{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "import pandas as pd\n",
    "\n",
    "data_file = Path('../../data/Macro16_SIME_Synthesis/fixed_macrolides_2025.csv')\n",
    "macrolactondb_file = Path('../../data/MacrolactoneDB/ring16/temp.csv')\n",
    "synthesis_df = pd.read_csv(data_file)\n",
    "synthesis_df['synthesis'] = 'SIME'\n",
    "macrolactondb_df = pd.read_csv(macrolactondb_file)\n",
    "macrolactondb_df['synthesis'] = 'MacrolactonDB'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>IDs</th>\n",
       "      <th>molecule_pref_name</th>\n",
       "      <th>max_pChEMBL</th>\n",
       "      <th>max_pChEMBL_target</th>\n",
       "      <th># Target Organisms</th>\n",
       "      <th>Target Organisms</th>\n",
       "      <th># Known Targets</th>\n",
       "      <th>Known Targets</th>\n",
       "      <th>target_pref_name</th>\n",
       "      <th>smiles</th>\n",
       "      <th>synthesis</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CHEMBL94657</td>\n",
       "      <td>PATUPILONE</td>\n",
       "      <td>10.67</td>\n",
       "      <td>CHEMBL1075590</td>\n",
       "      <td>695</td>\n",
       "      <td>Sus scrofa, Mus musculus, None, Plasmodium fal...</td>\n",
       "      <td>695</td>\n",
       "      <td>CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...</td>\n",
       "      <td>AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...</td>\n",
       "      <td>C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CHEMBL94657</td>\n",
       "      <td>PATUPILONE</td>\n",
       "      <td>10.67</td>\n",
       "      <td>CHEMBL1075590</td>\n",
       "      <td>695</td>\n",
       "      <td>Sus scrofa, Mus musculus, None, Plasmodium fal...</td>\n",
       "      <td>695</td>\n",
       "      <td>CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...</td>\n",
       "      <td>AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...</td>\n",
       "      <td>C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>CHEMBL1554</td>\n",
       "      <td>DACTINOMYCIN</td>\n",
       "      <td>10.10</td>\n",
       "      <td>CHEMBL614533</td>\n",
       "      <td>177</td>\n",
       "      <td>Giardia intestinalis, Trypanosoma cruzi, Equus...</td>\n",
       "      <td>177</td>\n",
       "      <td>CHEMBL388, CHEMBL614151, CHEMBL3577, CHEMBL551...</td>\n",
       "      <td>HT-29, CCRF-CEM, WIL2-NS, Unchecked, Caspase-7...</td>\n",
       "      <td>Cc1c2oc3c(C)ccc(C(=O)N[C@@H]4C(=O)N[C@H](C(C)C...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CHEMBL1173445</td>\n",
       "      <td>LARGAZOLE</td>\n",
       "      <td>8.80</td>\n",
       "      <td>CHEMBL612545</td>\n",
       "      <td>45</td>\n",
       "      <td>Homo sapiens, None</td>\n",
       "      <td>45</td>\n",
       "      <td>CHEMBL392, CHEMBL3192, CHEMBL3524, CHEMBL5103,...</td>\n",
       "      <td>Histone deacetylase 9, Ubiquitin-like modifier...</td>\n",
       "      <td>CCCCCCCC(=O)SCC/C=C/[C@@H]1CC(=O)NCc2nc(cs2)C2...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CHEMBL3902498</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.37</td>\n",
       "      <td>CHEMBL2095194,CHEMBL3991</td>\n",
       "      <td>17</td>\n",
       "      <td>Homo sapiens, None</td>\n",
       "      <td>17</td>\n",
       "      <td>CHEMBL2820, CHEMBL3991, CHEMBL1801, CHEMBL204,...</td>\n",
       "      <td>Coagulation factor X, Kallikrein 1, Coagulatio...</td>\n",
       "      <td>Cc1cc2ccc1[C@@H](C)COC(=O)Nc1ccc(S(=O)(=O)C3CC...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             IDs molecule_pref_name  max_pChEMBL        max_pChEMBL_target  \\\n",
       "0    CHEMBL94657         PATUPILONE        10.67             CHEMBL1075590   \n",
       "1    CHEMBL94657         PATUPILONE        10.67             CHEMBL1075590   \n",
       "2     CHEMBL1554       DACTINOMYCIN        10.10              CHEMBL614533   \n",
       "3  CHEMBL1173445          LARGAZOLE         8.80              CHEMBL612545   \n",
       "4  CHEMBL3902498                NaN         9.37  CHEMBL2095194,CHEMBL3991   \n",
       "\n",
       "   # Target Organisms                                   Target Organisms  \\\n",
       "0                 695  Sus scrofa, Mus musculus, None, Plasmodium fal...   \n",
       "1                 695  Sus scrofa, Mus musculus, None, Plasmodium fal...   \n",
       "2                 177  Giardia intestinalis, Trypanosoma cruzi, Equus...   \n",
       "3                  45                                 Homo sapiens, None   \n",
       "4                  17                                 Homo sapiens, None   \n",
       "\n",
       "   # Known Targets                                      Known Targets  \\\n",
       "0              695  CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...   \n",
       "1              695  CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...   \n",
       "2              177  CHEMBL388, CHEMBL614151, CHEMBL3577, CHEMBL551...   \n",
       "3               45  CHEMBL392, CHEMBL3192, CHEMBL3524, CHEMBL5103,...   \n",
       "4               17  CHEMBL2820, CHEMBL3991, CHEMBL1801, CHEMBL204,...   \n",
       "\n",
       "                                    target_pref_name  \\\n",
       "0  AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...   \n",
       "1  AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...   \n",
       "2  HT-29, CCRF-CEM, WIL2-NS, Unchecked, Caspase-7...   \n",
       "3  Histone deacetylase 9, Ubiquitin-like modifier...   \n",
       "4  Coagulation factor X, Kallikrein 1, Coagulatio...   \n",
       "\n",
       "                                              smiles      synthesis  \n",
       "0  C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...  MacrolactonDB  \n",
       "1  C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...  MacrolactonDB  \n",
       "2  Cc1c2oc3c(C)ccc(C(=O)N[C@@H]4C(=O)N[C@H](C(C)C...  MacrolactonDB  \n",
       "3  CCCCCCCC(=O)SCC/C=C/[C@@H]1CC(=O)NCc2nc(cs2)C2...  MacrolactonDB  \n",
       "4  Cc1cc2ccc1[C@@H](C)COC(=O)Nc1ccc(S(=O)(=O)C3CC...  MacrolactonDB  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "macrolactondb_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# Target Organisms\n",
      "0      1587\n",
      "1       195\n",
      "2        99\n",
      "3        36\n",
      "4        31\n",
      "5        27\n",
      "6        18\n",
      "7         9\n",
      "8         7\n",
      "9         5\n",
      "15        2\n",
      "695       2\n",
      "10        1\n",
      "177       1\n",
      "45        1\n",
      "17        1\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# 统计 '# Target Organisms' 列的唯一值计数\n",
    "counts = macrolactondb_df['# Target Organisms'].value_counts()\n",
    "\n",
    "# 打印结果（默认按计数降序排列）\n",
    "print(counts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "是否所有值都相等： True\n"
     ]
    }
   ],
   "source": [
    "# 判断两个列是否相等，返回一个布尔Series\n",
    "equal_mask = macrolactondb_df[\"# Target Organisms\"] == macrolactondb_df[\"# Known Targets\"]\n",
    "\n",
    "# 查看是否所有行都相等\n",
    "all_equal = equal_mask.all()\n",
    "\n",
    "# 输出是否所有值都相等\n",
    "print(\"是否所有值都相等：\", all_equal)\n",
    "\n",
    "# 如果不全相等，打印出不相等的行\n",
    "if not all_equal:\n",
    "    unequal_rows = macrolactondb_df[~equal_mask]\n",
    "    print(\"不相等的行：\")\n",
    "    print(unequal_rows)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Target Organisms\n",
      "Homo sapiens                                                                                                                                          259\n",
      "Homo sapiens, None                                                                                                                                     52\n",
      "Mus musculus                                                                                                                                           19\n",
      "Human immunodeficiency virus 1                                                                                                                          7\n",
      "Plasmodium falciparum                                                                                                                                   4\n",
      "Mus musculus, Homo sapiens, None                                                                                                                        3\n",
      "Mus musculus, Homo sapiens                                                                                                                              3\n",
      "Staphylococcus aureus                                                                                                                                   2\n",
      "Sus scrofa, Mus musculus, None, Plasmodium falciparum, Homo sapiens, Rattus norvegicus                                                                  2\n",
      "None, Rattus norvegicus                                                                                                                                 2\n",
      "Escherichia coli (strain K12)                                                                                                                           2\n",
      "Giardia intestinalis, Trypanosoma cruzi, Equus caballus, Bos taurus, Mus musculus, None, Plasmodium falciparum, Chlorocebus aethiops, Homo sapiens      1\n",
      "Homo sapiens, None, Trypanosoma brucei brucei                                                                                                           1\n",
      "Plasmodium falciparum NF54, Trypanosoma cruzi, Trypanosoma brucei rhodesiense                                                                           1\n",
      "Homo sapiens, Equus caballus                                                                                                                            1\n",
      "Mus musculus, Homo sapiens, Rattus norvegicus                                                                                                           1\n",
      "Plasmodium falciparum NF54, Trypanosoma cruzi, Trypanosoma brucei rhodesiense, Rattus norvegicus                                                        1\n",
      "Schistosoma mansoni, Influenza A virus                                                                                                                  1\n",
      "Homo sapiens, Gallus gallus                                                                                                                             1\n",
      "Homo sapiens, Sus scrofa                                                                                                                                1\n",
      "Bacillus subtilis                                                                                                                                       1\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# 统计 '# Target Organisms' 列的唯一值计数\n",
    "counts = macrolactondb_df['Target Organisms'].value_counts()\n",
    "\n",
    "# 打印结果（默认按计数降序排列）\n",
    "print(counts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>IDs</th>\n",
       "      <th>molecule_pref_name</th>\n",
       "      <th>max_pChEMBL</th>\n",
       "      <th>max_pChEMBL_target</th>\n",
       "      <th># Target Organisms</th>\n",
       "      <th>Target Organisms</th>\n",
       "      <th># Known Targets</th>\n",
       "      <th>Known Targets</th>\n",
       "      <th>target_pref_name</th>\n",
       "      <th>smiles</th>\n",
       "      <th>synthesis</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>284</th>\n",
       "      <td>CHEMBL3342324</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.52</td>\n",
       "      <td>CHEMBL3341578</td>\n",
       "      <td>1</td>\n",
       "      <td>Escherichia coli (strain K12)</td>\n",
       "      <td>1</td>\n",
       "      <td>CHEMBL3341578</td>\n",
       "      <td>ATP-dependent Clp protease proteolytic subunit</td>\n",
       "      <td>C/C=C/C=C/C=C/C(=O)N[C@@H](Cc1ccccc1)C(=O)N[C@...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>338</th>\n",
       "      <td>CHEMBL3342325</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.16</td>\n",
       "      <td>CHEMBL3341578</td>\n",
       "      <td>1</td>\n",
       "      <td>Escherichia coli (strain K12)</td>\n",
       "      <td>1</td>\n",
       "      <td>CHEMBL3341578</td>\n",
       "      <td>ATP-dependent Clp protease proteolytic subunit</td>\n",
       "      <td>C/C=C/C=C/C=C/C(=O)N[C@@H](Cc1ccccc1)C(=O)N[C@...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>341</th>\n",
       "      <td>CHEMBL3742171</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.52</td>\n",
       "      <td>CHEMBL1681616</td>\n",
       "      <td>1</td>\n",
       "      <td>Staphylococcus aureus</td>\n",
       "      <td>1</td>\n",
       "      <td>CHEMBL1681616</td>\n",
       "      <td>Accessory gene regulator protein A</td>\n",
       "      <td>CC(C)[C@@H]1NC(=O)C[C@H](/C=C/c2ccccc2)OC(=O)[...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>350</th>\n",
       "      <td>CHEMBL1784527</td>\n",
       "      <td>TURNAGAINOLIDE A</td>\n",
       "      <td>6.10</td>\n",
       "      <td>CHEMBL1681616</td>\n",
       "      <td>1</td>\n",
       "      <td>Staphylococcus aureus</td>\n",
       "      <td>1</td>\n",
       "      <td>CHEMBL1681616</td>\n",
       "      <td>Accessory gene regulator protein A</td>\n",
       "      <td>CC[C@H](C)[C@@H]1NC(=O)[C@@H](C)NC(=O)[C@H](C(...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>392</th>\n",
       "      <td>CHEMBL1317175</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.55</td>\n",
       "      <td>CHEMBL1293248</td>\n",
       "      <td>1</td>\n",
       "      <td>Bacillus subtilis</td>\n",
       "      <td>1</td>\n",
       "      <td>CHEMBL1293248</td>\n",
       "      <td>4'-phosphopantetheinyl transferase ffp</td>\n",
       "      <td>CO/C1=C\\C(C)=C\\[C@@H](C)[C@@H](O)[C@@H](C)C/C(...</td>\n",
       "      <td>MacrolactonDB</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               IDs molecule_pref_name  max_pChEMBL max_pChEMBL_target  \\\n",
       "284  CHEMBL3342324                NaN         6.52      CHEMBL3341578   \n",
       "338  CHEMBL3342325                NaN         6.16      CHEMBL3341578   \n",
       "341  CHEMBL3742171                NaN         6.52      CHEMBL1681616   \n",
       "350  CHEMBL1784527   TURNAGAINOLIDE A         6.10      CHEMBL1681616   \n",
       "392  CHEMBL1317175                NaN         5.55      CHEMBL1293248   \n",
       "\n",
       "     # Target Organisms               Target Organisms  # Known Targets  \\\n",
       "284                   1  Escherichia coli (strain K12)                1   \n",
       "338                   1  Escherichia coli (strain K12)                1   \n",
       "341                   1          Staphylococcus aureus                1   \n",
       "350                   1          Staphylococcus aureus                1   \n",
       "392                   1              Bacillus subtilis                1   \n",
       "\n",
       "     Known Targets                                target_pref_name  \\\n",
       "284  CHEMBL3341578  ATP-dependent Clp protease proteolytic subunit   \n",
       "338  CHEMBL3341578  ATP-dependent Clp protease proteolytic subunit   \n",
       "341  CHEMBL1681616              Accessory gene regulator protein A   \n",
       "350  CHEMBL1681616              Accessory gene regulator protein A   \n",
       "392  CHEMBL1293248          4'-phosphopantetheinyl transferase ffp   \n",
       "\n",
       "                                                smiles      synthesis  \n",
       "284  C/C=C/C=C/C=C/C(=O)N[C@@H](Cc1ccccc1)C(=O)N[C@...  MacrolactonDB  \n",
       "338  C/C=C/C=C/C=C/C(=O)N[C@@H](Cc1ccccc1)C(=O)N[C@...  MacrolactonDB  \n",
       "341  CC(C)[C@@H]1NC(=O)C[C@H](/C=C/c2ccccc2)OC(=O)[...  MacrolactonDB  \n",
       "350  CC[C@H](C)[C@@H]1NC(=O)[C@@H](C)NC(=O)[C@H](C(...  MacrolactonDB  \n",
       "392  CO/C1=C\\C(C)=C\\[C@@H](C)[C@@H](O)[C@@H](C)C/C(...  MacrolactonDB  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 保留抗菌的数据\n",
    "\n",
    "# 定义包含细菌靶点名称的列表\n",
    "bacteria = ['Staphylococcus aureus', 'Escherichia coli', 'Bacillus subtilis']\n",
    "\n",
    "# 构造正则表达式，用 | 分隔多个目标\n",
    "pattern = '|'.join(bacteria)\n",
    "\n",
    "# 筛选出 'Target Organisms' 列中包含任意细菌名称的行\n",
    "macrolide_16_antibacterial_df = macrolactondb_df[macrolactondb_df['Target Organisms'].str.contains(pattern, case=False, na=False)]\n",
    "\n",
    "# 打印筛选后的数据\n",
    "macrolide_16_antibacterial_df\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       695\n",
       "1       695\n",
       "2       177\n",
       "3        45\n",
       "4        17\n",
       "       ... \n",
       "2017      0\n",
       "2018      0\n",
       "2019      0\n",
       "2020      0\n",
       "2021      0\n",
       "Name: # Target Organisms, Length: 2022, dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "macrolactondb_df['# Target Organisms']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 45, 15, 177, 17, 695}\n"
     ]
    }
   ],
   "source": [
    "print(set(macrolactondb_df['# Target Organisms'].to_list()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "16"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(set(macrolactondb_df['# Target Organisms'].to_list()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# macrolactondb_df[\"synthesis\"] = macrolactondb_df[\"# Target Organisms\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>original_smiles</th>\n",
       "      <th>fixed_smiles</th>\n",
       "      <th>status</th>\n",
       "      <th>message</th>\n",
       "      <th>synthesis</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     original_smiles  \\\n",
       "0  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "1  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "2  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "3  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "4  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "\n",
       "                                        fixed_smiles     status  message  \\\n",
       "0  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "1  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "2  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "3  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "4  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "\n",
       "  synthesis  \n",
       "0      SIME  \n",
       "1      SIME  \n",
       "2      SIME  \n",
       "3      SIME  \n",
       "4      SIME  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "synthesis_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "synthesis_df = synthesis_df.rename(columns={'fixed_smiles': 'smiles'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>original_smiles</th>\n",
       "      <th>smiles</th>\n",
       "      <th>status</th>\n",
       "      <th>message</th>\n",
       "      <th>synthesis</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...</td>\n",
       "      <td>CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...</td>\n",
       "      <td>corrected</td>\n",
       "      <td>修复原子 28</td>\n",
       "      <td>SIME</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     original_smiles  \\\n",
       "0  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "1  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "2  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "3  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "4  O=C1C[C@@H](O)C[C@H](O[C@H]9C[C@@](C)(OC)[C@@H...   \n",
       "\n",
       "                                              smiles     status  message  \\\n",
       "0  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "1  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "2  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "3  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "4  CCC1=C\\[C@H](O[C@H]2C[C@@](C)(OC)[C@@H](O)[C@H...  corrected  修复原子 28   \n",
       "\n",
       "  synthesis  \n",
       "0      SIME  \n",
       "1      SIME  \n",
       "2      SIME  \n",
       "3      SIME  \n",
       "4      SIME  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "synthesis_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "merge_df = pd.concat([macrolactondb_df, synthesis_df], ignore_index=True, axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "252023"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(merge_df)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 12-20 环大环内酯分析\n",
    "\n",
    "每一种环的抗菌药物数量，看下是哪一种环的抗菌药物最多。\n",
    "\n",
    "整体12-20环大环内酯的，抗菌药物有多少。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "总计数据：11036\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# 读取数据和统计\n",
    "macrolactondb_df_ring12_20 = pd.read_csv('../../data/MacrolactoneDB/ring12_20/temp.csv')\n",
    "counts = macrolactondb_df_ring12_20['Target Organisms'].value_counts()\n",
    "\n",
    "# 将 counts Series 转换成字符串并写入 txt 文件\n",
    "with open('../../data/MacrolactoneDB/ring12_20/counts.txt', 'w') as file:\n",
    "    file.write(counts.to_string())\n",
    "\n",
    "\n",
    "print(f\"总计数据：{len(macrolactondb_df_ring12_20)}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>IDs</th>\n",
       "      <th>molecule_pref_name</th>\n",
       "      <th>max_pChEMBL</th>\n",
       "      <th>max_pChEMBL_target</th>\n",
       "      <th># Target Organisms</th>\n",
       "      <th>Target Organisms</th>\n",
       "      <th># Known Targets</th>\n",
       "      <th>Known Targets</th>\n",
       "      <th>target_pref_name</th>\n",
       "      <th>smiles</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CHEMBL94657</td>\n",
       "      <td>PATUPILONE</td>\n",
       "      <td>10.67</td>\n",
       "      <td>CHEMBL1075590</td>\n",
       "      <td>695</td>\n",
       "      <td>Sus scrofa, Mus musculus, None, Plasmodium fal...</td>\n",
       "      <td>695</td>\n",
       "      <td>CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...</td>\n",
       "      <td>AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...</td>\n",
       "      <td>C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CHEMBL94657</td>\n",
       "      <td>PATUPILONE</td>\n",
       "      <td>10.67</td>\n",
       "      <td>CHEMBL1075590</td>\n",
       "      <td>695</td>\n",
       "      <td>Sus scrofa, Mus musculus, None, Plasmodium fal...</td>\n",
       "      <td>695</td>\n",
       "      <td>CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...</td>\n",
       "      <td>AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...</td>\n",
       "      <td>C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>CHEMBL449158</td>\n",
       "      <td>BRYOSTATIN</td>\n",
       "      <td>9.36</td>\n",
       "      <td>CHEMBL2996</td>\n",
       "      <td>664</td>\n",
       "      <td>Homo sapiens, None, Rattus norvegicus</td>\n",
       "      <td>664</td>\n",
       "      <td>CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...</td>\n",
       "      <td>AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...</td>\n",
       "      <td>CCC/C=C/C=C/C(=O)O[C@H]1/C(=C/C(=O)OC)C[C@H]2C...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CHEMBL1554</td>\n",
       "      <td>DACTINOMYCIN</td>\n",
       "      <td>10.10</td>\n",
       "      <td>CHEMBL614533</td>\n",
       "      <td>177</td>\n",
       "      <td>Giardia intestinalis, Trypanosoma cruzi, Equus...</td>\n",
       "      <td>177</td>\n",
       "      <td>CHEMBL388, CHEMBL614151, CHEMBL3577, CHEMBL551...</td>\n",
       "      <td>HT-29, CCRF-CEM, WIL2-NS, Unchecked, Caspase-7...</td>\n",
       "      <td>Cc1c2oc3c(C)ccc(C(=O)N[C@@H]4C(=O)N[C@H](C(C)C...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CHEMBL529</td>\n",
       "      <td>AZITHROMYCIN</td>\n",
       "      <td>8.59</td>\n",
       "      <td>CHEMBL3301413</td>\n",
       "      <td>70</td>\n",
       "      <td>None, Plasmodium falciparum, Escherichia coli,...</td>\n",
       "      <td>70</td>\n",
       "      <td>CHEMBL347, CHEMBL612313, CHEMBL354, CHEMBL3301...</td>\n",
       "      <td>Streptococcus, Unchecked, Cytochrome P450 3A4,...</td>\n",
       "      <td>CC[C@H]1OC(=O)[C@H](C)[C@@H](O[C@H]2C[C@@](C)(...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            IDs molecule_pref_name  max_pChEMBL max_pChEMBL_target  \\\n",
       "0   CHEMBL94657         PATUPILONE        10.67      CHEMBL1075590   \n",
       "1   CHEMBL94657         PATUPILONE        10.67      CHEMBL1075590   \n",
       "2  CHEMBL449158         BRYOSTATIN         9.36         CHEMBL2996   \n",
       "3    CHEMBL1554       DACTINOMYCIN        10.10       CHEMBL614533   \n",
       "4     CHEMBL529       AZITHROMYCIN         8.59      CHEMBL3301413   \n",
       "\n",
       "   # Target Organisms                                   Target Organisms  \\\n",
       "0                 695  Sus scrofa, Mus musculus, None, Plasmodium fal...   \n",
       "1                 695  Sus scrofa, Mus musculus, None, Plasmodium fal...   \n",
       "2                 664              Homo sapiens, None, Rattus norvegicus   \n",
       "3                 177  Giardia intestinalis, Trypanosoma cruzi, Equus...   \n",
       "4                  70  None, Plasmodium falciparum, Escherichia coli,...   \n",
       "\n",
       "   # Known Targets                                      Known Targets  \\\n",
       "0              695  CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...   \n",
       "1              695  CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...   \n",
       "2              664  CHEMBL612519, CHEMBL614129, CHEMBL1075484, CHE...   \n",
       "3              177  CHEMBL388, CHEMBL614151, CHEMBL3577, CHEMBL551...   \n",
       "4               70  CHEMBL347, CHEMBL612313, CHEMBL354, CHEMBL3301...   \n",
       "\n",
       "                                    target_pref_name  \\\n",
       "0  AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...   \n",
       "1  AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...   \n",
       "2  AGS, NCI-H1703, MKN-7, HT-1080, NCI-H226, Lu-6...   \n",
       "3  HT-29, CCRF-CEM, WIL2-NS, Unchecked, Caspase-7...   \n",
       "4  Streptococcus, Unchecked, Cytochrome P450 3A4,...   \n",
       "\n",
       "                                              smiles  \n",
       "0  C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...  \n",
       "1  C/C(=C\\c1csc(C)n1)[C@@H]1C[C@@H]2O[C@]2(C)CCC[...  \n",
       "2  CCC/C=C/C=C/C(=O)O[C@H]1/C(=C/C(=O)OC)C[C@H]2C...  \n",
       "3  Cc1c2oc3c(C)ccc(C(=O)N[C@@H]4C(=O)N[C@H](C(C)C...  \n",
       "4  CC[C@H]1OC(=O)[C@H](C)[C@@H](O[C@H]2C[C@@](C)(...  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "macrolactondb_df_ring12_20.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Target Organisms\n",
       "Homo sapiens                                                                                             815\n",
       "Homo sapiens, None                                                                                       180\n",
       "Plasmodium falciparum                                                                                    161\n",
       "Hepatitis C virus, None                                                                                  112\n",
       "Homo sapiens, Plasmodium falciparum                                                                       63\n",
       "                                                                                                        ... \n",
       "Giardia intestinalis, Schistosoma mansoni, Mus musculus, None, Homo sapiens, Saccharomyces cerevisiae      1\n",
       "Trypanosoma cruzi                                                                                          1\n",
       "Influenza A virus                                                                                          1\n",
       "Escherichia coli K-12                                                                                      1\n",
       "Human herpesvirus 4 (strain B95-8)                                                                         1\n",
       "Name: count, Length: 88, dtype: int64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "macrolactondb_df_ring12_20['Target Organisms'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "synthesis_df.to_parquet(\"../../data/Macro16_SIME_Synthesis/synthesis_with_sa.parquet\")  # 比CSV更快"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## chempot 绘制\n",
    "\n",
    "参考 utils/chem_viz.py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "merge_df[[\"synthesis\", \"smiles\"]].to_csv('../../data/tSNE/merge.csv', index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "“RDKit设计的分子和天然分子在结构上有何不同？” → 用 tailored。\n",
    "\n",
    "“RDKit设计的分子是否覆盖了天然分子的化学空间？” → 用 structural。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 合成分子减少为1w进行可视化\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "synthesis_df 中 synthesis=1 的样本少于10,000个。",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[16], line 13\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[38;5;66;03m# 3. 随机抽取1万个样本\u001b[39;00m\n\u001b[1;32m     12\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(synthesis_1_df) \u001b[38;5;241m<\u001b[39m \u001b[38;5;241m10000\u001b[39m:\n\u001b[0;32m---> 13\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msynthesis_df 中 synthesis=1 的样本少于10,000个。\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     15\u001b[0m sampled_synthesis_1_df \u001b[38;5;241m=\u001b[39m synthesis_1_df\u001b[38;5;241m.\u001b[39msample(n\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m10000\u001b[39m, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m42\u001b[39m)\u001b[38;5;241m.\u001b[39mreset_index(drop\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m     17\u001b[0m \u001b[38;5;66;03m# 4. 合并抽取的样本与 macrolactondb_df\u001b[39;00m\n",
      "\u001b[0;31mValueError\u001b[0m: synthesis_df 中 synthesis=1 的样本少于10,000个。"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from chemplot import Plotter\n",
    "import numpy as np\n",
    "\n",
    "# 1. 合并数据框\n",
    "merge_df = pd.concat([macrolactondb_df, synthesis_df], ignore_index=True, axis=0)\n",
    "\n",
    "# 2. 过滤出 synthesis=1 的样本\n",
    "synthesis_1_df = synthesis_df[synthesis_df['synthesis'] == 1]\n",
    "\n",
    "# 3. 随机抽取1万个样本\n",
    "if len(synthesis_1_df) < 10000:\n",
    "    raise ValueError(\"synthesis_df 中 synthesis=1 的样本少于10,000个。\")\n",
    "\n",
    "sampled_synthesis_1_df = synthesis_1_df.sample(n=10000, random_state=42).reset_index(drop=True)\n",
    "\n",
    "# 4. 合并抽取的样本与 macrolactondb_df\n",
    "final_df = pd.concat([macrolactondb_df, sampled_synthesis_1_df], ignore_index=True, axis=0).reset_index(drop=True)\n",
    "\n",
    "# 5. 使用 ChemPlot 进行可视化\n",
    "cp = Plotter.from_smiles(\n",
    "    final_df[\"smiles\"],\n",
    "    target=final_df[\"synthesis\"],\n",
    "    target_type=\"C\",\n",
    "    sim_type=\"structural\"\n",
    ")\n",
    "\n",
    "# 进行 t-SNE 降维\n",
    "cp.tsne()\n",
    "\n",
    "# 可视化结果\n",
    "cp.visualize_plot(kind=\"scatter\", size=20, remove_outliers=False, is_colored=True, colorbar=False)\n",
    "\n",
    "# 如果需要保存图像，可以取消下一行的注释\n",
    "# cp.visualize_plot(kind=\"scatter\", size=20, remove_outliers=False, is_colored=True, colorbar=False, filename=\"scatter_plot.png\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "qsarml",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}