{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "Example lactam analysis using a single cores on a very large dataset." ] }, { "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.rdRGroupDecomposition import RGroupDecomposition\n", "import pandas as pd\n", "from rdkit.Chem import PandasTools\n", "from IPython.display import HTML\n", "from rdkit import rdBase\n", "rdBase.DisableLog(\"rdApp.debug\")" ] }, { "cell_type": "code", "execution_count": 2, "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", "\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": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "core = Chem.MolFromSmiles('O=C1C([*])C2N1C(C(O)=O)=C([*])CS2')\n", "core" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "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": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "RDKit ERROR: [20:17:28] SMILES Parse Error: syntax error while parsing: CANONICAL_SMILES\n", "RDKit ERROR: [20:17:28] SMILES Parse Error: Failed parsing SMILES 'CANONICAL_SMILES' for input: 'CANONICAL_SMILES'\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Added 1194 to RGroup Decomposition out of 4340\n" ] } ], "source": [ "rg = RGroupDecomposition(core)\n", "\n", "mols = []\n", "count = 0\n", "for line in open(\"compounds.txt\"):\n", " sm = line.split()[-1]\n", " m = Chem.MolFromSmiles(sm)\n", " if m:\n", " count += 1\n", " idx = rg.Add(m)\n", "rg.Process()\n", "print (\"Added %s to RGroup Decomposition out of %s\"%(idx, count))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It is useful to disable logging here. When making RGroup renderings there \n", "are a lot of sanitization warnings." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "from rdkit import RDLogger\n", "RDLogger.DisableLog(\"rdApp.*\")" ] }, { "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": 5, "metadata": {}, "outputs": [], "source": [ "frame = pd.DataFrame(rg.GetRGroupsAsColumns())\n", "PandasTools.ChangeMoleculeRendering(frame)" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "Just show the first few (for speed and to keep the notebook small)" ] }, { "cell_type": "code", "execution_count": 6, "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", "
CoreR1R2R3R4R5
0\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/
1\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/
2\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/
3\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/
4\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/\"Mol\"/
" ], "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "f2 = pd.DataFrame(frame.head())\n", "PandasTools.ChangeMoleculeRendering(f2)\n", "HTML(f2.to_html())" ] } ], "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 }