{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# User API examples"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Setup python environment and install posebusters to run this notebook.\n",
    "\n",
    "```bash\n",
    "conda create -n posebusters python=3.10 jupyter notebook\n",
    "conda activate posebusters\n",
    "pip install posebusters --upgrade\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "\n",
    "pred_file = Path(\"inputs/generated_molecules.sdf\")  # predicted or generated molecules\n",
    "true_file = Path(\"inputs/crystal_ligand.sdf\")  # \"ground truth\" molecules\n",
    "cond_file = Path(\"inputs/protein.pdb\")  # conditioning molecule"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PoseBusters default configs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from posebusters import PoseBusters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### redock\n",
    "The `redock' mode is for ligands docked into their cognate receptor crystal structures."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# by default only the binary test report columns are returned\n",
    "buster = PoseBusters(config=\"redock\")\n",
    "df = buster.bust([pred_file], true_file, cond_file)\n",
    "print(df.shape)\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### dock\n",
    "The `dock` mode is for *de-novo* generated molecules for a given receptor or for ligands docked into a non-cognate receptor."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "buster = PoseBusters(config=\"dock\")\n",
    "df = buster.bust([pred_file], true_file, cond_file)\n",
    "print(df.shape)\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### mol\n",
    "The `mol` mode is for *de-novo* generated molecules or for generated molecular conformations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "buster = PoseBusters(config=\"mol\")\n",
    "df = buster.bust([pred_file], None, None)\n",
    "print(df.shape)\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Output formatting"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### full report\n",
    "The `full_report` option of `bust` will return all columns of the test reports, not only the binary columns. This is useful for debugging and for further analysis of the results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "buster = PoseBusters(config=\"mol\")\n",
    "df = buster.bust([pred_file], None, None, full_report=True)\n",
    "print(df.shape)\n",
    "df"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "posebusters",
   "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": "3.10.12"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}