{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "This example shows how RGroupDecomposition works with stereochemistry matching.\n", "If stereochemistry is specified in the core, the RGroup decomposition correctly assigns R1 and R2." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from rdkit import Chem\n", "from rdkit.Chem.Draw import IPythonConsole\n", "IPythonConsole.ipython_useSVG=True\n", "from rdkit.Chem import rdRGroupDecomposition\n", "from IPython.display import HTML\n", "from rdkit import rdBase\n", "rdBase.DisableLog(\"rdApp.debug\")" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from rdkit.Chem import PandasTools" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "m = Chem.MolFromSmarts(\"C1CCO[C@@](*)(*)1\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Perhaps we should file a bug that smarts doesn't show stereochem here." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "image/svg+xml": [ "\n", "\n", "\n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n" ], "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "m" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Make some example stereochemistries" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "C1CCO[C@@H](N)1\n", "C1CCO[C@H](N)1\n", "C1CCO[C@@](N)(O)1\n", "C1CCO[C@@](N)(P)1\n", "C1CCO[C@@](N)(S)1\n", "C1CCO[C@@H](O)1\n", "C1CCO[C@H](O)1\n", "C1CCO[C@@](O)(N)1\n", "C1CCO[C@@](O)(P)1\n", "C1CCO[C@@](O)(S)1\n", "C1CCO[C@@H](P)1\n", "C1CCO[C@H](P)1\n", "C1CCO[C@@](P)(N)1\n", "C1CCO[C@@](P)(O)1\n", "C1CCO[C@@](P)(S)1\n", "C1CCO[C@@H](S)1\n", "C1CCO[C@H](S)1\n", "C1CCO[C@@](S)(N)1\n", "C1CCO[C@@](S)(O)1\n", "C1CCO[C@@](S)(P)1\n" ] } ], "source": [ "el = \"NOPS\"\n", "mols = []\n", "for e in el:\n", " smi = \"C1CCO[C@@H](%s)1\"%e\n", " print(smi)\n", " m = Chem.MolFromSmiles(smi)\n", " mols.append(m)\n", " smi = \"C1CCO[C@H](%s)1\"%e\n", " print(smi)\n", " m = Chem.MolFromSmiles(smi)\n", " mols.append(m)\n", " for e2 in el:\n", " if e != e2:\n", " smi = \"C1CCO[C@@](%s)(%s)1\"%(e,e2)\n", " m = Chem.MolFromSmiles(smi)\n", " if m:\n", " print(smi)\n", " mols.append(m)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "" ], "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from rdkit.Chem import Draw\n", "Draw.MolsToGridImage(mols)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "" ], "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "hmols = [Chem.AddHs(m) for m in mols]\n", "Draw.MolsToGridImage(hmols)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "core = Chem.MolFromSmarts(\"C1CCO[C@@](*)(*)1\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Make RGroup decomposition!\n", "\n", "To use RGroupDecomposition:\n", " \n", " 1. construct the class on the core rg = RGroupDecomposition(core)\n", " 2. Call rg.Add( mol ) on the molecules. If this returns -1, the molecule is not\n", " compatible with the core\n", " 3. After all molecules are added, call rg.Process() to complete the rgroup\n", " decomposition." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "rgroups = rdRGroupDecomposition.RGroupDecomposition(core)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "for i,m in enumerate(mols):\n", " rgroups.Add(m)\n", " if i == 10:\n", " break" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We need to call process after all molecules are added. To optimize the RGroups." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rgroups.Process()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The RGroupDecomposition code is quite compatible with the python pandas integration.\n", "Calling rg.GetRGroupsAsColumns() can be sent directly into a pandas table.\n", "\n", "**n.b.** You need to call PandasTools.ChangeMoleculeRendering(frame) to allow the molecules\n", "to be rendered properly." ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "groups = rgroups.GetRGroupsAsColumns()\n", "frame = pd.DataFrame(groups)\n", "PandasTools.ChangeMoleculeRendering(frame)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The first two (0 and 1) are different due to the sterochemistry difference.\n", "I still haven't found a way to show the core with stereochem which is annoying." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CoreR1R2
0\"Mol\"/\"Mol\"/\"Mol\"/
1\"Mol\"/\"Mol\"/\"Mol\"/
2\"Mol\"/\"Mol\"/\"Mol\"/
3\"Mol\"/\"Mol\"/\"Mol\"/
4\"Mol\"/\"Mol\"/\"Mol\"/
5\"Mol\"/\"Mol\"/\"Mol\"/
6\"Mol\"/\"Mol\"/\"Mol\"/
7\"Mol\"/\"Mol\"/\"Mol\"/
8\"Mol\"/\"Mol\"/\"Mol\"/
9\"Mol\"/\"Mol\"/\"Mol\"/
10\"Mol\"/\"Mol\"/\"Mol\"/
" ], "text/plain": [ "" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "HTML(frame.to_html())" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "Let's try the same with stereochemistry in the core.\n", "\n", "**Note that the core has symmetry and the analysis nicely supports this during \n", "the side chain optimization**\n", "\n", "**n.b.** stereo information is lost here which is fairly annoying and will be analyzed at a later date." ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CoreR1
0\"Mol\"/\"Mol\"/
1\"Mol\"/\"Mol\"/
2\"Mol\"/\"Mol\"/
3\"Mol\"/\"Mol\"/
4\"Mol\"/\"Mol\"/
5\"Mol\"/\"Mol\"/
6\"Mol\"/\"Mol\"/
7\"Mol\"/\"Mol\"/
8\"Mol\"/\"Mol\"/
9\"Mol\"/\"Mol\"/
10\"Mol\"/\"Mol\"/
11\"Mol\"/\"Mol\"/
12\"Mol\"/\"Mol\"/
13\"Mol\"/\"Mol\"/
14\"Mol\"/\"Mol\"/
15\"Mol\"/\"Mol\"/
16\"Mol\"/\"Mol\"/
17\"Mol\"/\"Mol\"/
18\"Mol\"/\"Mol\"/
19\"Mol\"/\"Mol\"/
" ], "text/plain": [ "" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "core = Chem.MolFromSmarts(\"C1CCOC1\")\n", "rgroups = rdRGroupDecomposition.RGroupDecomposition(core)\n", "for m in mols:\n", " rgroups.Add(m)\n", "rgroups.Process()\n", "frame = pd.DataFrame(rgroups.GetRGroupsAsColumns())\n", "PandasTools.ChangeMoleculeRendering(frame)\n", "HTML(frame.to_html())" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python (conda rdkit_build)", "language": "python", "name": "rdkit_build" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.3" } }, "nbformat": 4, "nbformat_minor": 1 }