{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "85857f5c",
   "metadata": {},
   "source": [
    "# EpiCMITHypo"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5bc819a",
   "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": "6908f801",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "38309ebf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:18.861408Z",
     "iopub.status.busy": "2026-07-04T19:39:18.861231Z",
     "iopub.status.idle": "2026-07-04T19:39:20.907018Z",
     "shell.execute_reply": "2026-07-04T19:39:20.906530Z"
    }
   },
   "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": "98778012",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5aac85ce",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:20.908636Z",
     "iopub.status.busy": "2026-07-04T19:39:20.908465Z",
     "iopub.status.idle": "2026-07-04T19:39:20.911208Z",
     "shell.execute_reply": "2026-07-04T19:39:20.910849Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class EpiCMITHypo(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.EpiCMITHypo)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "385d21d8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:20.912617Z",
     "iopub.status.busy": "2026-07-04T19:39:20.912523Z",
     "iopub.status.idle": "2026-07-04T19:39:20.914218Z",
     "shell.execute_reply": "2026-07-04T19:39:20.913852Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.EpiCMITHypo()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "32bcc319",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "bb771c46",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:20.915449Z",
     "iopub.status.busy": "2026-07-04T19:39:20.915358Z",
     "iopub.status.idle": "2026-07-04T19:39:20.917567Z",
     "shell.execute_reply": "2026-07-04T19:39:20.917213Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"epicmithypo\"\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\"] = \"Hypomethylation component of epiCMIT: a 1,164-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\"] = \"complement of mean methylation\"  # Paper: Complement of 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\"] = 1164\n",
    "model.metadata[\"citations\"] = 104\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4402281",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "0070d992",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:20.918946Z",
     "iopub.status.busy": "2026-07-04T19:39:20.918870Z",
     "iopub.status.idle": "2026-07-04T19:39:23.319051Z",
     "shell.execute_reply": "2026-07-04T19:39:23.318537Z"
    }
   },
   "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": "2dc0f591",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7d8d285a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:23.320498Z",
     "iopub.status.busy": "2026-07-04T19:39:23.320390Z",
     "iopub.status.idle": "2026-07-04T19:39:24.253177Z",
     "shell.execute_reply": "2026-07-04T19:39:24.252634Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_excel('epicmit.xlsx', sheet_name='Table 23')\n",
    "df = df[df['epiCMIT.class'].astype(str).str.contains('hypo', case=False)]\n",
    "model.features = df['Name'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "97815cdc",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "41572803",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.254695Z",
     "iopub.status.busy": "2026-07-04T19:39:24.254602Z",
     "iopub.status.idle": "2026-07-04T19:39:24.256660Z",
     "shell.execute_reply": "2026-07-04T19:39:24.256276Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor([-1.0]).unsqueeze(0)\n",
    "intercept = torch.tensor([1.0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4b3dec57",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.257835Z",
     "iopub.status.busy": "2026-07-04T19:39:24.257758Z",
     "iopub.status.idle": "2026-07-04T19:39:24.259861Z",
     "shell.execute_reply": "2026-07-04T19:39:24.259497Z"
    }
   },
   "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": "8127702e",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "52cfab7a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.261037Z",
     "iopub.status.busy": "2026-07-04T19:39:24.260974Z",
     "iopub.status.idle": "2026-07-04T19:39:24.262509Z",
     "shell.execute_reply": "2026-07-04T19:39:24.262171Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = [-1]*len(model.features)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb6b834b",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "7aa8d11a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.263579Z",
     "iopub.status.busy": "2026-07-04T19:39:24.263510Z",
     "iopub.status.idle": "2026-07-04T19:39:24.265057Z",
     "shell.execute_reply": "2026-07-04T19:39:24.264672Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = \"mean\"\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "57a46eea",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.266131Z",
     "iopub.status.busy": "2026-07-04T19:39:24.266055Z",
     "iopub.status.idle": "2026-07-04T19:39:24.267546Z",
     "shell.execute_reply": "2026-07-04T19:39:24.267197Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86135a92",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8624db05",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.268509Z",
     "iopub.status.busy": "2026-07-04T19:39:24.268441Z",
     "iopub.status.idle": "2026-07-04T19:39:24.271620Z",
     "shell.execute_reply": "2026-07-04T19:39:24.271355Z"
    }
   },
   "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': 'epicmithypo',\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: 1164]\n",
      "preprocess_name: 'mean'\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg21870274', 'cg17810211', 'cg08263140', 'cg05663262', 'cg00055603', 'cg05042706', 'cg25469314', 'cg16515477', 'cg07910726', 'cg22037030', 'cg00954256', 'cg13047196', 'cg04910179', 'cg08123701', 'cg14777634', 'cg11795488', 'cg21679730', 'cg11228758', 'cg13784017', 'cg17987458', 'cg12302119', 'cg05928873', 'cg17041296', 'cg16926302', 'cg11338128', 'cg05948962', 'cg01952027', 'cg17175521', 'cg17011453', 'cg26032419']... [Total elements: 1164]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=1164, 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([1.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86be345b",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "682e50ed",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.272825Z",
     "iopub.status.busy": "2026-07-04T19:39:24.272756Z",
     "iopub.status.idle": "2026-07-04T19:39:24.278148Z",
     "shell.execute_reply": "2026-07-04T19:39:24.277639Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[0.9526],\n",
       "        [1.0553],\n",
       "        [1.0356],\n",
       "        [0.9706],\n",
       "        [1.0003],\n",
       "        [0.9377],\n",
       "        [1.0229],\n",
       "        [1.0117],\n",
       "        [1.0650],\n",
       "        [0.9722]], 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": "3cdde583",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "1e3c2a62",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.279390Z",
     "iopub.status.busy": "2026-07-04T19:39:24.279300Z",
     "iopub.status.idle": "2026-07-04T19:39:24.284998Z",
     "shell.execute_reply": "2026-07-04T19:39:24.284482Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "efc099e8",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "59376b02",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:39:24.286618Z",
     "iopub.status.busy": "2026-07-04T19:39:24.286529Z",
     "iopub.status.idle": "2026-07-04T19:39:24.290066Z",
     "shell.execute_reply": "2026-07-04T19:39:24.289760Z"
    }
   },
   "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
}