diff --git a/nbs_tests/constants/modification.ipynb b/nbs_tests/constants/modification.ipynb
index 9163cb7c..8de89896 100644
--- a/nbs_tests/constants/modification.ipynb
+++ b/nbs_tests/constants/modification.ipynb
@@ -31,9 +31,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:52.218842Z",
+     "start_time": "2024-11-15T12:12:50.057596Z"
+    }
+   },
    "source": [
     "import os\n",
     "\n",
@@ -41,18 +44,99 @@
     "import pandas as pd\n",
     "\n",
     "from alphabase.constants._const import CONST_FILE_FOLDER\n",
+    "import alphabase.constants.modification as modification\n",
     "from alphabase.constants.modification import MOD_DF, calc_modification_mass, load_mod_df, calc_modloss_mass, \\\n",
     "    add_modifications_for_lower_case_AA, update_all_by_MOD_DF, MOD_INFO_DICT, add_new_modifications, MOD_Composition, \\\n",
     "    MOD_MASS, MOD_LOSS_IMPORTANCE"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 1
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:52.883420Z",
+     "start_time": "2024-11-15T12:12:52.872386Z"
+    }
+   },
+   "source": "modification.MOD_DF",
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "                                                mod_name  unimod_mass  \\\n",
+       "mod_name                                                                \n",
+       "Acetyl@T                                        Acetyl@T    42.010565   \n",
+       "Acetyl@Protein_N-term              Acetyl@Protein_N-term    42.010565   \n",
+       "Acetyl@S                                        Acetyl@S    42.010565   \n",
+       "Acetyl@C                                        Acetyl@C    42.010565   \n",
+       "Acetyl@Any_N-term                      Acetyl@Any_N-term    42.010565   \n",
+       "...                                                  ...          ...   \n",
+       "Ethyl@Protein_C-term                Ethyl@Protein_C-term     0.000000   \n",
+       "Cation:Na@Protein_C-term        Cation:Na@Protein_C-term     0.000000   \n",
+       "Cation:K@Protein_C-term          Cation:K@Protein_C-term     0.000000   \n",
+       "Cation:Cu[I]@Protein_C-term  Cation:Cu[I]@Protein_C-term     0.000000   \n",
+       "Cation:Li@Protein_C-term        Cation:Li@Protein_C-term     0.000000   \n",
+       "\n",
+       "                             unimod_avge_mass   composition  unimod_modloss  \\\n",
+       "mod_name                                                                      \n",
+       "Acetyl@T                              42.0367  H(2)C(2)O(1)             0.0   \n",
+       "Acetyl@Protein_N-term                 42.0367  H(2)C(2)O(1)             0.0   \n",
+       "Acetyl@S                              42.0367  H(2)C(2)O(1)             0.0   \n",
+       "Acetyl@C                              42.0367  H(2)C(2)O(1)             0.0   \n",
+       "Acetyl@Any_N-term                     42.0367  H(2)C(2)O(1)             0.0   \n",
+       "...                                       ...           ...             ...   \n",
+       "Ethyl@Protein_C-term                   0.0000      C(2)H(4)             0.0   \n",
+       "Cation:Na@Protein_C-term               0.0000    H(-1)Na(1)             0.0   \n",
+       "Cation:K@Protein_C-term                0.0000     H(-1)K(1)             0.0   \n",
+       "Cation:Cu[I]@Protein_C-term            0.0000    Cu(1)H(-1)             0.0   \n",
+       "Cation:Li@Protein_C-term               0.0000    H(-1)Li(1)             0.0   \n",
+       "\n",
+       "                            modloss_composition      classification  \\\n",
+       "mod_name                                                              \n",
+       "Acetyl@T                                         Post-translational   \n",
+       "Acetyl@Protein_N-term                            Post-translational   \n",
+       "Acetyl@S                                         Post-translational   \n",
+       "Acetyl@C                                         Post-translational   \n",
+       "Acetyl@Any_N-term                                          Multiple   \n",
+       "...                                         ...                 ...   \n",
+       "Ethyl@Protein_C-term                                     User-added   \n",
+       "Cation:Na@Protein_C-term                                 User-added   \n",
+       "Cation:K@Protein_C-term                                  User-added   \n",
+       "Cation:Cu[I]@Protein_C-term                              User-added   \n",
+       "Cation:Li@Protein_C-term                                 User-added   \n",
+       "\n",
+       "                             unimod_id  smiles  modloss_importance       mass  \\\n",
+       "mod_name                                                                        \n",
+       "Acetyl@T                             1                         0.0  42.010565   \n",
+       "Acetyl@Protein_N-term                1  C(=O)C                 0.0  42.010565   \n",
+       "Acetyl@S                             1                         0.0  42.010565   \n",
+       "Acetyl@C                             1                         0.0  42.010565   \n",
+       "Acetyl@Any_N-term                    1  C(=O)C                 0.0  42.010565   \n",
+       "...                                ...     ...                 ...        ...   \n",
+       "Ethyl@Protein_C-term                 0     OCC                 0.0  28.031300   \n",
+       "Cation:Na@Protein_C-term             0   O[Na]                 0.0  21.981944   \n",
+       "Cation:K@Protein_C-term              0    O[K]                 0.0  37.955881   \n",
+       "Cation:Cu[I]@Protein_C-term          0   O[Cu]                 0.0  61.921773   \n",
+       "Cation:Li@Protein_C-term             0   O[Li]                 0.0   6.008178   \n",
+       "\n",
+       "                             modloss_original  modloss  \n",
+       "mod_name                                                \n",
+       "Acetyl@T                                  0.0      0.0  \n",
+       "Acetyl@Protein_N-term                     0.0      0.0  \n",
+       "Acetyl@S                                  0.0      0.0  \n",
+       "Acetyl@C                                  0.0      0.0  \n",
+       "Acetyl@Any_N-term                         0.0      0.0  \n",
+       "...                                       ...      ...  \n",
+       "Ethyl@Protein_C-term                      0.0      0.0  \n",
+       "Cation:Na@Protein_C-term                  0.0      0.0  \n",
+       "Cation:K@Protein_C-term                   0.0      0.0  \n",
+       "Cation:Cu[I]@Protein_C-term               0.0      0.0  \n",
+       "Cation:Li@Protein_C-term                  0.0      0.0  \n",
+       "\n",
+       "[2796 rows x 13 columns]"
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -80,6 +164,7 @@
        "      <th>modloss_composition</th>\n",
        "      <th>classification</th>\n",
        "      <th>unimod_id</th>\n",
+       "      <th>smiles</th>\n",
        "      <th>modloss_importance</th>\n",
        "      <th>mass</th>\n",
        "      <th>modloss_original</th>\n",
@@ -99,6 +184,7 @@
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
+       "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -112,6 +198,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -127,6 +214,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td>C(=O)C</td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -142,6 +230,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -157,6 +246,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -172,6 +262,7 @@
        "      <td></td>\n",
        "      <td>Multiple</td>\n",
        "      <td>1</td>\n",
+       "      <td>C(=O)C</td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -191,153 +282,100 @@
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
+       "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>TMTpro_zero@K</th>\n",
-       "      <td>TMTpro_zero@K</td>\n",
-       "      <td>295.189592</td>\n",
-       "      <td>295.3773</td>\n",
-       "      <td>H(25)C(15)N(3)O(3)</td>\n",
+       "      <th>Ethyl@Protein_C-term</th>\n",
+       "      <td>Ethyl@Protein_C-term</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>C(2)H(4)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Chemical derivative</td>\n",
-       "      <td>2017</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>OCC</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>295.189592</td>\n",
+       "      <td>28.031300</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>TMTpro_zero@T</th>\n",
-       "      <td>TMTpro_zero@T</td>\n",
-       "      <td>295.189592</td>\n",
-       "      <td>295.3773</td>\n",
-       "      <td>H(25)C(15)N(3)O(3)</td>\n",
+       "      <th>Cation:Na@Protein_C-term</th>\n",
+       "      <td>Cation:Na@Protein_C-term</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>H(-1)Na(1)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Chemical derivative</td>\n",
-       "      <td>2017</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>O[Na]</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>295.189592</td>\n",
+       "      <td>21.981944</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>Andro-H2O@C</th>\n",
-       "      <td>Andro-H2O@C</td>\n",
-       "      <td>332.198760</td>\n",
-       "      <td>332.4339</td>\n",
-       "      <td>H(28)C(20)O(4)</td>\n",
+       "      <th>Cation:K@Protein_C-term</th>\n",
+       "      <td>Cation:K@Protein_C-term</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>H(-1)K(1)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Chemical derivative</td>\n",
-       "      <td>2025</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>O[K]</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>332.198759</td>\n",
+       "      <td>37.955881</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>His+O(2)@H</th>\n",
-       "      <td>His+O(2)@H</td>\n",
-       "      <td>169.048741</td>\n",
-       "      <td>169.1381</td>\n",
-       "      <td>H(7)C(6)N(3)O(3)</td>\n",
+       "      <th>Cation:Cu[I]@Protein_C-term</th>\n",
+       "      <td>Cation:Cu[I]@Protein_C-term</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>Cu(1)H(-1)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>2027</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>O[Cu]</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>169.048741</td>\n",
+       "      <td>61.921773</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>GlyGly@K</th>\n",
-       "      <td>GlyGly@K</td>\n",
-       "      <td>114.042927</td>\n",
-       "      <td>114.1026</td>\n",
-       "      <td>H(6)C(4)N(2)O(2)</td>\n",
+       "      <th>Cation:Li@Protein_C-term</th>\n",
+       "      <td>Cation:Li@Protein_C-term</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>H(-1)Li(1)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>121</td>\n",
-       "      <td>1000000.0</td>\n",
-       "      <td>114.042927</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>O[Li]</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6.008178</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>2685 rows × 12 columns</p>\n",
+       "<p>2796 rows × 13 columns</p>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "                                    mod_name  unimod_mass  unimod_avge_mass  \\\n",
-       "mod_name                                                                      \n",
-       "Acetyl@T                            Acetyl@T    42.010565           42.0367   \n",
-       "Acetyl@Protein_N-term  Acetyl@Protein_N-term    42.010565           42.0367   \n",
-       "Acetyl@S                            Acetyl@S    42.010565           42.0367   \n",
-       "Acetyl@C                            Acetyl@C    42.010565           42.0367   \n",
-       "Acetyl@Any_N-term          Acetyl@Any_N-term    42.010565           42.0367   \n",
-       "...                                      ...          ...               ...   \n",
-       "TMTpro_zero@K                  TMTpro_zero@K   295.189592          295.3773   \n",
-       "TMTpro_zero@T                  TMTpro_zero@T   295.189592          295.3773   \n",
-       "Andro-H2O@C                      Andro-H2O@C   332.198760          332.4339   \n",
-       "His+O(2)@H                        His+O(2)@H   169.048741          169.1381   \n",
-       "GlyGly@K                            GlyGly@K   114.042927          114.1026   \n",
-       "\n",
-       "                              composition  unimod_modloss modloss_composition  \\\n",
-       "mod_name                                                                        \n",
-       "Acetyl@T                     H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@Protein_N-term        H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@S                     H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@C                     H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@Any_N-term            H(2)C(2)O(1)             0.0                       \n",
-       "...                                   ...             ...                 ...   \n",
-       "TMTpro_zero@K          H(25)C(15)N(3)O(3)             0.0                       \n",
-       "TMTpro_zero@T          H(25)C(15)N(3)O(3)             0.0                       \n",
-       "Andro-H2O@C                H(28)C(20)O(4)             0.0                       \n",
-       "His+O(2)@H               H(7)C(6)N(3)O(3)             0.0                       \n",
-       "GlyGly@K                 H(6)C(4)N(2)O(2)             0.0                       \n",
-       "\n",
-       "                            classification  unimod_id  modloss_importance  \\\n",
-       "mod_name                                                                    \n",
-       "Acetyl@T                Post-translational          1                 0.0   \n",
-       "Acetyl@Protein_N-term   Post-translational          1                 0.0   \n",
-       "Acetyl@S                Post-translational          1                 0.0   \n",
-       "Acetyl@C                Post-translational          1                 0.0   \n",
-       "Acetyl@Any_N-term                 Multiple          1                 0.0   \n",
-       "...                                    ...        ...                 ...   \n",
-       "TMTpro_zero@K          Chemical derivative       2017                 0.0   \n",
-       "TMTpro_zero@T          Chemical derivative       2017                 0.0   \n",
-       "Andro-H2O@C            Chemical derivative       2025                 0.0   \n",
-       "His+O(2)@H              Post-translational       2027                 0.0   \n",
-       "GlyGly@K                Post-translational        121           1000000.0   \n",
-       "\n",
-       "                             mass  modloss_original  modloss  \n",
-       "mod_name                                                      \n",
-       "Acetyl@T                42.010565               0.0      0.0  \n",
-       "Acetyl@Protein_N-term   42.010565               0.0      0.0  \n",
-       "Acetyl@S                42.010565               0.0      0.0  \n",
-       "Acetyl@C                42.010565               0.0      0.0  \n",
-       "Acetyl@Any_N-term       42.010565               0.0      0.0  \n",
-       "...                           ...               ...      ...  \n",
-       "TMTpro_zero@K          295.189592               0.0      0.0  \n",
-       "TMTpro_zero@T          295.189592               0.0      0.0  \n",
-       "Andro-H2O@C            332.198759               0.0      0.0  \n",
-       "His+O(2)@H             169.048741               0.0      0.0  \n",
-       "GlyGly@K               114.042927               0.0      0.0  \n",
-       "\n",
-       "[2685 rows x 12 columns]"
       ]
      },
-     "execution_count": null,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": "MOD_DF"
+   "execution_count": 2
   },
   {
    "cell_type": "markdown",
@@ -348,23 +386,52 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:53.785577Z",
+     "start_time": "2024-11-15T12:12:53.781807Z"
+    }
+   },
+   "source": [
+    "#| hide\n",
+    "for mod, unimod_mass, mass in MOD_DF[['mod_name','unimod_mass','mass']].values:\n",
+    "    if abs(unimod_mass-mass) > 1e-5:\n",
+    "        print(f\"{mod}: unimod mod={unimod_mass}, formula mass={mass}\")"
+   ],
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Delta:Hg(1)@C: unimod mod=201.970617, formula mass=201.9706434\n"
+      "Delta:Hg(1)@C: unimod mod=201.970617, formula mass=201.9706434\n",
+      "Pro->(2S,4R)-4-fluoroproline@P: unimod mod=0.0, formula mass=17.9905781305\n",
+      "Pro->(2S,4S)-4fluoroproline@P: unimod mod=0.0, formula mass=17.9905781305\n",
+      "Pro->(2S)-1,3-thiazolidine-2-carboxylic_acid@P: unimod mod=0.0, formula mass=17.95642110994\n",
+      "Pro->(4R)-1,3-Thiazolidine-4-carboxylic_acid@P: unimod mod=0.0, formula mass=17.95642110994\n",
+      "Pro->(2S,4R)-4-hydroxyproline@P: unimod mod=0.0, formula mass=15.99491461957\n",
+      "Pro->(DL)-pipecolic_acid@P: unimod mod=0.0, formula mass=14.01565006446\n",
+      "Pro->3,4-Dehydro-L-proline@P: unimod mod=0.0, formula mass=-2.01565006446\n",
+      "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-carboxylic_acid@P: unimod mod=0.0, formula mass=12.0\n",
+      "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-carboxylic_acid@P: unimod mod=0.0, formula mass=12.0\n",
+      "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxylic_acid@P: unimod mod=0.0, formula mass=54.04695019338\n",
+      "Pro->(DL)-5-trifluoromethylproline@P: unimod mod=0.0, formula mass=67.98738445596\n",
+      "mTRAQ@Protein_N-term: unimod mod=0.0, formula mass=140.09496301519\n",
+      "mTRAQ:13C(3)15N(1)@Protein_N-term: unimod mod=0.0, formula mass=144.10206241485002\n",
+      "mTRAQ:13C(6)15N(2)@Protein_N-term: unimod mod=0.0, formula mass=148.10916181451003\n",
+      "Biotin@Protein_N-term: unimod mod=0.0, formula mass=226.07759887362\n",
+      "Carbamidomethyl@Protein_N-term: unimod mod=0.0, formula mass=57.021463720689994\n",
+      "Propionamide@Protein_N-term: unimod mod=0.0, formula mass=71.03711378515\n",
+      "Pyridylacetyl@Protein_N-term: unimod mod=0.0, formula mass=119.03711378515\n",
+      "Methyl@Protein_C-term: unimod mod=0.0, formula mass=14.01565006446\n",
+      "Ethyl@Protein_C-term: unimod mod=0.0, formula mass=28.03130012892\n",
+      "Cation:Na@Protein_C-term: unimod mod=0.0, formula mass=21.981944249770002\n",
+      "Cation:K@Protein_C-term: unimod mod=0.0, formula mass=37.95588145417\n",
+      "Cation:Cu[I]@Protein_C-term: unimod mod=0.0, formula mass=61.921772687769995\n",
+      "Cation:Li@Protein_C-term: unimod mod=0.0, formula mass=6.00817840437\n"
      ]
     }
    ],
-   "source": [
-    "#| hide\n",
-    "for mod, unimod_mass, mass in MOD_DF[['mod_name','unimod_mass','mass']].values:\n",
-    "    if abs(unimod_mass-mass) > 1e-5:\n",
-    "        print(f\"{mod}: unimod mod={unimod_mass}, formula mass={mass}\")"
-   ]
+   "execution_count": 3
   },
   {
    "cell_type": "markdown",
@@ -387,9 +454,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:55.619757Z",
+     "start_time": "2024-11-15T12:12:55.616082Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "seq = 'AGHCEWQMK'\n",
@@ -400,13 +470,18 @@
     "    calc_modification_mass(len(seq), mod_names, mod_sites),\n",
     "    [42.01056468, 0, 0, 57.02146372, 0, 0, 0, 15.99491462, 0]\n",
     ")"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 4
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:56.709997Z",
+     "start_time": "2024-11-15T12:12:56.534087Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "mod_names = ['Oxidation@M', 'Phospho@S', 'Carbamidomethyl@C']\n",
@@ -431,7 +506,9 @@
     "    [97.97689557, 97.97689557, 97.97689557,  0 ,  0,\n",
     "        0,  0 ,  0,  0]\n",
     ")"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 5
   },
   {
    "cell_type": "markdown",
@@ -445,11 +522,145 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:57.662537Z",
+     "start_time": "2024-11-15T12:12:57.654234Z"
+    }
+   },
+   "source": [
+    "MOD_DF.drop_duplicates('classification')"
+   ],
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "                                                      mod_name  unimod_mass  \\\n",
+       "mod_name                                                                      \n",
+       "Acetyl@T                                              Acetyl@T    42.010565   \n",
+       "Acetyl@Any_N-term                            Acetyl@Any_N-term    42.010565   \n",
+       "Acetyl@Y                                              Acetyl@Y    42.010565   \n",
+       "Acetyl@R                                              Acetyl@R    42.010565   \n",
+       "ICAT-G@C                                              ICAT-G@C   486.251206   \n",
+       "Oxidation@G^Any_C-term                  Oxidation@G^Any_C-term    15.994915   \n",
+       "Hex@C                                                    Hex@C   162.052824   \n",
+       "Hex@T                                                    Hex@T   162.052824   \n",
+       "Hex@N                                                    Hex@N   162.052824   \n",
+       "His->Asn@H                                          His->Asn@H   -23.015984   \n",
+       "Delta:H(4)C(3)@K                              Delta:H(4)C(3)@K    40.031300   \n",
+       "Fluoro@Y                                              Fluoro@Y    17.990578   \n",
+       "Myristoleyl@G^Protein_N-term      Myristoleyl@G^Protein_N-term   208.182715   \n",
+       "HexN@K                                                  HexN@K   161.068808   \n",
+       "Pro->(2S,4R)-4-fluoroproline@P  Pro->(2S,4R)-4-fluoroproline@P     0.000000   \n",
+       "\n",
+       "                                unimod_avge_mass             composition  \\\n",
+       "mod_name                                                                   \n",
+       "Acetyl@T                                 42.0367            H(2)C(2)O(1)   \n",
+       "Acetyl@Any_N-term                        42.0367            H(2)C(2)O(1)   \n",
+       "Acetyl@Y                                 42.0367            H(2)C(2)O(1)   \n",
+       "Acetyl@R                                 42.0367            H(2)C(2)O(1)   \n",
+       "ICAT-G@C                                486.6253  H(38)C(22)N(4)O(6)S(1)   \n",
+       "Oxidation@G^Any_C-term                   15.9994                    O(1)   \n",
+       "Hex@C                                   162.1406           H(10)C(6)O(5)   \n",
+       "Hex@T                                   162.1406           H(10)C(6)O(5)   \n",
+       "Hex@N                                   162.1406           H(10)C(6)O(5)   \n",
+       "His->Asn@H                              -23.0366     H(-1)C(-2)N(-1)O(1)   \n",
+       "Delta:H(4)C(3)@K                         40.0639                H(4)C(3)   \n",
+       "Fluoro@Y                                 17.9905               H(-1)F(1)   \n",
+       "Myristoleyl@G^Protein_N-term            208.3398          H(24)C(14)O(1)   \n",
+       "HexN@K                                  161.1558       H(11)C(6)N(1)O(4)   \n",
+       "Pro->(2S,4R)-4-fluoroproline@P            0.0000               F(1)H(-1)   \n",
+       "\n",
+       "                                unimod_modloss modloss_composition  \\\n",
+       "mod_name                                                             \n",
+       "Acetyl@T                              0.000000                       \n",
+       "Acetyl@Any_N-term                     0.000000                       \n",
+       "Acetyl@Y                              0.000000                       \n",
+       "Acetyl@R                              0.000000                       \n",
+       "ICAT-G@C                              0.000000                       \n",
+       "Oxidation@G^Any_C-term                0.000000                       \n",
+       "Hex@C                                 0.000000                       \n",
+       "Hex@T                               162.052824       H(10)C(6)O(5)   \n",
+       "Hex@N                               162.052824       H(10)C(6)O(5)   \n",
+       "His->Asn@H                            0.000000                       \n",
+       "Delta:H(4)C(3)@K                      0.000000                       \n",
+       "Fluoro@Y                              0.000000                       \n",
+       "Myristoleyl@G^Protein_N-term          0.000000                       \n",
+       "HexN@K                                0.000000                       \n",
+       "Pro->(2S,4R)-4-fluoroproline@P        0.000000                       \n",
+       "\n",
+       "                                          classification  unimod_id  \\\n",
+       "mod_name                                                              \n",
+       "Acetyl@T                              Post-translational          1   \n",
+       "Acetyl@Any_N-term                               Multiple          1   \n",
+       "Acetyl@Y                             Chemical derivative          1   \n",
+       "Acetyl@R                                        Artefact          1   \n",
+       "ICAT-G@C                                  Isotopic label          8   \n",
+       "Oxidation@G^Any_C-term                 Pre-translational         35   \n",
+       "Hex@C                                Other glycosylation         41   \n",
+       "Hex@T                             O-linked glycosylation         41   \n",
+       "Hex@N                             N-linked glycosylation         41   \n",
+       "His->Asn@H                               AA substitution        348   \n",
+       "Delta:H(4)C(3)@K                                   Other        256   \n",
+       "Fluoro@Y                            Non-standard residue        127   \n",
+       "Myristoleyl@G^Protein_N-term            Co-translational        134   \n",
+       "HexN@K                          Synth. pep. protect. gp.        454   \n",
+       "Pro->(2S,4R)-4-fluoroproline@P                User-added          0   \n",
+       "\n",
+       "                                                            smiles  \\\n",
+       "mod_name                                                             \n",
+       "Acetyl@T                                                             \n",
+       "Acetyl@Any_N-term                                           C(=O)C   \n",
+       "Acetyl@Y                                                             \n",
+       "Acetyl@R                                                             \n",
+       "ICAT-G@C                                                             \n",
+       "Oxidation@G^Any_C-term                                               \n",
+       "Hex@C                                                                \n",
+       "Hex@T                                                                \n",
+       "Hex@N                                                                \n",
+       "His->Asn@H                                                           \n",
+       "Delta:H(4)C(3)@K                                                     \n",
+       "Fluoro@Y                                                             \n",
+       "Myristoleyl@G^Protein_N-term                                         \n",
+       "HexN@K                                                               \n",
+       "Pro->(2S,4R)-4-fluoroproline@P  F[C@@H]1C[C@H](N([Xe])C1)C(=O)[Rn]   \n",
+       "\n",
+       "                                modloss_importance        mass  \\\n",
+       "mod_name                                                         \n",
+       "Acetyl@T                                       0.0   42.010565   \n",
+       "Acetyl@Any_N-term                              0.0   42.010565   \n",
+       "Acetyl@Y                                       0.0   42.010565   \n",
+       "Acetyl@R                                       0.0   42.010565   \n",
+       "ICAT-G@C                                       0.0  486.251206   \n",
+       "Oxidation@G^Any_C-term                         0.0   15.994915   \n",
+       "Hex@C                                          0.0  162.052823   \n",
+       "Hex@T                                          0.5  162.052823   \n",
+       "Hex@N                                          0.5  162.052823   \n",
+       "His->Asn@H                                     0.0  -23.015984   \n",
+       "Delta:H(4)C(3)@K                               0.0   40.031300   \n",
+       "Fluoro@Y                                       0.0   17.990578   \n",
+       "Myristoleyl@G^Protein_N-term                   0.0  208.182715   \n",
+       "HexN@K                                         0.0  161.068808   \n",
+       "Pro->(2S,4R)-4-fluoroproline@P                 0.0   17.990578   \n",
+       "\n",
+       "                                modloss_original  modloss  \n",
+       "mod_name                                                   \n",
+       "Acetyl@T                                0.000000      0.0  \n",
+       "Acetyl@Any_N-term                       0.000000      0.0  \n",
+       "Acetyl@Y                                0.000000      0.0  \n",
+       "Acetyl@R                                0.000000      0.0  \n",
+       "ICAT-G@C                                0.000000      0.0  \n",
+       "Oxidation@G^Any_C-term                  0.000000      0.0  \n",
+       "Hex@C                                   0.000000      0.0  \n",
+       "Hex@T                                 162.052823      0.0  \n",
+       "Hex@N                                 162.052823      0.0  \n",
+       "His->Asn@H                              0.000000      0.0  \n",
+       "Delta:H(4)C(3)@K                        0.000000      0.0  \n",
+       "Fluoro@Y                                0.000000      0.0  \n",
+       "Myristoleyl@G^Protein_N-term            0.000000      0.0  \n",
+       "HexN@K                                  0.000000      0.0  \n",
+       "Pro->(2S,4R)-4-fluoroproline@P          0.000000      0.0  "
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -477,6 +688,7 @@
        "      <th>modloss_composition</th>\n",
        "      <th>classification</th>\n",
        "      <th>unimod_id</th>\n",
+       "      <th>smiles</th>\n",
        "      <th>modloss_importance</th>\n",
        "      <th>mass</th>\n",
        "      <th>modloss_original</th>\n",
@@ -496,6 +708,7 @@
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
+       "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -509,6 +722,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.000000</td>\n",
@@ -524,6 +738,7 @@
        "      <td></td>\n",
        "      <td>Multiple</td>\n",
        "      <td>1</td>\n",
+       "      <td>C(=O)C</td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.000000</td>\n",
@@ -539,6 +754,7 @@
        "      <td></td>\n",
        "      <td>Chemical derivative</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.000000</td>\n",
@@ -554,6 +770,7 @@
        "      <td></td>\n",
        "      <td>Artefact</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.000000</td>\n",
@@ -569,6 +786,7 @@
        "      <td></td>\n",
        "      <td>Isotopic label</td>\n",
        "      <td>8</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>486.251206</td>\n",
        "      <td>0.000000</td>\n",
@@ -584,6 +802,7 @@
        "      <td></td>\n",
        "      <td>Pre-translational</td>\n",
        "      <td>35</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>15.994915</td>\n",
        "      <td>0.000000</td>\n",
@@ -599,6 +818,7 @@
        "      <td></td>\n",
        "      <td>Other glycosylation</td>\n",
        "      <td>41</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>162.052823</td>\n",
        "      <td>0.000000</td>\n",
@@ -614,7 +834,8 @@
        "      <td>H(10)C(6)O(5)</td>\n",
        "      <td>O-linked glycosylation</td>\n",
        "      <td>41</td>\n",
-       "      <td>0.0</td>\n",
+       "      <td></td>\n",
+       "      <td>0.5</td>\n",
        "      <td>162.052823</td>\n",
        "      <td>162.052823</td>\n",
        "      <td>0.0</td>\n",
@@ -629,7 +850,8 @@
        "      <td>H(10)C(6)O(5)</td>\n",
        "      <td>N-linked glycosylation</td>\n",
        "      <td>41</td>\n",
-       "      <td>0.0</td>\n",
+       "      <td></td>\n",
+       "      <td>0.5</td>\n",
        "      <td>162.052823</td>\n",
        "      <td>162.052823</td>\n",
        "      <td>0.0</td>\n",
@@ -644,6 +866,7 @@
        "      <td></td>\n",
        "      <td>AA substitution</td>\n",
        "      <td>348</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>-23.015984</td>\n",
        "      <td>0.000000</td>\n",
@@ -659,6 +882,7 @@
        "      <td></td>\n",
        "      <td>Other</td>\n",
        "      <td>256</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>40.031300</td>\n",
        "      <td>0.000000</td>\n",
@@ -674,6 +898,7 @@
        "      <td></td>\n",
        "      <td>Non-standard residue</td>\n",
        "      <td>127</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>17.990578</td>\n",
        "      <td>0.000000</td>\n",
@@ -689,6 +914,7 @@
        "      <td></td>\n",
        "      <td>Co-translational</td>\n",
        "      <td>134</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>208.182715</td>\n",
        "      <td>0.000000</td>\n",
@@ -704,127 +930,39 @@
        "      <td></td>\n",
        "      <td>Synth. pep. protect. gp.</td>\n",
        "      <td>454</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>161.068808</td>\n",
        "      <td>0.000000</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Pro-&gt;(2S,4R)-4-fluoroproline@P</th>\n",
+       "      <td>Pro-&gt;(2S,4R)-4-fluoroproline@P</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>F(1)H(-1)</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td></td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>F[C@@H]1C[C@H](N([Xe])C1)C(=O)[Rn]</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>17.990578</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "                                                  mod_name  unimod_mass  \\\n",
-       "mod_name                                                                  \n",
-       "Acetyl@T                                          Acetyl@T    42.010565   \n",
-       "Acetyl@Any_N-term                        Acetyl@Any_N-term    42.010565   \n",
-       "Acetyl@Y                                          Acetyl@Y    42.010565   \n",
-       "Acetyl@R                                          Acetyl@R    42.010565   \n",
-       "ICAT-G@C                                          ICAT-G@C   486.251206   \n",
-       "Oxidation@G^Any_C-term              Oxidation@G^Any_C-term    15.994915   \n",
-       "Hex@C                                                Hex@C   162.052824   \n",
-       "Hex@T                                                Hex@T   162.052824   \n",
-       "Hex@N                                                Hex@N   162.052824   \n",
-       "His->Asn@H                                      His->Asn@H   -23.015984   \n",
-       "Delta:H(4)C(3)@K                          Delta:H(4)C(3)@K    40.031300   \n",
-       "Fluoro@Y                                          Fluoro@Y    17.990578   \n",
-       "Myristoleyl@G^Protein_N-term  Myristoleyl@G^Protein_N-term   208.182715   \n",
-       "HexN@K                                              HexN@K   161.068808   \n",
-       "\n",
-       "                              unimod_avge_mass             composition  \\\n",
-       "mod_name                                                                 \n",
-       "Acetyl@T                               42.0367            H(2)C(2)O(1)   \n",
-       "Acetyl@Any_N-term                      42.0367            H(2)C(2)O(1)   \n",
-       "Acetyl@Y                               42.0367            H(2)C(2)O(1)   \n",
-       "Acetyl@R                               42.0367            H(2)C(2)O(1)   \n",
-       "ICAT-G@C                              486.6253  H(38)C(22)N(4)O(6)S(1)   \n",
-       "Oxidation@G^Any_C-term                 15.9994                    O(1)   \n",
-       "Hex@C                                 162.1406           H(10)C(6)O(5)   \n",
-       "Hex@T                                 162.1406           H(10)C(6)O(5)   \n",
-       "Hex@N                                 162.1406           H(10)C(6)O(5)   \n",
-       "His->Asn@H                            -23.0366     H(-1)C(-2)N(-1)O(1)   \n",
-       "Delta:H(4)C(3)@K                       40.0639                H(4)C(3)   \n",
-       "Fluoro@Y                               17.9905               H(-1)F(1)   \n",
-       "Myristoleyl@G^Protein_N-term          208.3398          H(24)C(14)O(1)   \n",
-       "HexN@K                                161.1558       H(11)C(6)N(1)O(4)   \n",
-       "\n",
-       "                              unimod_modloss modloss_composition  \\\n",
-       "mod_name                                                           \n",
-       "Acetyl@T                            0.000000                       \n",
-       "Acetyl@Any_N-term                   0.000000                       \n",
-       "Acetyl@Y                            0.000000                       \n",
-       "Acetyl@R                            0.000000                       \n",
-       "ICAT-G@C                            0.000000                       \n",
-       "Oxidation@G^Any_C-term              0.000000                       \n",
-       "Hex@C                               0.000000                       \n",
-       "Hex@T                             162.052824       H(10)C(6)O(5)   \n",
-       "Hex@N                             162.052824       H(10)C(6)O(5)   \n",
-       "His->Asn@H                          0.000000                       \n",
-       "Delta:H(4)C(3)@K                    0.000000                       \n",
-       "Fluoro@Y                            0.000000                       \n",
-       "Myristoleyl@G^Protein_N-term        0.000000                       \n",
-       "HexN@K                              0.000000                       \n",
-       "\n",
-       "                                        classification  unimod_id  \\\n",
-       "mod_name                                                            \n",
-       "Acetyl@T                            Post-translational          1   \n",
-       "Acetyl@Any_N-term                             Multiple          1   \n",
-       "Acetyl@Y                           Chemical derivative          1   \n",
-       "Acetyl@R                                      Artefact          1   \n",
-       "ICAT-G@C                                Isotopic label          8   \n",
-       "Oxidation@G^Any_C-term               Pre-translational         35   \n",
-       "Hex@C                              Other glycosylation         41   \n",
-       "Hex@T                           O-linked glycosylation         41   \n",
-       "Hex@N                           N-linked glycosylation         41   \n",
-       "His->Asn@H                             AA substitution        348   \n",
-       "Delta:H(4)C(3)@K                                 Other        256   \n",
-       "Fluoro@Y                          Non-standard residue        127   \n",
-       "Myristoleyl@G^Protein_N-term          Co-translational        134   \n",
-       "HexN@K                        Synth. pep. protect. gp.        454   \n",
-       "\n",
-       "                              modloss_importance        mass  \\\n",
-       "mod_name                                                       \n",
-       "Acetyl@T                                     0.0   42.010565   \n",
-       "Acetyl@Any_N-term                            0.0   42.010565   \n",
-       "Acetyl@Y                                     0.0   42.010565   \n",
-       "Acetyl@R                                     0.0   42.010565   \n",
-       "ICAT-G@C                                     0.0  486.251206   \n",
-       "Oxidation@G^Any_C-term                       0.0   15.994915   \n",
-       "Hex@C                                        0.0  162.052823   \n",
-       "Hex@T                                        0.0  162.052823   \n",
-       "Hex@N                                        0.0  162.052823   \n",
-       "His->Asn@H                                   0.0  -23.015984   \n",
-       "Delta:H(4)C(3)@K                             0.0   40.031300   \n",
-       "Fluoro@Y                                     0.0   17.990578   \n",
-       "Myristoleyl@G^Protein_N-term                 0.0  208.182715   \n",
-       "HexN@K                                       0.0  161.068808   \n",
-       "\n",
-       "                              modloss_original  modloss  \n",
-       "mod_name                                                 \n",
-       "Acetyl@T                              0.000000      0.0  \n",
-       "Acetyl@Any_N-term                     0.000000      0.0  \n",
-       "Acetyl@Y                              0.000000      0.0  \n",
-       "Acetyl@R                              0.000000      0.0  \n",
-       "ICAT-G@C                              0.000000      0.0  \n",
-       "Oxidation@G^Any_C-term                0.000000      0.0  \n",
-       "Hex@C                                 0.000000      0.0  \n",
-       "Hex@T                               162.052823      0.0  \n",
-       "Hex@N                               162.052823      0.0  \n",
-       "His->Asn@H                            0.000000      0.0  \n",
-       "Delta:H(4)C(3)@K                      0.000000      0.0  \n",
-       "Fluoro@Y                              0.000000      0.0  \n",
-       "Myristoleyl@G^Protein_N-term          0.000000      0.0  \n",
-       "HexN@K                                0.000000      0.0  "
       ]
      },
-     "execution_count": null,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "MOD_DF.drop_duplicates('classification')"
-   ]
+   "execution_count": 6
   },
   {
    "cell_type": "markdown",
@@ -835,11 +973,204 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:58.924654Z",
+     "start_time": "2024-11-15T12:12:58.885608Z"
+    }
+   },
+   "source": [
+    "add_modifications_for_lower_case_AA()\n",
+    "modification.MOD_DFMOD_DF"
+   ],
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "                                                                                             mod_name  \\\n",
+       "mod_name                                                                                                \n",
+       "Acetyl@T                                                                                     Acetyl@T   \n",
+       "Acetyl@Protein_N-term                                                           Acetyl@Protein_N-term   \n",
+       "Acetyl@S                                                                                     Acetyl@S   \n",
+       "Acetyl@C                                                                                     Acetyl@C   \n",
+       "Acetyl@Any_N-term                                                                   Acetyl@Any_N-term   \n",
+       "...                                                                                               ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                             Pro->3,4-Dehydro-L-proline@p   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...  Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-ca...   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...  Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-ca...   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...  Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carbox...   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                             Pro->(DL)-5-trifluoromethylproline@p   \n",
+       "\n",
+       "                                                    unimod_mass  \\\n",
+       "mod_name                                                          \n",
+       "Acetyl@T                                              42.010565   \n",
+       "Acetyl@Protein_N-term                                 42.010565   \n",
+       "Acetyl@S                                              42.010565   \n",
+       "Acetyl@C                                              42.010565   \n",
+       "Acetyl@Any_N-term                                     42.010565   \n",
+       "...                                                         ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                           0.000000   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...     0.000000   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...     0.000000   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...     0.000000   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                   0.000000   \n",
+       "\n",
+       "                                                    unimod_avge_mass  \\\n",
+       "mod_name                                                               \n",
+       "Acetyl@T                                                     42.0367   \n",
+       "Acetyl@Protein_N-term                                        42.0367   \n",
+       "Acetyl@S                                                     42.0367   \n",
+       "Acetyl@C                                                     42.0367   \n",
+       "Acetyl@Any_N-term                                            42.0367   \n",
+       "...                                                              ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                  0.0000   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...            0.0000   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...            0.0000   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...            0.0000   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                          0.0000   \n",
+       "\n",
+       "                                                      composition  \\\n",
+       "mod_name                                                            \n",
+       "Acetyl@T                                             H(2)C(2)O(1)   \n",
+       "Acetyl@Protein_N-term                                H(2)C(2)O(1)   \n",
+       "Acetyl@S                                             H(2)C(2)O(1)   \n",
+       "Acetyl@C                                             H(2)C(2)O(1)   \n",
+       "Acetyl@Any_N-term                                    H(2)C(2)O(1)   \n",
+       "...                                                           ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                H(-2)   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...           C(1)   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...           C(1)   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...       C(4)H(6)   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                C(1)F(3)H(-1)   \n",
+       "\n",
+       "                                                    unimod_modloss  \\\n",
+       "mod_name                                                             \n",
+       "Acetyl@T                                                       0.0   \n",
+       "Acetyl@Protein_N-term                                          0.0   \n",
+       "Acetyl@S                                                       0.0   \n",
+       "Acetyl@C                                                       0.0   \n",
+       "Acetyl@Any_N-term                                              0.0   \n",
+       "...                                                            ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                   0.0   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...             0.0   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...             0.0   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...             0.0   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                           0.0   \n",
+       "\n",
+       "                                                   modloss_composition  \\\n",
+       "mod_name                                                                 \n",
+       "Acetyl@T                                                                 \n",
+       "Acetyl@Protein_N-term                                                    \n",
+       "Acetyl@S                                                                 \n",
+       "Acetyl@C                                                                 \n",
+       "Acetyl@Any_N-term                                                        \n",
+       "...                                                                ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                             \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...                       \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...                       \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...                       \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                                     \n",
+       "\n",
+       "                                                        classification  \\\n",
+       "mod_name                                                                 \n",
+       "Acetyl@T                                            Post-translational   \n",
+       "Acetyl@Protein_N-term                               Post-translational   \n",
+       "Acetyl@S                                            Post-translational   \n",
+       "Acetyl@C                                            Post-translational   \n",
+       "Acetyl@Any_N-term                                             Multiple   \n",
+       "...                                                                ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                User-added   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...          User-added   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...          User-added   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...          User-added   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                        User-added   \n",
+       "\n",
+       "                                                    unimod_id  \\\n",
+       "mod_name                                                        \n",
+       "Acetyl@T                                                    1   \n",
+       "Acetyl@Protein_N-term                                       1   \n",
+       "Acetyl@S                                                    1   \n",
+       "Acetyl@C                                                    1   \n",
+       "Acetyl@Any_N-term                                           1   \n",
+       "...                                                       ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                0   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...          0   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...          0   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...          0   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                        0   \n",
+       "\n",
+       "                                                                                          smiles  \\\n",
+       "mod_name                                                                                           \n",
+       "Acetyl@T                                                                                           \n",
+       "Acetyl@Protein_N-term                                                                     C(=O)C   \n",
+       "Acetyl@S                                                                                           \n",
+       "Acetyl@C                                                                                           \n",
+       "Acetyl@Any_N-term                                                                         C(=O)C   \n",
+       "...                                                                                          ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                           C1C=CC(N1([Xe]))C(=O)[Rn]   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...     [C@H]12N([Xe])[C@@H](C[C@@H]2C1)C(=O)[Rn]   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...     [C@@H]12N([Xe])[C@@H](C[C@H]2C1)C(=O)[Rn]   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...  N1([Xe])[C@@H](C[C@@H]2CCCC[C@H]12)C(=O)[Rn]   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                            FC(C1CCC(N1([Xe]))C(=O)[Rn])(F)F   \n",
+       "\n",
+       "                                                    modloss_importance  \\\n",
+       "mod_name                                                                 \n",
+       "Acetyl@T                                                           0.0   \n",
+       "Acetyl@Protein_N-term                                              0.0   \n",
+       "Acetyl@S                                                           0.0   \n",
+       "Acetyl@C                                                           0.0   \n",
+       "Acetyl@Any_N-term                                                  0.0   \n",
+       "...                                                                ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                       0.0   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...                 0.0   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...                 0.0   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...                 0.0   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                               0.0   \n",
+       "\n",
+       "                                                         mass  \\\n",
+       "mod_name                                                        \n",
+       "Acetyl@T                                            42.010565   \n",
+       "Acetyl@Protein_N-term                               42.010565   \n",
+       "Acetyl@S                                            42.010565   \n",
+       "Acetyl@C                                            42.010565   \n",
+       "Acetyl@Any_N-term                                   42.010565   \n",
+       "...                                                       ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                        -2.015650   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...  12.000000   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...  12.000000   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...  54.046950   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                67.987384   \n",
+       "\n",
+       "                                                    modloss_original  modloss  \\\n",
+       "mod_name                                                                        \n",
+       "Acetyl@T                                                         0.0      0.0   \n",
+       "Acetyl@Protein_N-term                                            0.0      0.0   \n",
+       "Acetyl@S                                                         0.0      0.0   \n",
+       "Acetyl@C                                                         0.0      0.0   \n",
+       "Acetyl@Any_N-term                                                0.0      0.0   \n",
+       "...                                                              ...      ...   \n",
+       "Pro->3,4-Dehydro-L-proline@p                                     0.0      0.0   \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...               0.0      0.0   \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...               0.0      0.0   \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...               0.0      0.0   \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                             0.0      0.0   \n",
+       "\n",
+       "                                                    lower_case_AA  \n",
+       "mod_name                                                           \n",
+       "Acetyl@T                                                    False  \n",
+       "Acetyl@Protein_N-term                                       False  \n",
+       "Acetyl@S                                                    False  \n",
+       "Acetyl@C                                                    False  \n",
+       "Acetyl@Any_N-term                                           False  \n",
+       "...                                                           ...  \n",
+       "Pro->3,4-Dehydro-L-proline@p                                 True  \n",
+       "Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-car...           True  \n",
+       "Pro->(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-car...           True  \n",
+       "Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxy...           True  \n",
+       "Pro->(DL)-5-trifluoromethylproline@p                         True  \n",
+       "\n",
+       "[5304 rows x 14 columns]"
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -867,6 +1198,7 @@
        "      <th>modloss_composition</th>\n",
        "      <th>classification</th>\n",
        "      <th>unimod_id</th>\n",
+       "      <th>smiles</th>\n",
        "      <th>modloss_importance</th>\n",
        "      <th>mass</th>\n",
        "      <th>modloss_original</th>\n",
@@ -888,6 +1220,7 @@
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
+       "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -901,6 +1234,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -917,6 +1251,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td>C(=O)C</td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -933,6 +1268,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -949,6 +1285,7 @@
        "      <td></td>\n",
        "      <td>Post-translational</td>\n",
        "      <td>1</td>\n",
+       "      <td></td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -965,6 +1302,7 @@
        "      <td></td>\n",
        "      <td>Multiple</td>\n",
        "      <td>1</td>\n",
+       "      <td>C(=O)C</td>\n",
        "      <td>0.0</td>\n",
        "      <td>42.010565</td>\n",
        "      <td>0.0</td>\n",
@@ -986,169 +1324,140 @@
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
+       "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>TMTpro_zero@k</th>\n",
-       "      <td>TMTpro_zero@k</td>\n",
-       "      <td>295.189592</td>\n",
-       "      <td>295.3773</td>\n",
-       "      <td>H(25)C(15)N(3)O(3)</td>\n",
+       "      <th>Pro-&gt;3,4-Dehydro-L-proline@p</th>\n",
+       "      <td>Pro-&gt;3,4-Dehydro-L-proline@p</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>H(-2)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Chemical derivative</td>\n",
-       "      <td>2017</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>C1C=CC(N1([Xe]))C(=O)[Rn]</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>295.189592</td>\n",
+       "      <td>-2.015650</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>TMTpro_zero@t</th>\n",
-       "      <td>TMTpro_zero@t</td>\n",
-       "      <td>295.189592</td>\n",
-       "      <td>295.3773</td>\n",
-       "      <td>H(25)C(15)N(3)O(3)</td>\n",
+       "      <th>Pro-&gt;(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-carboxylic_acid@p</th>\n",
+       "      <td>Pro-&gt;(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-ca...</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>C(1)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Chemical derivative</td>\n",
-       "      <td>2017</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>[C@H]12N([Xe])[C@@H](C[C@@H]2C1)C(=O)[Rn]</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>295.189592</td>\n",
+       "      <td>12.000000</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>Andro-H2O@c</th>\n",
-       "      <td>Andro-H2O@c</td>\n",
-       "      <td>332.198760</td>\n",
-       "      <td>332.4339</td>\n",
-       "      <td>H(28)C(20)O(4)</td>\n",
+       "      <th>Pro-&gt;(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-carboxylic_acid@p</th>\n",
+       "      <td>Pro-&gt;(1R,3S,5R)-2-Azabicyclo[3.1.0]hexane-3-ca...</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>C(1)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Chemical derivative</td>\n",
-       "      <td>2025</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>[C@@H]12N([Xe])[C@@H](C[C@H]2C1)C(=O)[Rn]</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>332.198759</td>\n",
+       "      <td>12.000000</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>His+O(2)@h</th>\n",
-       "      <td>His+O(2)@h</td>\n",
-       "      <td>169.048741</td>\n",
-       "      <td>169.1381</td>\n",
-       "      <td>H(7)C(6)N(3)O(3)</td>\n",
+       "      <th>Pro-&gt;(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxylic_acid@p</th>\n",
+       "      <td>Pro-&gt;(2S,3aS,7aS)-Octahydro-1H-indole-2-carbox...</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>C(4)H(6)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>2027</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>N1([Xe])[C@@H](C[C@@H]2CCCC[C@H]12)C(=O)[Rn]</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>169.048741</td>\n",
+       "      <td>54.046950</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>GlyGly@k</th>\n",
-       "      <td>GlyGly@k</td>\n",
-       "      <td>114.042927</td>\n",
-       "      <td>114.1026</td>\n",
-       "      <td>H(6)C(4)N(2)O(2)</td>\n",
+       "      <th>Pro-&gt;(DL)-5-trifluoromethylproline@p</th>\n",
+       "      <td>Pro-&gt;(DL)-5-trifluoromethylproline@p</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>C(1)F(3)H(-1)</td>\n",
        "      <td>0.0</td>\n",
        "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>121</td>\n",
-       "      <td>1000000.0</td>\n",
-       "      <td>114.042927</td>\n",
+       "      <td>User-added</td>\n",
+       "      <td>0</td>\n",
+       "      <td>FC(C1CCC(N1([Xe]))C(=O)[Rn])(F)F</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>67.987384</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>True</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>5103 rows × 13 columns</p>\n",
+       "<p>5304 rows × 14 columns</p>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "                                    mod_name  unimod_mass  unimod_avge_mass  \\\n",
-       "mod_name                                                                      \n",
-       "Acetyl@T                            Acetyl@T    42.010565           42.0367   \n",
-       "Acetyl@Protein_N-term  Acetyl@Protein_N-term    42.010565           42.0367   \n",
-       "Acetyl@S                            Acetyl@S    42.010565           42.0367   \n",
-       "Acetyl@C                            Acetyl@C    42.010565           42.0367   \n",
-       "Acetyl@Any_N-term          Acetyl@Any_N-term    42.010565           42.0367   \n",
-       "...                                      ...          ...               ...   \n",
-       "TMTpro_zero@k                  TMTpro_zero@k   295.189592          295.3773   \n",
-       "TMTpro_zero@t                  TMTpro_zero@t   295.189592          295.3773   \n",
-       "Andro-H2O@c                      Andro-H2O@c   332.198760          332.4339   \n",
-       "His+O(2)@h                        His+O(2)@h   169.048741          169.1381   \n",
-       "GlyGly@k                            GlyGly@k   114.042927          114.1026   \n",
-       "\n",
-       "                              composition  unimod_modloss modloss_composition  \\\n",
-       "mod_name                                                                        \n",
-       "Acetyl@T                     H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@Protein_N-term        H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@S                     H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@C                     H(2)C(2)O(1)             0.0                       \n",
-       "Acetyl@Any_N-term            H(2)C(2)O(1)             0.0                       \n",
-       "...                                   ...             ...                 ...   \n",
-       "TMTpro_zero@k          H(25)C(15)N(3)O(3)             0.0                       \n",
-       "TMTpro_zero@t          H(25)C(15)N(3)O(3)             0.0                       \n",
-       "Andro-H2O@c                H(28)C(20)O(4)             0.0                       \n",
-       "His+O(2)@h               H(7)C(6)N(3)O(3)             0.0                       \n",
-       "GlyGly@k                 H(6)C(4)N(2)O(2)             0.0                       \n",
-       "\n",
-       "                            classification  unimod_id  modloss_importance  \\\n",
-       "mod_name                                                                    \n",
-       "Acetyl@T                Post-translational          1                 0.0   \n",
-       "Acetyl@Protein_N-term   Post-translational          1                 0.0   \n",
-       "Acetyl@S                Post-translational          1                 0.0   \n",
-       "Acetyl@C                Post-translational          1                 0.0   \n",
-       "Acetyl@Any_N-term                 Multiple          1                 0.0   \n",
-       "...                                    ...        ...                 ...   \n",
-       "TMTpro_zero@k          Chemical derivative       2017                 0.0   \n",
-       "TMTpro_zero@t          Chemical derivative       2017                 0.0   \n",
-       "Andro-H2O@c            Chemical derivative       2025                 0.0   \n",
-       "His+O(2)@h              Post-translational       2027                 0.0   \n",
-       "GlyGly@k                Post-translational        121           1000000.0   \n",
-       "\n",
-       "                             mass  modloss_original  modloss  lower_case_AA  \n",
-       "mod_name                                                                     \n",
-       "Acetyl@T                42.010565               0.0      0.0          False  \n",
-       "Acetyl@Protein_N-term   42.010565               0.0      0.0          False  \n",
-       "Acetyl@S                42.010565               0.0      0.0          False  \n",
-       "Acetyl@C                42.010565               0.0      0.0          False  \n",
-       "Acetyl@Any_N-term       42.010565               0.0      0.0          False  \n",
-       "...                           ...               ...      ...            ...  \n",
-       "TMTpro_zero@k          295.189592               0.0      0.0           True  \n",
-       "TMTpro_zero@t          295.189592               0.0      0.0           True  \n",
-       "Andro-H2O@c            332.198759               0.0      0.0           True  \n",
-       "His+O(2)@h             169.048741               0.0      0.0           True  \n",
-       "GlyGly@k               114.042927               0.0      0.0           True  \n",
-       "\n",
-       "[5103 rows x 13 columns]"
       ]
      },
-     "execution_count": null,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "add_modifications_for_lower_case_AA()\n",
-    "MOD_DF"
-   ]
+   "execution_count": 7
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:12:59.467507Z",
+     "start_time": "2024-11-15T12:12:59.458754Z"
+    }
+   },
+   "source": [
+    "\n",
+    "modification.MOD_DF = MOD_DF[\n",
+    "    (modification.MOD_DF['classification'].isin(['Post-translational','O-linked glycosylation','AA substitution','Multiple','Non-standard residue','Pre-translational']))\n",
+    "    & modification.MOD_DF['lower_case_AA']\n",
+    "] # we only need PTMs\n",
+    "update_all_by_MOD_DF()\n",
+    "# MOD_INFO_DICT is also updated\n",
+    "pd.DataFrame().from_dict(MOD_INFO_DICT, orient='index')"
+   ],
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/6r/8h59xkv90qs2dyy8mdn_ch840000gn/T/ipykernel_50785/1388563684.py:1: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
+      "  modification.MOD_DF = MOD_DF[\n"
+     ]
+    },
     {
      "data": {
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: []\n",
+       "Index: []"
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -1168,360 +1477,95 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>mod_name</th>\n",
-       "      <th>unimod_mass</th>\n",
-       "      <th>unimod_avge_mass</th>\n",
-       "      <th>composition</th>\n",
-       "      <th>unimod_modloss</th>\n",
-       "      <th>modloss_composition</th>\n",
-       "      <th>classification</th>\n",
-       "      <th>unimod_id</th>\n",
-       "      <th>modloss_importance</th>\n",
-       "      <th>mass</th>\n",
-       "      <th>modloss_original</th>\n",
-       "      <th>modloss</th>\n",
-       "      <th>lower_case_AA</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>Acetyl@t</th>\n",
-       "      <td>Acetyl@t</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>42.0367</td>\n",
-       "      <td>H(2)C(2)O(1)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Acetyl@s</th>\n",
-       "      <td>Acetyl@s</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>42.0367</td>\n",
-       "      <td>H(2)C(2)O(1)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Acetyl@c</th>\n",
-       "      <td>Acetyl@c</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>42.0367</td>\n",
-       "      <td>H(2)C(2)O(1)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Acetyl@k</th>\n",
-       "      <td>Acetyl@k</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>42.0367</td>\n",
-       "      <td>H(2)C(2)O(1)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Multiple</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>42.010565</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Biotin@k</th>\n",
-       "      <td>Biotin@k</td>\n",
-       "      <td>226.077598</td>\n",
-       "      <td>226.2954</td>\n",
-       "      <td>H(14)C(10)N(2)O(2)S(1)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>226.077599</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</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>Hex(3)HexNAc(3)NeuAc(3)@t</th>\n",
-       "      <td>Hex(3)HexNAc(3)NeuAc(3)@t</td>\n",
-       "      <td>1968.682838</td>\n",
-       "      <td>1969.7631</td>\n",
-       "      <td>H(120)C(75)N(6)O(54)</td>\n",
-       "      <td>1968.682838</td>\n",
-       "      <td>H(120)C(75)N(6)O(54)</td>\n",
-       "      <td>O-linked glycosylation</td>\n",
-       "      <td>1968</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1968.682837</td>\n",
-       "      <td>1968.682837</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>CIGG@k</th>\n",
-       "      <td>CIGG@k</td>\n",
-       "      <td>330.136176</td>\n",
-       "      <td>330.4032</td>\n",
-       "      <td>H(22)C(13)N(4)O(4)S(1)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>1990</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>330.136176</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>GNLLFLACYCIGG@k</th>\n",
-       "      <td>GNLLFLACYCIGG@k</td>\n",
-       "      <td>1324.630800</td>\n",
-       "      <td>1325.5980</td>\n",
-       "      <td>H(92)C(61)N(14)O(15)S(2)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>1991</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1324.630801</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>His+O(2)@h</th>\n",
-       "      <td>His+O(2)@h</td>\n",
-       "      <td>169.048741</td>\n",
-       "      <td>169.1381</td>\n",
-       "      <td>H(7)C(6)N(3)O(3)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>2027</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>169.048741</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>GlyGly@k</th>\n",
-       "      <td>GlyGly@k</td>\n",
-       "      <td>114.042927</td>\n",
-       "      <td>114.1026</td>\n",
-       "      <td>H(6)C(4)N(2)O(2)</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td></td>\n",
-       "      <td>Post-translational</td>\n",
-       "      <td>121</td>\n",
-       "      <td>1000000.0</td>\n",
-       "      <td>114.042927</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>1249 rows × 13 columns</p>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "                                            mod_name  unimod_mass  \\\n",
-       "Acetyl@t                                    Acetyl@t    42.010565   \n",
-       "Acetyl@s                                    Acetyl@s    42.010565   \n",
-       "Acetyl@c                                    Acetyl@c    42.010565   \n",
-       "Acetyl@k                                    Acetyl@k    42.010565   \n",
-       "Biotin@k                                    Biotin@k   226.077598   \n",
-       "...                                              ...          ...   \n",
-       "Hex(3)HexNAc(3)NeuAc(3)@t  Hex(3)HexNAc(3)NeuAc(3)@t  1968.682838   \n",
-       "CIGG@k                                        CIGG@k   330.136176   \n",
-       "GNLLFLACYCIGG@k                      GNLLFLACYCIGG@k  1324.630800   \n",
-       "His+O(2)@h                                His+O(2)@h   169.048741   \n",
-       "GlyGly@k                                    GlyGly@k   114.042927   \n",
-       "\n",
-       "                           unimod_avge_mass               composition  \\\n",
-       "Acetyl@t                            42.0367              H(2)C(2)O(1)   \n",
-       "Acetyl@s                            42.0367              H(2)C(2)O(1)   \n",
-       "Acetyl@c                            42.0367              H(2)C(2)O(1)   \n",
-       "Acetyl@k                            42.0367              H(2)C(2)O(1)   \n",
-       "Biotin@k                           226.2954    H(14)C(10)N(2)O(2)S(1)   \n",
-       "...                                     ...                       ...   \n",
-       "Hex(3)HexNAc(3)NeuAc(3)@t         1969.7631      H(120)C(75)N(6)O(54)   \n",
-       "CIGG@k                             330.4032    H(22)C(13)N(4)O(4)S(1)   \n",
-       "GNLLFLACYCIGG@k                   1325.5980  H(92)C(61)N(14)O(15)S(2)   \n",
-       "His+O(2)@h                         169.1381          H(7)C(6)N(3)O(3)   \n",
-       "GlyGly@k                           114.1026          H(6)C(4)N(2)O(2)   \n",
-       "\n",
-       "                           unimod_modloss   modloss_composition  \\\n",
-       "Acetyl@t                         0.000000                         \n",
-       "Acetyl@s                         0.000000                         \n",
-       "Acetyl@c                         0.000000                         \n",
-       "Acetyl@k                         0.000000                         \n",
-       "Biotin@k                         0.000000                         \n",
-       "...                                   ...                   ...   \n",
-       "Hex(3)HexNAc(3)NeuAc(3)@t     1968.682838  H(120)C(75)N(6)O(54)   \n",
-       "CIGG@k                           0.000000                         \n",
-       "GNLLFLACYCIGG@k                  0.000000                         \n",
-       "His+O(2)@h                       0.000000                         \n",
-       "GlyGly@k                         0.000000                         \n",
-       "\n",
-       "                                   classification  unimod_id  \\\n",
-       "Acetyl@t                       Post-translational          1   \n",
-       "Acetyl@s                       Post-translational          1   \n",
-       "Acetyl@c                       Post-translational          1   \n",
-       "Acetyl@k                                 Multiple          1   \n",
-       "Biotin@k                       Post-translational          3   \n",
-       "...                                           ...        ...   \n",
-       "Hex(3)HexNAc(3)NeuAc(3)@t  O-linked glycosylation       1968   \n",
-       "CIGG@k                         Post-translational       1990   \n",
-       "GNLLFLACYCIGG@k                Post-translational       1991   \n",
-       "His+O(2)@h                     Post-translational       2027   \n",
-       "GlyGly@k                       Post-translational        121   \n",
-       "\n",
-       "                           modloss_importance         mass  modloss_original  \\\n",
-       "Acetyl@t                                  0.0    42.010565          0.000000   \n",
-       "Acetyl@s                                  0.0    42.010565          0.000000   \n",
-       "Acetyl@c                                  0.0    42.010565          0.000000   \n",
-       "Acetyl@k                                  0.0    42.010565          0.000000   \n",
-       "Biotin@k                                  0.0   226.077599          0.000000   \n",
-       "...                                       ...          ...               ...   \n",
-       "Hex(3)HexNAc(3)NeuAc(3)@t                 0.0  1968.682837       1968.682837   \n",
-       "CIGG@k                                    0.0   330.136176          0.000000   \n",
-       "GNLLFLACYCIGG@k                           0.0  1324.630801          0.000000   \n",
-       "His+O(2)@h                                0.0   169.048741          0.000000   \n",
-       "GlyGly@k                            1000000.0   114.042927          0.000000   \n",
-       "\n",
-       "                           modloss  lower_case_AA  \n",
-       "Acetyl@t                       0.0           True  \n",
-       "Acetyl@s                       0.0           True  \n",
-       "Acetyl@c                       0.0           True  \n",
-       "Acetyl@k                       0.0           True  \n",
-       "Biotin@k                       0.0           True  \n",
-       "...                            ...            ...  \n",
-       "Hex(3)HexNAc(3)NeuAc(3)@t      0.0           True  \n",
-       "CIGG@k                         0.0           True  \n",
-       "GNLLFLACYCIGG@k                0.0           True  \n",
-       "His+O(2)@h                     0.0           True  \n",
-       "GlyGly@k                       0.0           True  \n",
-       "\n",
-       "[1249 rows x 13 columns]"
       ]
      },
-     "execution_count": null,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "\n",
-    "MOD_DF = MOD_DF[\n",
-    "    (MOD_DF['classification'].isin(['Post-translational','O-linked glycosylation','AA substitution','Multiple','Non-standard residue','Pre-translational']))\n",
-    "    & MOD_DF['lower_case_AA']\n",
-    "] # we only need PTMs\n",
-    "update_all_by_MOD_DF()\n",
-    "# MOD_INFO_DICT is also updated\n",
-    "pd.DataFrame().from_dict(MOD_INFO_DICT, orient='index')"
-   ]
+   "execution_count": 8
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:14:31.271720Z",
+     "start_time": "2024-11-15T12:14:31.204426Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "load_mod_df()\n",
     "add_modifications_for_lower_case_AA()\n",
-    "MOD_DF = MOD_DF\n",
+    "MOD_DF = modification.MOD_DF\n",
     "MOD_DF = MOD_DF[\n",
     "    MOD_DF['lower_case_AA']\n",
     "] # we only need PTMs\n",
     "assert MOD_DF['mod_name'].apply(lambda x: x[x.find('@')+1].islower()).all()"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 12
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:14:31.790943Z",
+     "start_time": "2024-11-15T12:14:31.761574Z"
+    }
+   },
    "source": [
     "#| hide\n",
-    "prev_value = (MOD_DF.classification=='User-added').sum()\n",
+    "prev_value = (modification.MOD_DF.classification=='User-added').sum()\n",
     "add_new_modifications([\n",
     "    (\"Hello@S\",\"H(2)\"),\n",
     "    (\"World@S\",\"O(10)\",\"O(3)\")\n",
     "])\n",
-    "assert (MOD_DF.classification=='User-added').sum() - prev_value == 2\n",
-    "assert 'Hello@S' in MOD_DF.mod_name\n",
-    "assert 'World@S' in MOD_DF.mod_name\n",
-    "assert MOD_DF.loc['World@S','modloss'] > 0\n",
-    "assert MOD_DF.loc['World@S','modloss_importance'] > 0\n",
+    "assert (modification.MOD_DF.classification=='User-added').sum() - prev_value == 2\n",
+    "assert 'Hello@S' in modification.MOD_DF.mod_name\n",
+    "assert 'World@S' in modification.MOD_DF.mod_name\n",
+    "assert modification.MOD_DF.loc['World@S','modloss'] > 0\n",
+    "assert modification.MOD_DF.loc['World@S','modloss_importance'] > 0\n",
     "assert 'Hello@S' in MOD_Composition\n",
     "assert 'World@S' in MOD_MASS"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 13
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:14:56.060580Z",
+     "start_time": "2024-11-15T12:14:56.033300Z"
+    }
+   },
    "source": [
     "add_new_modifications({\n",
     "    \"Hi@S\":{'composition':\"H(2)\"},\n",
     "    \"AlphaX@S\":{'composition':\"O(10)\",'modloss_composition':\"O(3)\"}\n",
     "})\n",
-    "assert (MOD_DF.classification=='User-added').sum() - prev_value == 4\n",
-    "assert 'Hi@S' in MOD_DF.mod_name\n",
-    "assert 'Hi@S' in MOD_DF.index\n",
-    "assert 'AlphaX@S' in MOD_DF.mod_name\n",
-    "assert 'AlphaX@S' in MOD_DF.index\n",
-    "assert MOD_DF.loc['AlphaX@S','modloss'] > 0\n",
-    "assert MOD_DF.loc['AlphaX@S','modloss_importance'] > 0\n",
+    "assert (modification.MOD_DF.classification=='User-added').sum() - prev_value == 4\n",
+    "assert 'Hi@S' in modification.MOD_DF.mod_name\n",
+    "assert 'Hi@S' in modification.MOD_DF.index\n",
+    "assert 'AlphaX@S' in modification.MOD_DF.mod_name\n",
+    "assert 'AlphaX@S' in modification.MOD_DF.index\n",
+    "assert modification.MOD_DF.loc['AlphaX@S','modloss'] > 0\n",
+    "assert modification.MOD_DF.loc['AlphaX@S','modloss_importance'] > 0\n",
     "assert 'Hi@S' in MOD_Composition\n",
     "assert 'AlphaX@S' in MOD_MASS\n",
     "assert 'AlphaX@S' in MOD_LOSS_IMPORTANCE\n",
-    "assert MOD_DF.loc['AlphaX@S','unimod_mass'] == 0"
-   ]
+    "assert modification.MOD_DF.loc['AlphaX@S','unimod_mass'] == 0"
+   ],
+   "outputs": [],
+   "execution_count": 15
   },
   {
    "cell_type": "code",
diff --git a/nbs_tests/protein/fasta.ipynb b/nbs_tests/protein/fasta.ipynb
index fada88ff..637451c6 100644
--- a/nbs_tests/protein/fasta.ipynb
+++ b/nbs_tests/protein/fasta.ipynb
@@ -2,12 +2,17 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:05:45.448370Z",
+     "start_time": "2024-11-15T12:05:45.446169Z"
+    }
+   },
    "source": [
     "#---#| default_exp protein.fasta"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 1
   },
   {
    "cell_type": "markdown",
@@ -18,49 +23,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "OMP: Info #276: omp_set_nested routine deprecated, please use omp_set_max_active_levels instead.\n"
-     ]
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:27.063870Z",
+     "start_time": "2024-11-15T12:07:27.058114Z"
     }
-   ],
+   },
    "source": [
     "import numpy as np\n",
     "import pandas as pd\n",
     "\n",
+    "import alphabase.protein.fasta as fasta\n",
     "from alphabase.protein.fasta import get_uniprot_gene_name, protease_dict, Digest, get_fix_mods, get_candidate_sites, \\\n",
     "    get_var_mod_sites, get_var_mods_per_sites_multi_mods_on_aa, get_var_mods, get_var_mods_per_sites_single_mod_on_aa, \\\n",
     "    parse_term_mod, parse_labels, add_single_peptide_labeling, create_labeling_peptide_df, protein_idxes_to_names, \\\n",
     "    append_special_modifications, SpecLibFasta"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 10
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:27.583357Z",
+     "start_time": "2024-11-15T12:07:27.580516Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "assert get_uniprot_gene_name('sp|Q9H9K5|MER34_HUMAN Endogenous retroviral envelope protein HEMO OS=Homo sapiens OX=9606 GN=ERVMER34-1 PE=1 SV=1') == 'ERVMER34-1'"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 11
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:27.997771Z",
+     "start_time": "2024-11-15T12:07:27.995569Z"
+    }
+   },
+   "source": "assert 'trypsin_not_p' in protease_dict, 'trypsin_not_p not in protease_dict, why?'",
    "outputs": [],
-   "source": "assert 'trypsin_not_p' in protease_dict, 'trypsin_not_p not in protease_dict, why?'"
+   "execution_count": 12
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:28.286014Z",
+     "start_time": "2024-11-15T12:07:28.281793Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "digest = Digest(protease=\"trypsin_not_p\")\n",
@@ -69,12 +85,31 @@
     "seq = 'ABDNGKENGLANGIXHGRKTNGLANGKVHNAKHNARKANGKPFAAT'\n",
     "cut_pos = digest.get_cut_positions(seq)\n",
     "assert np.all(cut_pos==np.array([0, 6, 18, 19, 27, 32, 36, 37, len(seq)]))"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 13
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:28.580740Z",
+     "start_time": "2024-11-15T12:07:28.576209Z"
+    }
+   },
+   "source": [
+    "#| hide\n",
+    "seq = 'MABCDEKHIJKLNOPQRST'\n",
+    "digest = Digest()\n",
+    "seq_list, miss_list, nterm_list, cterm_list = digest.cleave_sequence(seq)\n",
+    "assert len(seq_list) == len(miss_list) == len(nterm_list) == len(cterm_list)\n",
+    "M_start_seqs = [seq for seq in seq_list if seq.startswith('M')]\n",
+    "assert len(M_start_seqs)*2 == len([_ for _ in nterm_list if _])\n",
+    "assert np.all(nterm_list[-len(M_start_seqs):])\n",
+    "T_end_seqs = [seq for seq in seq_list if seq.endswith('T')]\n",
+    "assert len(T_end_seqs) == len([_ for _ in cterm_list if _])\n",
+    "seq_list"
+   ],
    "outputs": [
     {
      "data": {
@@ -91,29 +126,30 @@
        " 'ABCDEKHIJKLNOPQR']"
       ]
      },
-     "execution_count": null,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "#| hide\n",
-    "seq = 'MABCDEKHIJKLNOPQRST'\n",
-    "digest = Digest()\n",
-    "seq_list, miss_list, nterm_list, cterm_list = digest.cleave_sequence(seq)\n",
-    "assert len(seq_list) == len(miss_list) == len(nterm_list) == len(cterm_list)\n",
-    "M_start_seqs = [seq for seq in seq_list if seq.startswith('M')]\n",
-    "assert len(M_start_seqs)*2 == len([_ for _ in nterm_list if _])\n",
-    "assert np.all(nterm_list[-len(M_start_seqs):])\n",
-    "T_end_seqs = [seq for seq in seq_list if seq.endswith('T')]\n",
-    "assert len(T_end_seqs) == len([_ for _ in cterm_list if _])\n",
-    "seq_list"
-   ]
+   "execution_count": 14
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:29.081366Z",
+     "start_time": "2024-11-15T12:07:29.078808Z"
+    }
+   },
+   "source": [
+    "seq = 'ACBCDCK'\n",
+    "_fix_mod_dict = {}\n",
+    "_fix_mod_dict['C'] = 'mod@C'\n",
+    "mods, mod_sites = get_fix_mods(seq, 'C', _fix_mod_dict)\n",
+    "assert mods==';'.join(['mod@C']*3)\n",
+    "assert mod_sites=='2;4;6'\n",
+    "get_fix_mods(seq, 'C', _fix_mod_dict)"
+   ],
    "outputs": [
     {
      "data": {
@@ -121,26 +157,21 @@
        "('mod@C;mod@C;mod@C', '2;4;6')"
       ]
      },
-     "execution_count": null,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "seq = 'ACBCDCK'\n",
-    "_fix_mod_dict = {}\n",
-    "_fix_mod_dict['C'] = 'mod@C'\n",
-    "mods, mod_sites = get_fix_mods(seq, 'C', _fix_mod_dict)\n",
-    "assert mods==';'.join(['mod@C']*3)\n",
-    "assert mod_sites=='2;4;6'\n",
-    "get_fix_mods(seq, 'C', _fix_mod_dict)"
-   ]
+   "execution_count": 15
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:29.412607Z",
+     "start_time": "2024-11-15T12:07:29.409340Z"
+    }
+   },
    "source": [
     "seq = 'AMCMSTYK'\n",
     "candidate_sites = get_candidate_sites(seq, 'MSTY')\n",
@@ -171,12 +202,40 @@
     "\n",
     "for s in ground_truth:\n",
     "    assert s in sites"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 16
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:29.834135Z",
+     "start_time": "2024-11-15T12:07:29.830419Z"
+    }
+   },
+   "source": [
+    "#| hide\n",
+    "fasta.get_var_mods_per_sites = get_var_mods_per_sites_multi_mods_on_aa # note: fasta module is patched here!\n",
+    "seq = 'AMCMSTYK'\n",
+    "candidate_sites = get_candidate_sites(seq, 'MSTY')\n",
+    "mod_sites_list = get_var_mod_sites(seq, 'MSTY', 0, 3, 20)\n",
+    "_mod_dict = {\n",
+    "    'M':['mod@M'],\n",
+    "    'S':['mod@S','modX@S'],\n",
+    "    'T':['mod@T'],\n",
+    "    'Y':['mod@Y'],\n",
+    "}\n",
+    "_mods, _sites = get_var_mods(seq, 'MSTY', _mod_dict, 0, 3, 16)\n",
+    "\n",
+    "assert 'mod@M;mod@M;mod@S' in _mods\n",
+    "assert _sites[_mods.index('mod@M;mod@M;mod@S')] == '2;4;5'\n",
+    "assert 'mod@M;mod@M;modX@S' in _mods\n",
+    "assert _sites[_mods.index('mod@M;mod@M;modX@S')] == '2;4;5'\n",
+    "assert 'mod@M;mod@S' in _mods\n",
+    "assert 'mod@M;modX@S' in _mods\n",
+    "get_var_mods(seq, 'MSTY', _mod_dict, 0, 3, 16)"
+   ],
    "outputs": [
     {
      "data": {
@@ -229,38 +288,38 @@
        "  ''])"
       ]
      },
-     "execution_count": null,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
+   "execution_count": 17
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:30.635628Z",
+     "start_time": "2024-11-15T12:07:30.631237Z"
+    }
+   },
    "source": [
     "#| hide\n",
-    "get_var_mods_per_sites = get_var_mods_per_sites_multi_mods_on_aa\n",
+    "fasta.get_var_mods_per_sites = get_var_mods_per_sites_single_mod_on_aa # note: fasta module is patched here!\n",
     "seq = 'AMCMSTYK'\n",
     "candidate_sites = get_candidate_sites(seq, 'MSTY')\n",
-    "mod_sites_list = get_var_mod_sites(seq, 'MSTY', 0, 3, 20)\n",
+    "mod_sites_list = get_var_mod_sites(seq, 'MSTY', 1, 3, 20)\n",
     "_mod_dict = {\n",
-    "    'M':['mod@M'],\n",
-    "    'S':['mod@S','modX@S'],\n",
-    "    'T':['mod@T'],\n",
-    "    'Y':['mod@Y'],\n",
+    "    'M':'mod@M',\n",
+    "    'S':'mod@S',\n",
+    "    'T':'mod@T',\n",
+    "    'Y':'mod@Y',\n",
     "}\n",
-    "_mods, _sites = get_var_mods(seq, 'MSTY', _mod_dict, 0, 3, 16)\n",
-    "\n",
-    "assert 'mod@M;mod@M;mod@S' in _mods\n",
+    "_mods, _sites = get_var_mods(seq, 'MSTY', _mod_dict, 1, 3, 16)\n",
+    "assert len(_mods) == len(_sites) == 16\n",
     "assert _sites[_mods.index('mod@M;mod@M;mod@S')] == '2;4;5'\n",
-    "assert 'mod@M;mod@M;modX@S' in _mods\n",
-    "assert _sites[_mods.index('mod@M;mod@M;modX@S')] == '2;4;5'\n",
-    "assert 'mod@M;mod@S' in _mods\n",
-    "assert 'mod@M;modX@S' in _mods\n",
     "get_var_mods(seq, 'MSTY', _mod_dict, 0, 3, 16)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   ],
    "outputs": [
     {
      "data": {
@@ -301,45 +360,37 @@
        "  ''])"
       ]
      },
-     "execution_count": null,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "#| hide\n",
-    "get_var_mods_per_sites = get_var_mods_per_sites_single_mod_on_aa\n",
-    "seq = 'AMCMSTYK'\n",
-    "candidate_sites = get_candidate_sites(seq, 'MSTY')\n",
-    "mod_sites_list = get_var_mod_sites(seq, 'MSTY', 1, 3, 20)\n",
-    "_mod_dict = {\n",
-    "    'M':'mod@M',\n",
-    "    'S':'mod@S',\n",
-    "    'T':'mod@T',\n",
-    "    'Y':'mod@Y',\n",
-    "}\n",
-    "_mods, _sites = get_var_mods(seq, 'MSTY', _mod_dict, 1, 3, 16)\n",
-    "assert len(_mods) == len(_sites) == 16\n",
-    "assert _sites[_mods.index('mod@M;mod@M;mod@S')] == '2;4;5'\n",
-    "get_var_mods(seq, 'MSTY', _mod_dict, 0, 3, 16)"
-   ]
+   "execution_count": 18
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:31.205274Z",
+     "start_time": "2024-11-15T12:07:31.203564Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "assert parse_term_mod('Acetyl@Protein_N-term') == ('', 'Protein_N-term')\n",
     "assert parse_term_mod('Gln->pyro-Glu@Q^Any_N-term') == ('Q', 'Any_N-term')"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 19
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:31.670694Z",
+     "start_time": "2024-11-15T12:07:31.662099Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "labels = ['label@Any_N-term','label@K']\n",
@@ -380,18 +431,25 @@
     "assert df[df.sequence=='EFGK'].mod_sites.values[0] == '0;4'\n",
     "df = create_labeling_peptide_df(pep_df, [])\n",
     "assert np.all(df.mods.values==pep_df.mods.values)"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 20
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:32.151431Z",
+     "start_time": "2024-11-15T12:07:32.149345Z"
+    }
+   },
    "source": [
     "#| hide\n",
     "assert protein_idxes_to_names('0;1', ['A','','B'])=='A'\n",
     "assert protein_idxes_to_names('0;1', ['A','C','B'])=='A;C'"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 21
   },
   {
    "cell_type": "markdown",
@@ -402,11 +460,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:32.872124Z",
+     "start_time": "2024-11-15T12:07:32.861593Z"
+    }
+   },
+   "source": [
+    "df = pd.DataFrame(\n",
+    "    {\n",
+    "        'sequence': ['ABSTY','ACXSX','ACDEFG'],\n",
+    "        'mods': ['', 'Acetyl@Protein_N-term', ''],\n",
+    "        'mod_sites': ['', '0', '']\n",
+    "    }\n",
+    ")\n",
+    "df = append_special_modifications(df, min_mod_num=0)\n",
+    "assert np.sum(df.sequence=='ABSTY')==4\n",
+    "assert np.sum(df.sequence=='ACXSX')==2\n",
+    "assert np.sum(df.sequence=='ACDEFG')==1\n",
+    "assert all(df[df.sequence=='ABSTY'].mods.values == np.array(['Phospho@S','Phospho@T','Phospho@Y','']))\n",
+    "assert all(df[df.sequence=='ABSTY'].mod_sites.values == np.array(['3','4','5','']))\n",
+    "assert all(df[df.sequence=='ACXSX'].mods.values == np.array(['Acetyl@Protein_N-term;Phospho@S','Acetyl@Protein_N-term']))\n",
+    "assert all(df[df.sequence=='ACXSX'].mod_sites.values == np.array(['0;4','0']))\n",
+    "df"
+   ],
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "  sequence                             mods mod_sites\n",
+       "0    ABSTY                        Phospho@S         3\n",
+       "1    ABSTY                        Phospho@T         4\n",
+       "2    ABSTY                        Phospho@Y         5\n",
+       "3    ABSTY                                           \n",
+       "4    ACXSX  Acetyl@Protein_N-term;Phospho@S       0;4\n",
+       "5    ACXSX            Acetyl@Protein_N-term         0\n",
+       "6   ACDEFG                                           "
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -477,23 +567,23 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "  sequence                             mods mod_sites\n",
-       "0    ABSTY                        Phospho@S         3\n",
-       "1    ABSTY                        Phospho@T         4\n",
-       "2    ABSTY                        Phospho@Y         5\n",
-       "3    ABSTY                                           \n",
-       "4    ACXSX  Acetyl@Protein_N-term;Phospho@S       0;4\n",
-       "5    ACXSX            Acetyl@Protein_N-term         0\n",
-       "6   ACDEFG                                           "
       ]
      },
-     "execution_count": null,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
+   "execution_count": 22
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:33.439323Z",
+     "start_time": "2024-11-15T12:07:33.432633Z"
+    }
+   },
    "source": [
     "df = pd.DataFrame(\n",
     "    {\n",
@@ -502,24 +592,22 @@
     "        'mod_sites': ['', '0', '']\n",
     "    }\n",
     ")\n",
-    "df = append_special_modifications(df, min_mod_num=0)\n",
-    "assert np.sum(df.sequence=='ABSTY')==4\n",
-    "assert np.sum(df.sequence=='ACXSX')==2\n",
-    "assert np.sum(df.sequence=='ACDEFG')==1\n",
-    "assert all(df[df.sequence=='ABSTY'].mods.values == np.array(['Phospho@S','Phospho@T','Phospho@Y','']))\n",
-    "assert all(df[df.sequence=='ABSTY'].mod_sites.values == np.array(['3','4','5','']))\n",
-    "assert all(df[df.sequence=='ACXSX'].mods.values == np.array(['Acetyl@Protein_N-term;Phospho@S','Acetyl@Protein_N-term']))\n",
-    "assert all(df[df.sequence=='ACXSX'].mod_sites.values == np.array(['0;4','0']))\n",
+    "df = append_special_modifications(df, min_mod_num=1)\n",
+    "assert np.sum(df.sequence=='ABSTY')==3\n",
+    "assert np.sum(df.sequence=='ACXSX')==1\n",
+    "assert np.sum(df.sequence=='ACDEFG')==0\n",
     "df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   ],
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "  sequence                             mods mod_sites\n",
+       "0    ABSTY                        Phospho@S         3\n",
+       "1    ABSTY                        Phospho@T         4\n",
+       "2    ABSTY                        Phospho@Y         5\n",
+       "3    ACXSX  Acetyl@Protein_N-term;Phospho@S       0;4"
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -572,20 +660,23 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "  sequence                             mods mod_sites\n",
-       "0    ABSTY                        Phospho@S         3\n",
-       "1    ABSTY                        Phospho@T         4\n",
-       "2    ABSTY                        Phospho@Y         5\n",
-       "3    ACXSX  Acetyl@Protein_N-term;Phospho@S       0;4"
       ]
      },
-     "execution_count": null,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
+   "execution_count": 23
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:33.915057Z",
+     "start_time": "2024-11-15T12:07:33.908861Z"
+    }
+   },
    "source": [
     "df = pd.DataFrame(\n",
     "    {\n",
@@ -594,20 +685,21 @@
     "        'mod_sites': ['', '0', '']\n",
     "    }\n",
     ")\n",
-    "df = append_special_modifications(df, min_mod_num=1)\n",
+    "df = append_special_modifications(df, min_mod_num=2, max_mod_num=2)\n",
     "assert np.sum(df.sequence=='ABSTY')==3\n",
-    "assert np.sum(df.sequence=='ACXSX')==1\n",
+    "assert np.sum(df.sequence=='ACXSX')==0\n",
     "assert np.sum(df.sequence=='ACDEFG')==0\n",
     "df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   ],
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "  sequence                 mods mod_sites\n",
+       "0    ABSTY  Phospho@S;Phospho@T       3;4\n",
+       "1    ABSTY  Phospho@S;Phospho@Y       3;5\n",
+       "2    ABSTY  Phospho@T;Phospho@Y       4;5"
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -654,39 +746,23 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "  sequence                 mods mod_sites\n",
-       "0    ABSTY  Phospho@S;Phospho@T       3;4\n",
-       "1    ABSTY  Phospho@S;Phospho@Y       3;5\n",
-       "2    ABSTY  Phospho@T;Phospho@Y       4;5"
       ]
      },
-     "execution_count": null,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "df = pd.DataFrame(\n",
-    "    {\n",
-    "        'sequence': ['ABSTY','ACXSX','ACDEFG'],\n",
-    "        'mods': ['', 'Acetyl@Protein_N-term', ''],\n",
-    "        'mod_sites': ['', '0', '']\n",
-    "    }\n",
-    ")\n",
-    "df = append_special_modifications(df, min_mod_num=2, max_mod_num=2)\n",
-    "assert np.sum(df.sequence=='ABSTY')==3\n",
-    "assert np.sum(df.sequence=='ACXSX')==0\n",
-    "assert np.sum(df.sequence=='ACDEFG')==0\n",
-    "df"
-   ]
+   "execution_count": 24
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:34.980393Z",
+     "start_time": "2024-11-15T12:07:34.977299Z"
+    }
+   },
    "source": [
     "def get_protein_dict():\n",
     "    prot1 = 'MABCDESTKAFGHIJKLMNOPQRAFGHIJK'\n",
@@ -704,15 +780,54 @@
     "        }\n",
     "    }\n",
     "    return protein_dict"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": 25
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:35.345803Z",
+     "start_time": "2024-11-15T12:07:35.335738Z"
+    }
+   },
+   "source": [
+    "_lib = SpecLibFasta(None, I_to_L=False, decoy='pseudo_reverse')\n",
+    "protein_dict = get_protein_dict()\n",
+    "_lib.get_peptides_from_protein_dict(protein_dict)\n",
+    "_lib.precursor_df"
+   ],
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "                   sequence protein_idxes  miss_cleavage  is_prot_nterm  \\\n",
+       "0                   AFGHIJK           0;1              0           True   \n",
+       "1                   LMNOPQR           0;1              0          False   \n",
+       "2                  ABCDESTK             0              0           True   \n",
+       "3                 MABCDESTK             0              0           True   \n",
+       "4            AFGHIJKLMNOPQR           0;1              1           True   \n",
+       "5            LMNOPQRAFGHIJK             0              1          False   \n",
+       "6           ABCDESTKAFGHIJK             0              1           True   \n",
+       "7          MABCDESTKAFGHIJK             0              1           True   \n",
+       "8     AFGHIJKLMNOPQRAFGHIJK             0              2          False   \n",
+       "9    ABCDESTKAFGHIJKLMNOPQR             0              2           True   \n",
+       "10  MABCDESTKAFGHIJKLMNOPQR             0              2           True   \n",
+       "\n",
+       "    is_prot_cterm mods mod_sites  nAA  \n",
+       "0            True                   7  \n",
+       "1            True                   7  \n",
+       "2           False                   8  \n",
+       "3           False                   9  \n",
+       "4            True                  14  \n",
+       "5            True                  14  \n",
+       "6           False                  15  \n",
+       "7           False                  16  \n",
+       "8            True                  21  \n",
+       "9           False                  22  \n",
+       "10          False                  23  "
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -867,54 +982,34 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "                   sequence protein_idxes  miss_cleavage  is_prot_nterm  \\\n",
-       "0                   AFGHIJK           0;1              0           True   \n",
-       "1                   LMNOPQR           0;1              0          False   \n",
-       "2                  ABCDESTK             0              0           True   \n",
-       "3                 MABCDESTK             0              0           True   \n",
-       "4            AFGHIJKLMNOPQR           0;1              1           True   \n",
-       "5            LMNOPQRAFGHIJK             0              1          False   \n",
-       "6           ABCDESTKAFGHIJK             0              1           True   \n",
-       "7          MABCDESTKAFGHIJK             0              1           True   \n",
-       "8     AFGHIJKLMNOPQRAFGHIJK             0              2          False   \n",
-       "9    ABCDESTKAFGHIJKLMNOPQR             0              2           True   \n",
-       "10  MABCDESTKAFGHIJKLMNOPQR             0              2           True   \n",
-       "\n",
-       "    is_prot_cterm mods mod_sites  nAA  \n",
-       "0            True                   7  \n",
-       "1            True                   7  \n",
-       "2           False                   8  \n",
-       "3           False                   9  \n",
-       "4            True                  14  \n",
-       "5            True                  14  \n",
-       "6           False                  15  \n",
-       "7           False                  16  \n",
-       "8            True                  21  \n",
-       "9           False                  22  \n",
-       "10          False                  23  "
       ]
      },
-     "execution_count": null,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "_lib = SpecLibFasta(None, I_to_L=False, decoy='pseudo_reverse')\n",
-    "protein_dict = get_protein_dict()\n",
-    "_lib.get_peptides_from_protein_dict(protein_dict)\n",
-    "_lib.precursor_df"
-   ]
+   "execution_count": 26
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-15T12:07:35.844950Z",
+     "start_time": "2024-11-15T12:07:35.840808Z"
+    }
+   },
+   "source": [
+    "_lib.protein_df"
+   ],
    "outputs": [
     {
      "data": {
+      "text/plain": [
+       "  protein_id gene_name                        sequence\n",
+       "0         xx            MABCDESTKAFGHIJKLMNOPQRAFGHIJK\n",
+       "1         yy      gene                  AFGHIJKLMNOPQR"
+      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -955,21 +1050,14 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
-      ],
-      "text/plain": [
-       "  protein_id gene_name                        sequence\n",
-       "0         xx            MABCDESTKAFGHIJKLMNOPQRAFGHIJK\n",
-       "1         yy      gene                  AFGHIJKLMNOPQR"
       ]
      },
-     "execution_count": null,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "_lib.protein_df"
-   ]
+   "execution_count": 27
   },
   {
    "cell_type": "code",