{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "This example shows how ring substitutions are handled." ] }, { "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": [ "core = Chem.MolFromSmarts(\"*1CCCC1\")" ] }, { "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" ], "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "core" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "scrolled": true }, "outputs": [], "source": [ "smiles = [\"C1CCCC1-C2CCC2Cl\", \"N1CCCC1-C2CCC2Cl\", \"O1CCCC1-C2CCC2Cl\", \"N1OCCC1-C2CCC2Cl\", \"N1OCSC1-C2CCC2Cl\"]\n", "\n", "mols = [Chem.MolFromSmiles(smi) for smi in smiles]" ] }, { "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", "" ], "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": { "text/plain": [ "(0, 1, 2, 3, 4)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "core.GetSubstructMatch(core)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Make RGroup decomposition!" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "rgroups = rdRGroupDecomposition.RGroupDecomposition(core)" ] }, { "cell_type": "code", "execution_count": 9, "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": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rgroups.Process()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "groups = rgroups.GetRGroupsAsColumns()\n", "frame = pd.DataFrame(groups)\n", "PandasTools.ChangeMoleculeRendering(frame)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "I would have preferred new cores to appear and the [*:2]-N-[*:2] depiction is a bit annoying... Perhaps for round 2" ] }, { "cell_type": "code", "execution_count": 12, "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", "
CoreR1R2
0\"Mol\"/\"Mol\"/\"Mol\"/
1\"Mol\"/\"Mol\"/\"Mol\"/
2\"Mol\"/\"Mol\"/\"Mol\"/
" ], "text/plain": [ "" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "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 }