{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a91bca46-c056-4784-8c6c-b0f5d3f33496",
   "metadata": {
    "tags": []
   },
   "source": [
    "## Tokenizing .loom single cell RNA-seq data to rank value encoding .dataset format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "080fdd9c-0c48-4d5d-a254-52b6c53cdf78",
   "metadata": {},
   "outputs": [],
   "source": [
    "from geneformer import TranscriptomeTokenizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9641b146-af2c-4688-9d8a-9c570246d116",
   "metadata": {},
   "outputs": [],
   "source": [
    "tk = TranscriptomeTokenizer({\"cell_type\": \"cell_type\", \"organ_major\": \"organ_major\"}, nproc=4)   # Dictionary of custom attributes to be added to the dataset.\n",
    "tk.tokenize_data(\"loom_data_directory\", \"output_directory\", \"output_prefix\")"
   ]
  }
 ],
 "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}