{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "6c379230",
   "metadata": {},
   "source": [
    "# CellPopAge"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6419584a",
   "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": "07d0fa09",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "85b8df28",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:45:58.451845Z",
     "iopub.status.busy": "2026-07-04T19:45:58.451640Z",
     "iopub.status.idle": "2026-07-04T19:46:00.395599Z",
     "shell.execute_reply": "2026-07-04T19:46:00.395166Z"
    }
   },
   "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": "52bfd2b6",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "078323d8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:00.397380Z",
     "iopub.status.busy": "2026-07-04T19:46:00.397183Z",
     "iopub.status.idle": "2026-07-04T19:46:00.399885Z",
     "shell.execute_reply": "2026-07-04T19:46:00.399462Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class CellPopAge(LinearReferenceClock):\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.CellPopAge)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "35240ac6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:00.401008Z",
     "iopub.status.busy": "2026-07-04T19:46:00.400928Z",
     "iopub.status.idle": "2026-07-04T19:46:00.402564Z",
     "shell.execute_reply": "2026-07-04T19:46:00.402178Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.CellPopAge()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd11061c",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cf2487d6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:00.403823Z",
     "iopub.status.busy": "2026-07-04T19:46:00.403746Z",
     "iopub.status.idle": "2026-07-04T19:46:00.405609Z",
     "shell.execute_reply": "2026-07-04T19:46:00.405295Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"cellpopage\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The model is based on DNA methylation measurements.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The study samples are Homo sapiens.\n",
    "model.metadata[\"year\"] = 2024\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Lujan, Celia, et al. \\\"An expedited screening platform for the discovery of anti-ageing compounds in vitro and in vivo.\\\" Genome Medicine 16 (2024): 85.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1186/s13073-024-01349-w\"\n",
    "model.metadata[\"notes\"] = \"CellPopAge is an elastic-net DNA-methylation clock using 42 selected CpGs to predict passage-based age of serially cultured adult primary human fibroblast populations and screen compounds that decelerate this measure.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"cultured fibroblasts\"]  # Paper: The listed tissue is the model-development sample material.\n",
    "model.metadata[\"predicts\"] = [\"cell-population passage age\"]  # Paper: The reported predictor output is cell-population passage age.\n",
    "model.metadata[\"training_target\"] = [\"cell passage number\"]  # Paper: The fitting outcome is cell passage number.\n",
    "model.metadata[\"unit\"] = [\"passages\"]  # Paper: The returned construct is expressed as cell passage number.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: The clock was fitted using Elastic net.\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: Training/selection used Illumina EPIC.\n",
    "model.metadata[\"population\"] = \"human cell cultures\"  # Paper: adult primary human fibroblast cultures (39 training samples, passages 10–20)\n",
    "model.metadata[\"journal\"] = \"Genome Medicine\"\n",
    "model.metadata[\"last_author\"] = \"Ivana Bjedov\"\n",
    "model.metadata[\"n_features\"] = 42\n",
    "model.metadata[\"citations\"] = 6\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae9b254b",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a8e2c135",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:00.406893Z",
     "iopub.status.busy": "2026-07-04T19:46:00.406825Z",
     "iopub.status.idle": "2026-07-04T19:46:00.657381Z",
     "shell.execute_reply": "2026-07-04T19:46:00.656857Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o CellPopAge_ref.rda https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data/CellPopAge_ref.rda\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8d66b13e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:00.658766Z",
     "iopub.status.busy": "2026-07-04T19:46:00.658671Z",
     "iopub.status.idle": "2026-07-04T19:46:00.660953Z",
     "shell.execute_reply": "2026-07-04T19:46:00.660648Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing download.r\n"
     ]
    }
   ],
   "source": [
    "%%writefile download.r\n",
    "\n",
    "library(jsonlite)\n",
    "load(\"CellPopAge_ref.rda\")\n",
    "write_json(CellPopAge_ref$all_CpGs, \"coefficients.json\", digits = 10)\n",
    "write_json(CellPopAge_ref$intercept, \"intercept.json\", digits = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "53dbf945",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:00.662217Z",
     "iopub.status.busy": "2026-07-04T19:46:00.662127Z",
     "iopub.status.idle": "2026-07-04T19:46:01.032942Z",
     "shell.execute_reply": "2026-07-04T19:46:01.032560Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(\"Rscript download.r\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cfee76a8",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a8334694",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.034363Z",
     "iopub.status.busy": "2026-07-04T19:46:01.034283Z",
     "iopub.status.idle": "2026-07-04T19:46:01.040414Z",
     "shell.execute_reply": "2026-07-04T19:46:01.039980Z"
    }
   },
   "outputs": [],
   "source": [
    "coef_df = pd.DataFrame(json.load(open('coefficients.json')))\n",
    "model.features = coef_df['CpG'].tolist()\n",
    "iv = json.load(open('intercept.json'))\n",
    "intercept_value = iv[0] if isinstance(iv, list) else iv"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cb23ac70",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "7dac5b06",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.041749Z",
     "iopub.status.busy": "2026-07-04T19:46:01.041674Z",
     "iopub.status.idle": "2026-07-04T19:46:01.043859Z",
     "shell.execute_reply": "2026-07-04T19:46:01.043539Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['coefficient'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6c894382",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.045013Z",
     "iopub.status.busy": "2026-07-04T19:46:01.044937Z",
     "iopub.status.idle": "2026-07-04T19:46:01.046967Z",
     "shell.execute_reply": "2026-07-04T19:46:01.046627Z"
    }
   },
   "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": "fa73a479",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "adc90abc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.048292Z",
     "iopub.status.busy": "2026-07-04T19:46:01.048212Z",
     "iopub.status.idle": "2026-07-04T19:46:01.049570Z",
     "shell.execute_reply": "2026-07-04T19:46:01.049275Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb898eb8",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "cf384da9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.050703Z",
     "iopub.status.busy": "2026-07-04T19:46:01.050642Z",
     "iopub.status.idle": "2026-07-04T19:46:01.052284Z",
     "shell.execute_reply": "2026-07-04T19:46:01.051902Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "94773e69",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.053694Z",
     "iopub.status.busy": "2026-07-04T19:46:01.053596Z",
     "iopub.status.idle": "2026-07-04T19:46:01.055218Z",
     "shell.execute_reply": "2026-07-04T19:46:01.054898Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4419e365",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f4c16793",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.056577Z",
     "iopub.status.busy": "2026-07-04T19:46:01.056501Z",
     "iopub.status.idle": "2026-07-04T19:46:01.059606Z",
     "shell.execute_reply": "2026-07-04T19:46:01.059245Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Lujan, Gabriel M., et al. \"A DNA methylation clock to measure '\n",
      "             'the epigenetic age of cell populations.\" Genome Medicine 16 '\n",
      "             '(2024).',\n",
      " 'clock_name': 'cellpopage',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1186/s13073-024-01349-w',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2024}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg03662648', 'cg07230471', 'cg09689790', 'cg00283934', 'cg27617964', 'cg21734265', 'cg21184340', 'cg17342766', 'cg00312508', 'cg08907118', 'cg12071423', 'cg16622870', 'cg08126590', 'cg04121501', 'cg18571156', 'cg22900075', 'cg26475539', 'cg27500194', 'cg09992376', 'cg26450896', 'cg06863239', 'cg25651783', 'cg08461941', 'cg11738198', 'cg23407476', 'cg01159380', 'cg05369308', 'cg27537795', 'cg15563081', 'cg19920898']... [Total elements: 2543]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=2543, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -0.5474669337272644, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]... [Tensor of shape torch.Size([1, 2543])]\n",
      "base_model.linear.bias: tensor([11.5268])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd0adc7c",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "5d51015a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.060740Z",
     "iopub.status.busy": "2026-07-04T19:46:01.060657Z",
     "iopub.status.idle": "2026-07-04T19:46:01.065577Z",
     "shell.execute_reply": "2026-07-04T19:46:01.065187Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 8.1066],\n",
       "        [21.9362],\n",
       "        [13.3644],\n",
       "        [31.7122],\n",
       "        [30.1219],\n",
       "        [-3.8962],\n",
       "        [ 9.8756],\n",
       "        [-2.5270],\n",
       "        [ 2.6161],\n",
       "        [ 9.8903]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "execution_count": 15,
     "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": "6671255d",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "e8a65c42",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.066911Z",
     "iopub.status.busy": "2026-07-04T19:46:01.066840Z",
     "iopub.status.idle": "2026-07-04T19:46:01.070482Z",
     "shell.execute_reply": "2026-07-04T19:46:01.070088Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9625b988",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "24a38a70",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:01.071814Z",
     "iopub.status.busy": "2026-07-04T19:46:01.071745Z",
     "iopub.status.idle": "2026-07-04T19:46:01.075216Z",
     "shell.execute_reply": "2026-07-04T19:46:01.074829Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: intercept.json\n",
      "Deleted file: download.r\n",
      "Deleted file: coefficients.json\n",
      "Deleted file: CellPopAge_ref.rda\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
}