{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import qml "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from glob import glob\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from rdkit import Chem"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "def read_sdf(sdf):\n",
    "    with open(sdf, \"r\") as f:\n",
    "        txt = f.read().rstrip()\n",
    "    return txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_CM(sdf):\n",
    "    mol = Chem.MolFromMolBlock(sdf)\n",
    "    # rdkit molobj\n",
    "    ncharges = [atom.GetAtomicNum() for atom in mol.GetAtoms()]\n",
    "    conf = mol.GetConformer()\n",
    "    coords = np.asarray(conf.GetPositions())\n",
    "    CM = np.zeros((len(coords), len(coords)))\n",
    "    for i in range(len(coords)):\n",
    "        for j in range(len(coords)):\n",
    "            if i==j:\n",
    "                CM[i,j] = 0.5 * ncharges[i]**2.4\n",
    "            else:\n",
    "                CM[i,j] = ncharges[i] * ncharges[j] / np.linalg.norm(coords[j] - coords[i])\n",
    "                \n",
    "    return ncharges, CM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['targets/qm9.sdf', 'targets/vitc.sdf', 'targets/vitd.sdf']"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target_sdfs = sorted(glob(\"targets/*.sdf\"))\n",
    "target_sdfs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_amons_files = sorted(glob(\"amons-qm9/*.sdf\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_amons_sdfs = [read_sdf(x) for x in qm9_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_amons_ncharges = []\n",
    "qm9_amons_CMs = []\n",
    "for sdf in qm9_amons_sdfs:\n",
    "    ncharge, CM = get_CM(sdf)\n",
    "    qm9_amons_ncharges.append(ncharge)\n",
    "    qm9_amons_CMs.append(CM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "qm9_amons_labels = [t.split(\"/\")[-1].split(\".sdf\")[0] for t in qm9_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_amons_files = sorted(glob(\"amons-vitc/*.sdf\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_amons_sdfs = [read_sdf(x) for x in vitc_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_amons_ncharges = []\n",
    "vitc_amons_CMs = []\n",
    "for sdf in vitc_amons_sdfs:\n",
    "    ncharge, CM = get_CM(sdf)\n",
    "    vitc_amons_ncharges.append(ncharge)\n",
    "    vitc_amons_CMs.append(CM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitc_amons_labels = [t.split(\"/\")[-1].split(\".sdf\")[0] for t in vitc_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_amons_files = sorted(glob(\"amons-vitd/*.sdf\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_amons_sdfs = [read_sdf(x) for x in vitd_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_amons_ncharges = []\n",
    "vitd_amons_CMs = []\n",
    "for sdf in vitd_amons_sdfs:\n",
    "    ncharge, CM = get_CM(sdf)\n",
    "    vitd_amons_ncharges.append(ncharge)\n",
    "    vitd_amons_CMs.append(CM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "vitd_amons_labels = [t.split(\"/\")[-1].split(\".sdf\")[0] for t in vitd_amons_files]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# np save "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/puck/anaconda3/envs/rdkit/lib/python3.7/site-packages/numpy/core/_asarray.py:136: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
      "  return array(a, dtype, copy=False, order=order, subok=True)\n"
     ]
    }
   ],
   "source": [
    "np.savez(\"amons_data.npz\", \n",
    "         vitd_amons_labels=vitd_amons_labels,\n",
    "         vitc_amons_labels=vitc_amons_labels,\n",
    "         qm9_amons_labels=qm9_amons_labels,\n",
    "         vitd_amons_ncharges=vitd_amons_ncharges,\n",
    "         vitc_amons_ncharges=vitc_amons_ncharges,\n",
    "         qm9_amons_ncharges=qm9_amons_ncharges,\n",
    "         vitd_amons_CMs=vitd_amons_CMs,\n",
    "         vitc_amons_CMs=vitc_amons_CMs,\n",
    "         qm9_amons_CMs=qm9_amons_CMs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = np.load(\"amons_data.npz\", allow_pickle=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['vitd_amons_labels',\n",
       " 'vitc_amons_labels',\n",
       " 'qm9_amons_labels',\n",
       " 'vitd_amons_ncharges',\n",
       " 'vitc_amons_ncharges',\n",
       " 'qm9_amons_ncharges',\n",
       " 'vitd_amons_CMs',\n",
       " 'vitc_amons_CMs',\n",
       " 'qm9_amons_CMs']"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}