{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f9a56972",
   "metadata": {},
   "source": [
    "# Foreword\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3b6d2f62-03a1-4f4d-9d36-6efedfd46aef",
   "metadata": {},
   "source": [
    "These demo notebooks must be executed from the `docs` directory. \n",
    "\n",
    "Before starting, remember to activate the environment: \n",
    "\n",
    "    source .venv/bin/activate\n",
    "\n",
    "or equivalently \n",
    "\n",
    "    uv run jupyter notebook\n",
    "    \n",
    "The scripts also produce publication-quality figures in `../extra`.\n",
    "\n",
    "The original trajectories files are supporting information of the paper [1](http://science.sciencemag.org/content/334/6055/517) and must be obtained from DESRES. They need to be split in 3 unfolded + 3 folded segments, downsampled, and filtered according to the directions in the files. For reproducibility, we provide the corresponding pre-computed projections (the high-dimensional embeddings that are input to the ID functions).\n",
    "\n",
    "1. Lindorff-Larsen K, Piana S, Dror RO, Shaw DE. How Fast-Folding Proteins Fold. [Science. 2011 Oct 28;334(6055):517–20.](http://science.sciencemag.org/content/334/6055/517) \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "80c00921-a9f5-40a1-ad67-072f5a36d30b",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}