Merge pull request #223 from MannLabs/smiles

ENH: hydroxyisobutyryl@K smiles
MannLabs · Sep 30, 2024 · 379e857 · 379e857
2 parents 1b7d2de + 24932ad
commit 379e857
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 57 deletions.
diff --git a/alphabase/constants/const_files/modification.tsv b/alphabase/constants/const_files/modification.tsv
@@ -2440,7 +2440,7 @@ PhosphoCytidine@S	305.041287	305.1812	H(12)C(9)N(3)O(7)P(1)	0.0		Post-translatio
 AzidoF@F	41.001397	41.0122	H(-1)N(3)	0.0		Chemical derivative	1845		0.0
 Dimethylaminoethyl@C	71.073499	71.121	H(9)C(4)N(1)	0.0		Chemical derivative	1846		0.0
 Gluratylation@K	114.031694	114.0993	H(6)C(5)O(3)	0.0		Post-translational	1848		0.0
-hydroxyisobutyryl@K	86.036779	86.0892	H(6)C(4)O(2)	0.0		Post-translational	1849		0.0
+hydroxyisobutyryl@K	86.036779	86.0892	H(6)C(4)O(2)	0.0		Post-translational	1849	CC(C)(O)C(=O)NCCCCC(N([Xe])[Xe])C([Rn])=O	0.0
 MeMePhosphorothioate@S	107.979873	108.0993	H(5)C(2)O(1)P(1)S(1)	0.0		Chemical derivative	1868		0.0
 Cation:Fe[III]@D	52.911464	52.8212	H(-3)Fe(1)	0.0		Artefact	1870		0.0
 Cation:Fe[III]@E	52.911464	52.8212	H(-3)Fe(1)	0.0		Artefact	1870		0.0

diff --git a/docs/nbs/adding_smiles.ipynb b/docs/nbs/adding_smiles.ipynb
@@ -49,46 +49,6 @@
    "cell_type": "code",
    "execution_count": 2,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "defaultdict(int, {'O': -1, 'H': 2, 'C': 1})"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "(ChemicalCompositonFormula(\"C(1)H(4)\") - ChemicalCompositonFormula(\"H(2)O(1)\")).elements"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ChemicalCompositonFormula('C(1)H(2)O(-1)')"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "ChemicalCompositonFormula(\"C(1)H(2)O(-1)\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
    "outputs": [],
    "source": [
     "n_term_modifications = {'mTRAQ@Any_N-term': 'C(=O)CN1CCN(CC1)C',\n",
@@ -153,7 +113,8 @@
     " 'Pro->(1S,3S,5S)-2-Azabicyclo[3.1.0]hexane-3-carboxylic_acid@P': '[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-carboxylic_acid@P': '[C@@H]12N([Xe])[C@@H](C[C@H]2C1)C(=O)[Rn]',\n",
     " 'Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxylic_acid@P': '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'}"
+    " 'Pro->(DL)-5-trifluoromethylproline@P': 'FC(C1CCC(N1([Xe]))C(=O)[Rn])(F)F',\n",
+    " 'hydroxyisobutyryl@K': 'CC(C)(O)C(=O)NCCCCC(N([Xe])[Xe])C([Rn])=O',}\n"
    ]
   },
   {
@@ -170,7 +131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -195,7 +156,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -222,7 +183,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -299,10 +260,12 @@
        " 'Pro->(2S,3aS,7aS)-Octahydro-1H-indole-2-carboxylic_acid@P': {'composition': 'C(4)H(6)',\n",
        "  'smiles': 'N1([Xe])[C@@H](C[C@@H]2CCCC[C@H]12)C(=O)[Rn]'},\n",
        " 'Pro->(DL)-5-trifluoromethylproline@P': {'composition': 'C(1)F(3)H(-1)',\n",
-       "  'smiles': 'FC(C1CCC(N1([Xe]))C(=O)[Rn])(F)F'}}"
+       "  'smiles': 'FC(C1CCC(N1([Xe]))C(=O)[Rn])(F)F'},\n",
+       " 'hydroxyisobutyryl@K': {'composition': 'C(4)H(6)O(2)',\n",
+       "  'smiles': 'CC(C)(O)C(=O)NCCCCC(N([Xe])[Xe])C([Rn])=O'}}"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -331,7 +294,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -350,7 +313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -411,7 +374,7 @@
        "  'smiles': '[13C]([2H])([2H])([1H])'}}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -434,7 +397,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -453,7 +416,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -478,7 +441,7 @@
        " 'Cation:Li@Protein_C-term': {'composition': 'H(-1)Li(1)', 'smiles': 'O[Li]'}}"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -502,7 +465,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -521,7 +484,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -832,7 +795,7 @@
        "[2796 rows x 13 columns]"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -852,7 +815,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [