{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f6e7d8c9",
   "metadata": {},
   "source": [
    "# Saving a MethylSeg Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6dea5bfa",
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "56805eb7",
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import yaml\n",
    "from pathlib import Path\n",
    "\n",
    "import os\n",
    "\n",
    "\n",
    "from methylseg import MethylSegPathway, MethylDataPrep, MethylStateAssignmentMethod, MethylationStates\n",
    "from methylseg.helper_classes import DATA_DIR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "66b4e992",
   "metadata": {},
   "outputs": [],
   "source": [
    "REFERENCE_DIR = DATA_DIR / Path(\"reference_files\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d15dc1b9",
   "metadata": {},
   "outputs": [],
   "source": [
    "tcga_sample_info, tcga_sample_info_removed = MethylDataPrep(\n",
    "    meth_file=REFERENCE_DIR / \"TCGA-BD-A3EP-01A_450k.tsv.gz\",\n",
    "    sample_id=\"TCGA-BD-A3EP-01A\",\n",
    "    resolution=\"450k\",\n",
    "    remove_low_coverage_like_cpgs=True,\n",
    ").prepare()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "56603441",
   "metadata": {},
   "outputs": [],
   "source": [
    "hm450k_model = MethylSegPathway(\n",
    "    train_sample_info=tcga_sample_info,\n",
    "    out_dir=Path(\"out\") / \"hm450k_model_outdir\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "23ca4994",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Random search: 100%|██████████| 500/500 [04:43<00:00,  1.77it/s]\n"
     ]
    }
   ],
   "source": [
    "hm450k_model.fit_pathway(force_optimize_rules=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fcedce3d",
   "metadata": {},
   "outputs": [],
   "source": [
    "hm450k_model.to_yaml(REFERENCE_DIR / \"tcga_hm450k_model.yaml\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "980df81f",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_model = MethylSegPathway.from_yaml(REFERENCE_DIR / \"tcga_hm450k_model.yaml\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9347ed64",
   "metadata": {},
   "outputs": [],
   "source": [
    "wgbs_test_sample_info, wgbs_test_sample_info_removed = MethylDataPrep(\n",
    "    meth_file=REFERENCE_DIR / \"WGBS_colon-primary-tumor_1_wgbs.tsv.gz\",\n",
    "    sample_id=\"colon-primary-tumor_1\",\n",
    "    resolution=\"wgbs\",\n",
    "    min_coverage=10,\n",
    "    remove_low_coverage_like_cpgs=True,\n",
    ").prepare()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8463f6e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "wgbs_model = MethylSegPathway(\n",
    "    train_sample_info=wgbs_test_sample_info,\n",
    "    out_dir= Path(\"out\") /  \"wgbs_model_outdir\",\n",
    "    hmm_type=\"sticky\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "024e8f38",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Random search: 100%|██████████| 500/500 [13:29<00:00,  1.62s/it]\n"
     ]
    }
   ],
   "source": [
    "wgbs_model.fit_pathway(force_optimize_rules=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "92dd4a59",
   "metadata": {},
   "outputs": [],
   "source": [
    "wgbs_model.to_yaml(REFERENCE_DIR / \"wgbs_colon_model.yaml\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b35f3cda",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_model = MethylSegPathway.from_yaml(REFERENCE_DIR / \"wgbs_colon_model.yaml\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "jt_wgbs_analysis",
   "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": "3.11.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}