{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'H': 1, 'F': 1, 'Cl': 1, 'Br': 1, 'I': 1, 'B': 3, 'B+1': 2, 'B-1': 4, 'O': 2, 'O+1': 3, 'O-1': 1, 'N': 3, 'N+1': 4, 'N-1': 2, 'C': 4, 'C+1': 5, 'C-1': 3, 'P': 5, 'P+1': 6, 'P-1': 4, 'S': 6, 'S+1': 7, 'S-1': 5, '?': 8}\n"
     ]
    }
   ],
   "source": [
    "import selfies as sf\n",
    "\n",
    "# 获取默认的语义约束字典\n",
    "constraints = sf.get_preset_constraints(\"default\")\n",
    "print(constraints)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import selfies as sf\n",
    "new_constraints = sf.get_preset_constraints(\"default\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "sf.set_semantic_constraints(new_constraints)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "smiles_dataset = [\"COC\", \"FCF\", \"O=O\", \"O=Cc1ccccc1\"]\n",
    "selfies_dataset = list(map(sf.encoder, smiles_dataset))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "alphabet = sf.get_alphabet_from_selfies(selfies_dataset)\n",
    "alphabet.add(\"[nop]\")\n",
    "\n",
    "alphabet = list(sorted(alphabet))\n",
    "alphabet"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "frage",
   "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": "3.10.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}