862': 'trt',\n",
       " 'JCP2022_010702': 'trt',\n",
       " 'JCP2022_103266': 'trt',\n",
       " 'JCP2022_035816': 'trt',\n",
       " 'JCP2022_009789': 'trt',\n",
       " 'JCP2022_029856': 'trt',\n",
       " 'JCP2022_071223': 'trt',\n",
       " 'JCP2022_043795': 'trt',\n",
       " 'JCP2022_093901': 'trt',\n",
       " 'JCP2022_023270': 'trt',\n",
       " 'JCP2022_111533': 'trt',\n",
       " 'JCP2022_073934': 'trt',\n",
       " 'JCP2022_096855': 'trt',\n",
       " 'JCP2022_026047': 'trt',\n",
       " 'JCP2022_078803': 'trt',\n",
       " 'JCP2022_086281': 'trt',\n",
       " 'JCP2022_098183': 'trt',\n",
       " 'JCP2022_111410': 'trt',\n",
       " 'JCP2022_018027': 'trt',\n",
       " 'JCP2022_028961': 'trt',\n",
       " 'JCP2022_045245': 'trt',\n",
       " ...}"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "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>Compartment</th>\n",
       "      <th>Feature</th>\n",
       "      <th>Channel</th>\n",
       "      <th>Suffix</th>\n",
       "      <th>Feature significance</th>\n",
       "      <th>Perturbation</th>\n",
       "      <th>Perturbation example image</th>\n",
       "      <th>Median</th>\n",
       "      <th>Gene Rank</th>\n",
       "      <th>Feature Rank</th>\n",
       "      <th>JCP2022</th>\n",
       "      <th>Resources</th>\n",
       "      <th>Synonyms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Cells</td>\n",
       "      <td>RadialDistributionFracAtD</td>\n",
       "      <td></td>\n",
       "      <td>_mito_tubeness_3of16</td>\n",
       "      <td>0.08213</td>\n",
       "      <td>AIRPKJLLJCUQSV-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-0.964</td>\n",
       "      <td>999999</td>\n",
       "      <td>9</td>\n",
       "      <td>JCP2022_001647</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>AreaShapeZernike</td>\n",
       "      <td></td>\n",
       "      <td>_6_2</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>DTCQXSFBETURSZ-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.244</td>\n",
       "      <td>999999</td>\n",
       "      <td>0</td>\n",
       "      <td>JCP2022_018053</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>RadialDistribution_RadialCV</td>\n",
       "      <td>Mito</td>\n",
       "      <td>_3of4</td>\n",
       "      <td>0.02041</td>\n",
       "      <td>UQEZJEIWCQNVQU-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.514</td>\n",
       "      <td>999999</td>\n",
       "      <td>4</td>\n",
       "      <td>JCP2022_090828</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Cytoplasm</td>\n",
       "      <td>RadialDistribution_FracAtD</td>\n",
       "      <td>ER</td>\n",
       "      <td>_2of4</td>\n",
       "      <td>0.00227</td>\n",
       "      <td>MOQWDHSSODJEDU-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.486</td>\n",
       "      <td>999999</td>\n",
       "      <td>2</td>\n",
       "      <td>JCP2022_055532</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cytoplasm</td>\n",
       "      <td>RadialDistribution_FracAtD</td>\n",
       "      <td>DNA</td>\n",
       "      <td>_1of4</td>\n",
       "      <td>0.01685</td>\n",
       "      <td>WPCDYOHCABUJAF-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.097</td>\n",
       "      <td>999999</td>\n",
       "      <td>1</td>\n",
       "      <td>JCP2022_100243</td>\n",
       "      <td>None</td>\n",
       "      <td>None</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189393</th>\n",
       "      <td>Cells</td>\n",
       "      <td>Texture_SumEntropy</td>\n",
       "      <td>RNA</td>\n",
       "      <td>_10_01_256</td>\n",
       "      <td>0.02717</td>\n",
       "      <td>KHEBJWNXOZKKBY-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.227</td>\n",
       "      <td>999999</td>\n",
       "      <td>2</td>\n",
       "      <td>JCP2022_044597</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189394</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>AreaShapeCompactness</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>0.00000</td>\n",
       "      <td>QGGLNUGOWVBAJC-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.906</td>\n",
       "      <td>999999</td>\n",
       "      <td>1</td>\n",
       "      <td>JCP2022_073238</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189395</th>\n",
       "      <td>Cells</td>\n",
       "      <td>AreaShapeMaxFeretDiameter</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>0.00138</td>\n",
       "      <td>SBJVCDHWJCQQIQ-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.688</td>\n",
       "      <td>999999</td>\n",
       "      <td>8</td>\n",
       "      <td>JCP2022_082092</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189396</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>Texture_Correlation</td>\n",
       "      <td>ER</td>\n",
       "      <td>_10_02_256</td>\n",
       "      <td>0.19502</td>\n",
       "      <td>FCQDLIHIOSXHMH-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.206</td>\n",
       "      <td>999999</td>\n",
       "      <td>5</td>\n",
       "      <td>JCP2022_019780</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189397</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>Correlation_RWC_ER</td>\n",
       "      <td>AGP</td>\n",
       "      <td></td>\n",
       "      <td>0.05743</td>\n",
       "      <td>AXYLSEVXPWECHR-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.665</td>\n",
       "      <td>999999</td>\n",
       "      <td>2</td>\n",
       "      <td>JCP2022_004567</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1189398 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Compartment                      Feature Channel  \\\n",
       "0             Cells    RadialDistributionFracAtD           \n",
       "1            Nuclei             AreaShapeZernike           \n",
       "2            Nuclei  RadialDistribution_RadialCV    Mito   \n",
       "3         Cytoplasm   RadialDistribution_FracAtD      ER   \n",
       "4         Cytoplasm   RadialDistribution_FracAtD     DNA   \n",
       "...             ...                          ...     ...   \n",
       "1189393       Cells           Texture_SumEntropy     RNA   \n",
       "1189394      Nuclei         AreaShapeCompactness           \n",
       "1189395       Cells    AreaShapeMaxFeretDiameter           \n",
       "1189396      Nuclei          Texture_Correlation      ER   \n",
       "1189397      Nuclei           Correlation_RWC_ER     AGP   \n",
       "\n",
       "                       Suffix  Feature significance  \\\n",
       "0        _mito_tubeness_3of16               0.08213   \n",
       "1                        _6_2               0.00003   \n",
       "2                       _3of4               0.02041   \n",
       "3                       _2of4               0.00227   \n",
       "4                       _1of4               0.01685   \n",
       "...                       ...                   ...   \n",
       "1189393            _10_01_256               0.02717   \n",
       "1189394                                     0.00000   \n",
       "1189395                                     0.00138   \n",
       "1189396            _10_02_256               0.19502   \n",
       "1189397                                     0.05743   \n",
       "\n",
       "                        Perturbation  \\\n",
       "0        AIRPKJLLJCUQSV-UHFFFAOYSA-N   \n",
       "1        DTCQXSFBETURSZ-UHFFFAOYSA-N   \n",
       "2        UQEZJEIWCQNVQU-UHFFFAOYSA-N   \n",
       "3        MOQWDHSSODJEDU-UHFFFAOYSA-N   \n",
       "4        WPCDYOHCABUJAF-UHFFFAOYSA-N   \n",
       "...                              ...   \n",
       "1189393  KHEBJWNXOZKKBY-UHFFFAOYSA-N   \n",
       "1189394  QGGLNUGOWVBAJC-UHFFFAOYSA-N   \n",
       "1189395  SBJVCDHWJCQQIQ-UHFFFAOYSA-N   \n",
       "1189396  FCQDLIHIOSXHMH-UHFFFAOYSA-N   \n",
       "1189397  AXYLSEVXPWECHR-UHFFFAOYSA-N   \n",
       "\n",
       "                                Perturbation example image  Median  Gene Rank  \\\n",
       "0        {\"img_src\": \"https://phenaid.ardigen.com/stati...  -0.964     999999   \n",
       "1        {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.244     999999   \n",
       "2        {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.514     999999   \n",
       "3        {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.486     999999   \n",
       "4        {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.097     999999   \n",
       "...                                                    ...     ...        ...   \n",
       "1189393  {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.227     999999   \n",
       "1189394  {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.906     999999   \n",
       "1189395  {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.688     999999   \n",
       "1189396  {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.206     999999   \n",
       "1189397  {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.665     999999   \n",
       "\n",
       "         Feature Rank         JCP2022 Resources Synonyms  \n",
       "0                   9  JCP2022_001647      None     None  \n",
       "1                   0  JCP2022_018053      None     None  \n",
       "2                   4  JCP2022_090828      None     None  \n",
       "3                   2  JCP2022_055532      None     None  \n",
       "4                   1  JCP2022_100243      None     None  \n",
       "...               ...             ...       ...      ...  \n",
       "1189393             2  JCP2022_044597      None     None  \n",
       "1189394             1  JCP2022_073238      None     None  \n",
       "1189395             8  JCP2022_082092      None     None  \n",
       "1189396             5  JCP2022_019780      None     None  \n",
       "1189397             2  JCP2022_004567      None     None  \n",
       "\n",
       "[1189398 rows x 13 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_parquet(path / 'compound_interpretable_features.parquet?download=1')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "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>Compartment</th>\n",
       "      <th>Feature</th>\n",
       "      <th>Channel</th>\n",
       "      <th>Suffix</th>\n",
       "      <th>Feature significance</th>\n",
       "      <th>Perturbation</th>\n",
       "      <th>Perturbation example image</th>\n",
       "      <th>Median</th>\n",
       "      <th>Gene Rank</th>\n",
       "      <th>Feature Rank</th>\n",
       "      <th>JCP2022</th>\n",
       "      <th>Resources</th>\n",
       "      <th>Synonyms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Cells</td>\n",
       "      <td>RadialDistributionFracAtD</td>\n",
       "      <td></td>\n",
       "      <td>_mito_tubeness_3of16</td>\n",
       "      <td>0.08213</td>\n",
       "      <td>AIRPKJLLJCUQSV-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-0.964</td>\n",
       "      <td>999999</td>\n",
       "      <td>9</td>\n",
       "      <td>JCP2022_001647</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>AreaShapeZernike</td>\n",
       "      <td></td>\n",
       "      <td>_6_2</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>DTCQXSFBETURSZ-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.244</td>\n",
       "      <td>999999</td>\n",
       "      <td>0</td>\n",
       "      <td>JCP2022_018053</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>RadialDistribution_RadialCV</td>\n",
       "      <td>Mito</td>\n",
       "      <td>_3of4</td>\n",
       "      <td>0.02041</td>\n",
       "      <td>UQEZJEIWCQNVQU-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.514</td>\n",
       "      <td>999999</td>\n",
       "      <td>4</td>\n",
       "      <td>JCP2022_090828</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Cytoplasm</td>\n",
       "      <td>RadialDistribution_FracAtD</td>\n",
       "      <td>ER</td>\n",
       "      <td>_2of4</td>\n",
       "      <td>0.00227</td>\n",
       "      <td>MOQWDHSSODJEDU-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.486</td>\n",
       "      <td>999999</td>\n",
       "      <td>2</td>\n",
       "      <td>JCP2022_055532</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cytoplasm</td>\n",
       "      <td>RadialDistribution_FracAtD</td>\n",
       "      <td>DNA</td>\n",
       "      <td>_1of4</td>\n",
       "      <td>0.01685</td>\n",
       "      <td>WPCDYOHCABUJAF-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.097</td>\n",
       "      <td>999999</td>\n",
       "      <td>1</td>\n",
       "      <td>JCP2022_100243</td>\n",
       "      <td>None</td>\n",
       "      <td>None</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189393</th>\n",
       "      <td>Cells</td>\n",
       "      <td>Texture_SumEntropy</td>\n",
       "      <td>RNA</td>\n",
       "      <td>_10_01_256</td>\n",
       "      <td>0.02717</td>\n",
       "      <td>KHEBJWNXOZKKBY-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.227</td>\n",
       "      <td>999999</td>\n",
       "      <td>2</td>\n",
       "      <td>JCP2022_044597</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189394</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>AreaShapeCompactness</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>0.00000</td>\n",
       "      <td>QGGLNUGOWVBAJC-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.906</td>\n",
       "      <td>999999</td>\n",
       "      <td>1</td>\n",
       "      <td>JCP2022_073238</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189395</th>\n",
       "      <td>Cells</td>\n",
       "      <td>AreaShapeMaxFeretDiameter</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>0.00138</td>\n",
       "      <td>SBJVCDHWJCQQIQ-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.688</td>\n",
       "      <td>999999</td>\n",
       "      <td>8</td>\n",
       "      <td>JCP2022_082092</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189396</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>Texture_Correlation</td>\n",
       "      <td>ER</td>\n",
       "      <td>_10_02_256</td>\n",
       "      <td>0.19502</td>\n",
       "      <td>FCQDLIHIOSXHMH-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>1.206</td>\n",
       "      <td>999999</td>\n",
       "      <td>5</td>\n",
       "      <td>JCP2022_019780</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1189397</th>\n",
       "      <td>Nuclei</td>\n",
       "      <td>Correlation_RWC_ER</td>\n",
       "      <td>AGP</td>\n",
       "      <td></td>\n",
       "      <td>0.05743</td>\n",
       "      <td>AXYLSEVXPWECHR-UHFFFAOYSA-N</td>\n",
       "      <td>{\"img_src\": \"https://phenaid.ardigen.com/stati...</td>\n",
       "      <td>-1.665</td>\n",
       "      <td>999999</td>\n",
       "      <td>2</td>\n",
       "      <td>JCP2022_004567</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1189398 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Compartment                      Feature Channel  \\\n",
       "0             Cells    RadialDistributionFracAtD           \n",
       "1            Nuclei             AreaShapeZernike           \n",
       "2            Nuclei  RadialDistribution_RadialCV    Mito   \n",
       "3         Cytoplasm   RadialDistribution_FracAtD      ER   \n",
       "4         Cytoplasm   RadialDistribution_FracAtD     DNA   \n",
       "...             ...                          ...     ...   \n",
       "1189393       Cells           Texture_SumEntropy     RNA   \n",
       "1189394      Nuclei         AreaShapeCompactness           \n",
       "1189395       Cells    AreaShapeMaxFeretDiameter           \n",
       "1189396      Nuclei          Texture_Correlation      ER   \n",
       "1189397      Nuclei           Correlation_RWC_ER     AGP   \n",
       "\n",
       "                       Suffix  Feature significance  \\\n",
       "0        _mito_tubeness_3of16               0.08213   \n",
       "1                        _6_2               0.00003   \n",
       "2                       _3of4               0.02041   \n",
       "3                       _2of4               0.00227   \n",
       "4                       _1of4               0.01685   \n",
       "...                       ...                   ...   \n",
       "1189393            _10_01_256               0.02717   \n",
       "1189394                                     0.00000   \n",
       "1189395                                     0.00138   \n",
       "1189396            _10_02_256               0.19502   \n",
       "1189397                                     0.05743   \n",
       "\n",
       "                        Perturbation  \\\n",
       "0        AIRPKJLLJCUQSV-UHFFFAOYSA-N   \n",
       "1        DTCQXSFBETURSZ-UHFFFAOYSA-N   \n",
       "2        UQEZJEIWCQNVQU-UHFFFAOYSA-N   \n",
       "3        MOQWDHSSODJEDU-UHFFFAOYSA-N   \n",
       "4        WPCDYOHCABUJAF-UHFFFAOYSA-N   \n",
       "...                              ...   \n",
       "1189393  KHEBJWNXOZKKBY-UHFFFAOYSA-N   \n",
       "1189394  QGGLNUGOWVBAJC-UHFFFAOYSA-N   \n",
       "1189395  SBJVCDHWJCQQIQ-UHFFFAOYSA-N   \n",
       "1189396  FCQDLIHIOSXHMH-UHFFFAOYSA-N   \n",
       "1189397  AXYLSEVXPWECHR-UHFFFAOYSA-N   \n",
       "\n",
       "                                Perturbation example image  Median  Gene Rank  \\\n",
       "0        {\"img_src\": \"https://phenaid.ardigen.com/stati...  -0.964     999999   \n",
       "1        {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.244     999999   \n",
       "2        {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.514     999999   \n",
       "3        {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.486     999999   \n",
       "4        {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.097     999999   \n",
       "...                                                    ...     ...        ...   \n",
       "1189393  {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.227     999999   \n",
       "1189394  {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.906     999999   \n",
       "1189395  {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.688     999999   \n",
       "1189396  {\"img_src\": \"https://phenaid.ardigen.com/stati...   1.206     999999   \n",
       "1189397  {\"img_src\": \"https://phenaid.ardigen.com/stati...  -1.665     999999   \n",
       "\n",
       "         Feature Rank         JCP2022 Resources Synonyms  \n",
       "0                   9  JCP2022_001647      None     None  \n",
       "1                   0  JCP2022_018053      None     None  \n",
       "2                   4  JCP2022_090828      None     None  \n",
       "3                   2  JCP2022_055532      None     None  \n",
       "4                   1  JCP2022_100243      None     None  \n",
       "...               ...             ...       ...      ...  \n",
       "1189393             2  JCP2022_044597      None     None  \n",
       "1189394             1  JCP2022_073238      None     None  \n",
       "1189395             8  JCP2022_082092      None     None  \n",
       "1189396             5  JCP2022_019780      None     None  \n",
       "1189397             2  JCP2022_004567      None     None  \n",
       "\n",
       "[1189398 rows x 13 columns]"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Compound(76974213), Compound(11467167), Compound(11434515), Compound(11228026)]\n"
     ]
    }
   ],
   "source": [
    "import pubchempy as pcp\n",
    "import time\n",
    "\n",
    "def get_compound_name_and_synonyms_from_inchikey(inchikey):\n",
    "    \"\"\"\n",
    "    Retrieve a compound name and all possible synonyms based on an InChIKey using PubChemPy.\n",
    "    \n",
    "    Args:\n",
    "        inchikey (str): The InChIKey of the compound\n",
    "        \n",
    "    Returns:\n",
    "        dict: A dictionary containing the compound name, CID, and synonyms\n",
    "    \"\"\"\n",
    "    result = {\n",
    "        \"inchikey\": inchikey,\n",
    "        \"cid\": None,\n",
    "        \"name\": None,\n",
    "        \"synonyms\": [],\n",
    "        \"status\": \"success\"\n",
    "    }\n",
    "    \n",
    "    try:\n",
    "        # Step 1: Get compounds by InChIKey\n",
    "        compounds = pcp.get_compounds(inchikey, 'inchikey')\n",
    "    except Exception as e:\n",
    "        result[\"status\"] = \"error\"\n",
    "        result[\"error\"] = str(e)\n",
    "        return result\n",
    "    \n",
    "    # if compounds:\n",
    "        # compound = compounds[0]\n",
    "    return compounds\n",
    "\n",
    "# Example usage\n",
    "inchikey = \"ASMXXROZKSBQIH\"\n",
    "result = get_compound_name_and_synonyms_from_inchikey(inchikey)\n",
    "print(result)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[]\n",
      "['SCHEMBL72140', 'SCHEMBL12964939', 'SCHEMBL14021458', 'NS00004667']\n",
      "['Aclidinium', 'Aclidinium ion', 'Aclidinium cation', 'UNII-K17VY42F6C', 'K17VY42F6C', '727649-81-2', 'CHEBI:65346', 'DTXSID00223070', '(3R)-3-[2-hydroxy(di-2-thienyl)acetoxy]-1-(3-phenoxypropyl)-1-azoniabicyclo[2.2.2]octane', '(3R)-3-(2-HYDROXY(DI-2-THIENYL)ACETOXY)-1-(3-PHENOXYPROPYL)-1-AZONIABICYCLO(2.2.2)OCTANE', '1-AZONIABICYCLO(2.2.2)OCTANE, 3-((HYDROXYDI-2-THIENYLACETYL)OXY)-1-(3-PHENOXYPROPYL)-, (3R)-', 'Aclidinio', 'DTXCID00145561', 'CHEMBL551466', 'ACLIDINIUM [VANDF]', 'ACLIDINIUM [WHO-DD]', 'SCHEMBL72141', 'GTPL7449', 'CHEMBL1194325', 'SCHEMBL15096073', 'BDBM50296331', 'DB08897', 'NCGC00386257-02', 'HY-159686', 'AB01565828_02', 'Q521173', 'BRD-K74363950-004-01-0', '[(3R)-1-(3-phenoxypropyl)-1-azoniabicyclo[2.2.2]octan-3-yl] 2-hydroxy-2,2-dithiophen-2-ylacetate', '[(8R)-1-[3-(phenoxy)propyl]-1-azoniabicyclo[2.2.2]octan-8-yl] 2-hydroxy-2,2-di(thiophen-2-yl)acetate']\n",
      "['C6V6LNU2YL', 'SCHEMBL2075481', 'SCHEMBL13115694', '(3S)-3-[(2-Hydroxy-2,2-di-2-thienylacetyl)oxy]-1-(3-phenoxypropyl)-1-azoniabicyclo[2.2.2]octane', '1-Azoniabicyclo[2.2.2]octane, 3-[(2-hydroxy-2,2-di-2-thienylacetyl)oxy]-1-(3-phenoxypropyl)-, (3S)-', '1-Azoniabicyclo[2.2.2]octane, 3-[(hydroxydi-2-thienylacetyl)oxy]-1-(3-phenoxypropyl)-, (3S)-', '3-[(2-Hydroxy-2,2-di-2-thienylacetyl)oxy]-1-(3-phenoxypropyl)-1-azoniabicyclo[2.2.2]octane, (3S)-', '760163-21-1']\n"
     ]
    }
   ],
   "source": [
    "for r in result:\n",
    "    print(r.synonyms)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "tahoe",
   "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": "3.11.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}