Skip to content

Instantly share code, notes, and snippets.

@yamasakih

yamasakih/12-calculate_descriptors.ipynb

Created March 5, 2019 21:46
Show Gist options
  • Save yamasakih/d423cb2a387c397112eb66a64202965c to your computer and use it in GitHub Desktop.
Save yamasakih/d423cb2a387c397112eb66a64202965c to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
12-calculate_descriptors.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from rdkit import Chem\n",
"from rdkit.Chem import Descriptors\n",
"from rdkit.ML.Descriptors import MoleculeDescriptors\n",
"\n",
"\n",
"def calculate_descriptors(mols, names=None, ipc_avg=False):\n",
" if names is None:\n",
" names = [d[0] for d in Descriptors._descList]\n",
" calc = MoleculeDescriptors.MolecularDescriptorCalculator(names)\n",
" descs = [calc.CalcDescriptors(mol) for mol in mols]\n",
" descs = pd.DataFrame(descs, columns=names)\n",
" if 'Ipc' in names and ipc_avg:\n",
" descs['Ipc'] = [Descriptors.Ipc(mol, avg=True) for mol in mols] \n",
" return descs"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"mols = [Chem.MolFromSmiles(s) for s in ['c1ccccc1', 'C1CCCCC1', 'CCO']]"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>MaxEStateIndex</th>\n",
" <th>MinEStateIndex</th>\n",
" <th>MaxAbsEStateIndex</th>\n",
" <th>MinAbsEStateIndex</th>\n",
" <th>qed</th>\n",
" <th>MolWt</th>\n",
" <th>HeavyAtomMolWt</th>\n",
" <th>ExactMolWt</th>\n",
" <th>NumValenceElectrons</th>\n",
" <th>NumRadicalElectrons</th>\n",
" <th>...</th>\n",
" <th>fr_sulfide</th>\n",
" <th>fr_sulfonamd</th>\n",
" <th>fr_sulfone</th>\n",
" <th>fr_term_acetylene</th>\n",
" <th>fr_tetrazole</th>\n",
" <th>fr_thiazole</th>\n",
" <th>fr_thiocyan</th>\n",
" <th>fr_thiophene</th>\n",
" <th>fr_unbrch_alkane</th>\n",
" <th>fr_urea</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2.000000</td>\n",
" <td>2.00</td>\n",
" <td>2.000000</td>\n",
" <td>2.00</td>\n",
" <td>0.442628</td>\n",
" <td>78.114</td>\n",
" <td>72.066</td>\n",
" <td>78.046950</td>\n",
" <td>30</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.500000</td>\n",
" <td>1.50</td>\n",
" <td>1.500000</td>\n",
" <td>1.50</td>\n",
" <td>0.422316</td>\n",
" <td>84.162</td>\n",
" <td>72.066</td>\n",
" <td>84.093900</td>\n",
" <td>36</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>7.569444</td>\n",
" <td>0.25</td>\n",
" <td>7.569444</td>\n",
" <td>0.25</td>\n",
" <td>0.406808</td>\n",
" <td>46.069</td>\n",
" <td>40.021</td>\n",
" <td>46.041865</td>\n",
" <td>20</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 200 columns</p>\n",
"</div>"
],
"text/plain": [
" MaxEStateIndex MinEStateIndex MaxAbsEStateIndex MinAbsEStateIndex \\\n",
"0 2.000000 2.00 2.000000 2.00 \n",
"1 1.500000 1.50 1.500000 1.50 \n",
"2 7.569444 0.25 7.569444 0.25 \n",
"\n",
" qed MolWt HeavyAtomMolWt ExactMolWt NumValenceElectrons \\\n",
"0 0.442628 78.114 72.066 78.046950 30 \n",
"1 0.422316 84.162 72.066 84.093900 36 \n",
"2 0.406808 46.069 40.021 46.041865 20 \n",
"\n",
" NumRadicalElectrons ... fr_sulfide fr_sulfonamd fr_sulfone \\\n",
"0 0 ... 0 0 0 \n",
"1 0 ... 0 0 0 \n",
"2 0 ... 0 0 0 \n",
"\n",
" fr_term_acetylene fr_tetrazole fr_thiazole fr_thiocyan fr_thiophene \\\n",
"0 0 0 0 0 0 \n",
"1 0 0 0 0 0 \n",
"2 0 0 0 0 0 \n",
"\n",
" fr_unbrch_alkane fr_urea \n",
"0 0 0 \n",
"1 0 0 \n",
"2 0 0 \n",
"\n",
"[3 rows x 200 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"calculate_descriptors(mols)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Ipc</th>\n",
" <th>MolWt</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>34.399462</td>\n",
" <td>78.114</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>34.399462</td>\n",
" <td>84.162</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2.754888</td>\n",
" <td>46.069</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Ipc MolWt\n",
"0 34.399462 78.114\n",
"1 34.399462 84.162\n",
"2 2.754888 46.069"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"calculate_descriptors(mols, ['Ipc', 'MolWt'])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Ipc</th>\n",
" <th>MolWt</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.719973</td>\n",
" <td>78.114</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.719973</td>\n",
" <td>84.162</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.918296</td>\n",
" <td>46.069</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Ipc MolWt\n",
"0 1.719973 78.114\n",
"1 1.719973 84.162\n",
"2 0.918296 46.069"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"calculate_descriptors(mols, ['Ipc', 'MolWt'], ipc_avg=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# EOF "
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment