LucaCappelletti94/epigenomic_dataset

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from crr_labels import fantom\n",
    "from tqdm.auto import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ad87780a9ea74c99881a2dddf52028e4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/5 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from epigenomic_dataset.utils import get_cell_lines\n",
    "\n",
    "window_sizes = [64, 128, 256, 512, 1024]\n",
    "\n",
    "for window_size, (enhancers_fantom_hg38, promoters_fantom_hg38) in zip(tqdm(window_sizes), fantom(\n",
    "    # We retrieve the labels for all the cell lines we are interested in,\n",
    "    # whose epigenomic datasets are already made available from the `epigenomic_dataset`\n",
    "    # package.\n",
    "    # Since in FANTOM5 the cell line MCF-7 is encoded as MCF7, we need to\n",
    "    # remove the hyphen from the cell lines names.\n",
    "    cell_lines=[\n",
    "        cell_line.replace(\"-\", \"\")\n",
    "        for cell_line in get_cell_lines()\n",
    "    ],\n",
    "    # We will expand the sequence snippets to a size of 512\n",
    "    window_sizes=window_sizes,\n",
    "    # The genome version we want to use\n",
    "    genome=\"hg38\",\n",
    "    # We will not, for now, binarize the tasks\n",
    "    binarize=False,\n",
    ")):\n",
    "    path = f\"preprocessed/fantom/hg38/{window_size}/{{region}}.bed.xz\"\n",
    "    enhancers_fantom_hg38.to_csv(path.format(region=\"enhancers\"), sep=\"\\t\", index=False)\n",
    "    promoters_fantom_hg38.to_csv(path.format(region=\"promoters\"), sep=\"\\t\", index=False)"
   ]
  },
  {
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}