Pipeline for Chemoinformatics

pipeline-for-cheminformatics.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Study of Pipeline for Chemoinformatics\n",
    "\n",
    "- Feature Union [example](http://scikit-learn.org/stable/auto_examples/hetero_feature_union.html#sphx-glr-auto-examples-hetero-feature-union-py)\n",
    "- datasource [url](http://modem.ucsd.edu/adme/databases/databases_logS.htm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from rdkit import Chem\n",
    "\n",
    "from sklearn.base import BaseEstimator, TransformerMixin\n",
    "\n",
    "from sklearn.decomposition import TruncatedSVD\n",
    "from sklearn.feature_extraction import DictVectorizer\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.metrics import classification_report\n",
    "from sklearn.pipeline import FeatureUnion\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.svm import SVC, SVR\n",
    "from rdkit.Chem import MACCSkeys\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_FILE = '../data/Hou1290/data_set.sdf'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "index_sdf = [idx for idx, mol in enumerate(Chem.SDMolSupplier(DATA_FILE)) if mol is not None]\n",
    "\n",
    "mol_array = [mol for mol in Chem.SDMolSupplier(DATA_FILE) if mol is not None]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "class ItemSelector(BaseEstimator, TransformerMixin):\n",
    "    def __init__(self, key='objective'):\n",
    "        self.key = key\n",
    "\n",
    "    def fit(self, x, y=None):\n",
    "        return self\n",
    "\n",
    "    def transform(self, mol_array):\n",
    "        if self.key == 'objective':\n",
    "            return [m.GetProp('logS') for m in mol_array if m is not None]\n",
    "        else:\n",
    "            return data_dict[self.key]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1289, 167)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "class Descriptor(BaseEstimator, TransformerMixin):\n",
    "    def __init__(self, key='maccs'):\n",
    "        self.key = key\n",
    "    def fit(self, x, y=None):\n",
    "        return self\n",
    "    \n",
    "    def transform(self, mol_array):\n",
    "        if self.key == 'maccs':\n",
    "            return np.matrix([list(MACCSkeys.GenMACCSKeys(m)) for m in mol_array])\n",
    "\n",
    "ret = Descriptor().fit_transform(mol_array)\n",
    "ret.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "iselec = ItemSelector()\n",
    "yobs = iselec.fit_transform(mol_array)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Pipeline(memory=None,\n",
       "     steps=[('gen_fp', Descriptor(key='maccs')), ('svr', SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, gamma='auto',\n",
       "  kernel='rbf', max_iter=-1, shrinking=True, tol=0.001, verbose=False))])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = Pipeline([('gen_fp', Descriptor()),\n",
    "                  ('svr', SVR())])\n",
    "\n",
    "model.fit(mol_array, yobs)"
   ]
  }
 ],
 "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": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}