{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a472b026",
   "metadata": {},
   "source": [
    "# EpiCMITHyper"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17dcbe69",
   "metadata": {},
   "source": [
    "## Index\n",
    "1. [Instantiate model class](#Instantiate-model-class)\n",
    "2. [Define clock metadata](#Define-clock-metadata)\n",
    "3. [Download clock dependencies](#Download-clock-dependencies)\n",
    "5. [Load features](#Load-features)\n",
    "6. [Load weights into base model](#Load-weights-into-base-model)\n",
    "7. [Load reference values](#Load-reference-values)\n",
    "8. [Load preprocess and postprocess objects](#Load-preprocess-and-postprocess-objects)\n",
    "10. [Check all clock parameters](#Check-all-clock-parameters)\n",
    "10. [Basic test](#Basic-test)\n",
    "11. [Save torch model](#Save-torch-model)\n",
    "12. [Clear directory](#Clear-directory)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ab6f61e",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ec3511d3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:11.098617Z",
     "iopub.status.busy": "2026-07-04T19:39:11.098453Z",
     "iopub.status.idle": "2026-07-04T19:39:13.414710Z",
     "shell.execute_reply": "2026-07-04T19:39:13.413768Z"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import inspect\n",
    "import shutil\n",
    "import json\n",
    "import torch\n",
    "import pandas as pd\n",
    "import pyaging as pya"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bd750d1",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e2ecfb86",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:13.416927Z",
     "iopub.status.busy": "2026-07-04T19:39:13.416645Z",
     "iopub.status.idle": "2026-07-04T19:39:13.421587Z",
     "shell.execute_reply": "2026-07-04T19:39:13.421051Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class EpiCMITHyper(epiTOC1):\n",
      "    pass\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.EpiCMITHyper)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "43dca5a3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:13.422887Z",
     "iopub.status.busy": "2026-07-04T19:39:13.422808Z",
     "iopub.status.idle": "2026-07-04T19:39:13.424729Z",
     "shell.execute_reply": "2026-07-04T19:39:13.424290Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.EpiCMITHyper()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "47e4582b",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c2b5bd52",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:13.426027Z",
     "iopub.status.busy": "2026-07-04T19:39:13.425925Z",
     "iopub.status.idle": "2026-07-04T19:39:13.428495Z",
     "shell.execute_reply": "2026-07-04T19:39:13.427930Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"epicmithyper\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: methylation\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: Homo sapiens\n",
    "model.metadata[\"year\"] = 2020\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Duran-Ferrer, M., et al. \\\"The proliferative history shapes the DNA methylome of B-cell tumors and predicts clinical outcome.\\\" Nature Cancer 1 (2020): 1066-1081.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s43018-020-00131-2\"\n",
    "model.metadata[\"notes\"] = \"Hypermethylation component of epiCMIT: a 184-CpG score ranging from 0 to 1 that tracks low-to-high relative proliferative history in normal and neoplastic B cells.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"B cells\"]  # Paper: normal and neoplastic B cells\n",
    "model.metadata[\"predicts\"] = [\"mitotic age\"]  # Paper: The author tutorial states both component clocks range from 0 to 1 and report relative proliferative history.\n",
    "model.metadata[\"training_target\"] = [\"replicative history\"]  # Paper: relative proliferative history\n",
    "model.metadata[\"unit\"] = [\"proportion\"]  # Paper: The author tutorial states both component clocks range from 0 to 1 and report relative proliferative history.\n",
    "model.metadata[\"model_type\"] = \"mean methylation aggregation\"  # Paper: Mean methylation score\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\", \"Illumina EPIC\"]  # Paper: Illumina 450K; Illumina EPIC\n",
    "model.metadata[\"population\"] = \"human, age unspecified\"  # Paper: 1,595 human samples spanning normal B-cell subpopulations and 14 B-cell tumor subtypes\n",
    "model.metadata[\"journal\"] = \"Nature Cancer\"\n",
    "model.metadata[\"last_author\"] = \"José I. Martín-Subero\"\n",
    "model.metadata[\"n_features\"] = 184\n",
    "model.metadata[\"citations\"] = 104\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "569da7a8",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8be3b2e0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:13.429977Z",
     "iopub.status.busy": "2026-07-04T19:39:13.429896Z",
     "iopub.status.idle": "2026-07-04T19:39:15.872124Z",
     "shell.execute_reply": "2026-07-04T19:39:15.870891Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://static-content.springer.com/esm/art%3A10.1038%2Fs43018-020-00131-2/MediaObjects/43018_2020_131_MOESM3_ESM.xlsx\"\n",
    "supplementary_file_name = \"epicmit.xlsx\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a7e8e03c",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3d17c8fc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:15.875161Z",
     "iopub.status.busy": "2026-07-04T19:39:15.874889Z",
     "iopub.status.idle": "2026-07-04T19:39:16.856710Z",
     "shell.execute_reply": "2026-07-04T19:39:16.856186Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_excel('epicmit.xlsx', sheet_name='Table 23')\n",
    "df = df[df['epiCMIT.class'].astype(str).str.contains('hyper', case=False)]\n",
    "model.features = df['Name'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "78d5555d",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e8ed83f6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.858171Z",
     "iopub.status.busy": "2026-07-04T19:39:16.858093Z",
     "iopub.status.idle": "2026-07-04T19:39:16.860299Z",
     "shell.execute_reply": "2026-07-04T19:39:16.859655Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor([1.0]).unsqueeze(0)\n",
    "intercept = torch.tensor([0.0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6c3e88f2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.862131Z",
     "iopub.status.busy": "2026-07-04T19:39:16.861989Z",
     "iopub.status.idle": "2026-07-04T19:39:16.864681Z",
     "shell.execute_reply": "2026-07-04T19:39:16.864142Z"
    }
   },
   "outputs": [],
   "source": [
    "base_model = pya.models.LinearModel(input_dim=len(model.features))\n",
    "\n",
    "base_model.linear.weight.data = weights.float()\n",
    "base_model.linear.bias.data = intercept.float()\n",
    "\n",
    "model.base_model = base_model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8381f629",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "bfdf0b41",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.866249Z",
     "iopub.status.busy": "2026-07-04T19:39:16.866136Z",
     "iopub.status.idle": "2026-07-04T19:39:16.868018Z",
     "shell.execute_reply": "2026-07-04T19:39:16.867560Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = [-1]*len(model.features)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b2ac10e",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "db5944d5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.869473Z",
     "iopub.status.busy": "2026-07-04T19:39:16.869280Z",
     "iopub.status.idle": "2026-07-04T19:39:16.871514Z",
     "shell.execute_reply": "2026-07-04T19:39:16.870907Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = \"mean\"\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "062e7d42",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.873060Z",
     "iopub.status.busy": "2026-07-04T19:39:16.872948Z",
     "iopub.status.idle": "2026-07-04T19:39:16.874740Z",
     "shell.execute_reply": "2026-07-04T19:39:16.874347Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "774e7915",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7d20e68f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.875947Z",
     "iopub.status.busy": "2026-07-04T19:39:16.875872Z",
     "iopub.status.idle": "2026-07-04T19:39:16.879530Z",
     "shell.execute_reply": "2026-07-04T19:39:16.879157Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Duran-Ferrer, Marti, et al. \"The proliferative history shapes '\n",
      "             'the DNA methylome of B-cell tumors and predicts clinical '\n",
      "             'outcome.\" Nature Cancer 1.11 (2020): 1066-1081.',\n",
      " 'clock_name': 'epicmithyper',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s43018-020-00131-2',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2020}\n",
      "reference_values: [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1]... [Total elements: 184]\n",
      "preprocess_name: 'mean'\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg19715410', 'cg18279094', 'cg11823511', 'cg24453699', 'cg03989260', 'cg14565725', 'cg00466334', 'cg24035245', 'cg05378938', 'cg09671258', 'cg09826050', 'cg07279070', 'cg18093372', 'cg18173235', 'cg07813142', 'cg24772753', 'cg17737681', 'cg17078253', 'cg05467160', 'cg04415176', 'cg01405040', 'cg02694427', 'cg03964958', 'cg09578028', 'cg04739647', 'cg05167251', 'cg22674699', 'cg22541735', 'cg19384289', 'cg14473102']... [Total elements: 184]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=184, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[1.]])\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04d85a27",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "fff8eeb7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.880736Z",
     "iopub.status.busy": "2026-07-04T19:39:16.880664Z",
     "iopub.status.idle": "2026-07-04T19:39:16.890617Z",
     "shell.execute_reply": "2026-07-04T19:39:16.890143Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 0.0423],\n",
       "        [ 0.0471],\n",
       "        [ 0.0455],\n",
       "        [ 0.0341],\n",
       "        [ 0.0093],\n",
       "        [ 0.0674],\n",
       "        [ 0.0421],\n",
       "        [ 0.0545],\n",
       "        [ 0.0112],\n",
       "        [-0.1275]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.manual_seed(42)\n",
    "input = torch.randn(10, len(model.features), dtype=float)\n",
    "model.eval()\n",
    "model.to(float)\n",
    "pred = model(input)\n",
    "pred"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6fd22db0",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7f18d318",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.891834Z",
     "iopub.status.busy": "2026-07-04T19:39:16.891757Z",
     "iopub.status.idle": "2026-07-04T19:39:16.896145Z",
     "shell.execute_reply": "2026-07-04T19:39:16.895688Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "642baee1",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b2e4fe26",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:16.897525Z",
     "iopub.status.busy": "2026-07-04T19:39:16.897449Z",
     "iopub.status.idle": "2026-07-04T19:39:16.901192Z",
     "shell.execute_reply": "2026-07-04T19:39:16.900815Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: epicmit.xlsx\n"
     ]
    }
   ],
   "source": [
    "# Function to remove a folder and all its contents\n",
    "def remove_folder(path):\n",
    "    try:\n",
    "        shutil.rmtree(path)\n",
    "        print(f\"Deleted folder: {path}\")\n",
    "    except Exception as e:\n",
    "        print(f\"Error deleting folder {path}: {e}\")\n",
    "\n",
    "# Get a list of all files and folders in the current directory\n",
    "all_items = os.listdir('.')\n",
    "\n",
    "# Loop through the items\n",
    "for item in all_items:\n",
    "    # Check if it's a file and does not end with .ipynb\n",
    "    if os.path.isfile(item) and not item.endswith('.ipynb'):\n",
    "        os.remove(item)\n",
    "        print(f\"Deleted file: {item}\")\n",
    "    # Check if it's a folder\n",
    "    elif os.path.isdir(item):\n",
    "        remove_folder(item)"
   ]
  }
 ],
 "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": "3.13.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}