{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "57deffdc",
   "metadata": {},
   "source": [
    "# SenChronoAge"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a68ee91",
   "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": "8be737ca",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a99f7596",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:02.985821Z",
     "iopub.status.busy": "2026-07-04T19:46:02.985633Z",
     "iopub.status.idle": "2026-07-04T19:46:05.086019Z",
     "shell.execute_reply": "2026-07-04T19:46:05.085533Z"
    }
   },
   "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": "0b6ff41c",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e91f870c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.087732Z",
     "iopub.status.busy": "2026-07-04T19:46:05.087566Z",
     "iopub.status.idle": "2026-07-04T19:46:05.090266Z",
     "shell.execute_reply": "2026-07-04T19:46:05.089849Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class SenChronoAge(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.SenChronoAge)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b15d83dc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.091489Z",
     "iopub.status.busy": "2026-07-04T19:46:05.091388Z",
     "iopub.status.idle": "2026-07-04T19:46:05.093054Z",
     "shell.execute_reply": "2026-07-04T19:46:05.092657Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.SenChronoAge()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6182e7d6",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cc122626",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.094341Z",
     "iopub.status.busy": "2026-07-04T19:46:05.094250Z",
     "iopub.status.idle": "2026-07-04T19:46:05.096371Z",
     "shell.execute_reply": "2026-07-04T19:46:05.095989Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"senchronoage\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The predictors use CpG DNA-methylation beta values.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: All three assigned predictors were developed from human cell or human whole-blood datasets.\n",
    "model.metadata[\"year\"] = 2026\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Kasamoto, K., Gibson, J., Moqri, M., Smith, R. & Higgins-Chen, A.T. DNA methylation signatures of cellular senescence are not reversed by senolytic treatment. Aging Cell 25, e70430 (2026).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1111/acel.70430\"\n",
    "model.metadata[\"notes\"] = \"Senescence-enriched chronological-age predictor restricted to CpGs whose directions were concordant across in-vitro senescence, age and mortality analyses.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: SenChronoAge was trained in GSE40279 whole blood.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: SenChronoAge is the chronological-age predictor among the three clocks.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: The model was trained against chronological age.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: The chronological-age regression output is on the age scale in years.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: SenChronoAge used glmnet elastic-net regression with ten-fold cross-validation.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\", \"Illumina EPIC\"]  # Paper: Feature discovery and predictor training used human 450K and EPIC methylation datasets.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: GSE40279 contains 656 participants aged 19–101.\n",
    "model.metadata[\"journal\"] = \"Aging Cell\"\n",
    "model.metadata[\"last_author\"] = \"Albert T. Higgins-Chen\"\n",
    "model.metadata[\"n_features\"] = 187\n",
    "model.metadata[\"citations\"] = 0\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1ca68404",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "602e8cb7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.097543Z",
     "iopub.status.busy": "2026-07-04T19:46:05.097477Z",
     "iopub.status.idle": "2026-07-04T19:46:05.380287Z",
     "shell.execute_reply": "2026-07-04T19:46:05.379846Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o SenChronoAge_CpGs.csv https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data-raw/SenescenceAge/SenChronoAge_CpGs.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "38c3a070",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "bb6ec3a5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.381742Z",
     "iopub.status.busy": "2026-07-04T19:46:05.381629Z",
     "iopub.status.idle": "2026-07-04T19:46:05.386691Z",
     "shell.execute_reply": "2026-07-04T19:46:05.386214Z"
    }
   },
   "outputs": [],
   "source": [
    "coef_df = pd.read_csv('SenChronoAge_CpGs.csv')\n",
    "model.features = coef_df['CpG'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "503fc7fb",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "21d20545",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.387853Z",
     "iopub.status.busy": "2026-07-04T19:46:05.387779Z",
     "iopub.status.idle": "2026-07-04T19:46:05.389899Z",
     "shell.execute_reply": "2026-07-04T19:46:05.389455Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['Coefficient'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([-80.0532]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "5e90666e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.391061Z",
     "iopub.status.busy": "2026-07-04T19:46:05.390989Z",
     "iopub.status.idle": "2026-07-04T19:46:05.393027Z",
     "shell.execute_reply": "2026-07-04T19:46:05.392667Z"
    }
   },
   "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": "e2d7ca5c",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "0c62b584",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.394465Z",
     "iopub.status.busy": "2026-07-04T19:46:05.394373Z",
     "iopub.status.idle": "2026-07-04T19:46:05.395979Z",
     "shell.execute_reply": "2026-07-04T19:46:05.395661Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e4ef430",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d776def2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.397178Z",
     "iopub.status.busy": "2026-07-04T19:46:05.397113Z",
     "iopub.status.idle": "2026-07-04T19:46:05.398706Z",
     "shell.execute_reply": "2026-07-04T19:46:05.398306Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "cb2eec57",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.399897Z",
     "iopub.status.busy": "2026-07-04T19:46:05.399822Z",
     "iopub.status.idle": "2026-07-04T19:46:05.401416Z",
     "shell.execute_reply": "2026-07-04T19:46:05.401083Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59da477a",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ac044512",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.402537Z",
     "iopub.status.busy": "2026-07-04T19:46:05.402461Z",
     "iopub.status.idle": "2026-07-04T19:46:05.405630Z",
     "shell.execute_reply": "2026-07-04T19:46:05.405266Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Kasamoto, Kotaro, et al. \"DNA methylation clocks for estimating '\n",
      "             'replicative senescence in human cells.\" Aging Cell (2026): '\n",
      "             'e70430.',\n",
      " 'clock_name': 'senchronoage',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1111/acel.70430',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2026}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00210473', 'cg00254017', 'cg00296652', 'cg00602326', 'cg00922748', 'cg00964103', 'cg01013171', 'cg01079407', 'cg01141812', 'cg01196788', 'cg01249187', 'cg01263575', 'cg01302656', 'cg01654770', 'cg01675158', 'cg01769968', 'cg01987776', 'cg02716556', 'cg02796545', 'cg03649284', 'cg03660134', 'cg04094193', 'cg04270048', 'cg04432128', 'cg04503600', 'cg04597312', 'cg04840739', 'cg04912316', 'cg05530568', 'cg05818515']... [Total elements: 187]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=187, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [9.502220153808594, -10.09235954284668, -7.13555383682251, 7.0440497398376465, 0.07385352998971939, 4.94988489151001, 3.2296602725982666, -0.23233868181705475, 13.087000846862793, 6.111741065979004, 3.240180492401123, -5.130921840667725, 5.639341354370117, 4.501803398132324, 0.6832999587059021, -0.25918036699295044, 4.322950839996338, 18.638635635375977, 3.3074159622192383, 5.428537845611572, -0.6449773907661438, 5.176876068115234, 1.967892050743103, 5.64846658706665, -0.2769940495491028, 3.7448530197143555, 7.980226039886475, 3.951530694961548, 12.726526260375977, -9.475204467773438]... [Tensor of shape torch.Size([1, 187])]\n",
      "base_model.linear.bias: tensor([-80.0532])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "83683886",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "3c8a58e0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.406830Z",
     "iopub.status.busy": "2026-07-04T19:46:05.406762Z",
     "iopub.status.idle": "2026-07-04T19:46:05.410369Z",
     "shell.execute_reply": "2026-07-04T19:46:05.410090Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ -54.5464],\n",
       "        [-218.2588],\n",
       "        [ 143.5234],\n",
       "        [-101.8496],\n",
       "        [-296.5361],\n",
       "        [-180.5059],\n",
       "        [-193.5961],\n",
       "        [-180.5310],\n",
       "        [ -16.9680],\n",
       "        [  65.8968]], 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": "593b65d0",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "2714b647",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.411704Z",
     "iopub.status.busy": "2026-07-04T19:46:05.411633Z",
     "iopub.status.idle": "2026-07-04T19:46:05.414454Z",
     "shell.execute_reply": "2026-07-04T19:46:05.414157Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6ac2ffdc",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "2ab855c3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:05.416110Z",
     "iopub.status.busy": "2026-07-04T19:46:05.416026Z",
     "iopub.status.idle": "2026-07-04T19:46:05.419297Z",
     "shell.execute_reply": "2026-07-04T19:46:05.418935Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: SenChronoAge_CpGs.csv\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
}