{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1c464267",
   "metadata": {},
   "source": [
    "# SenCultureAge"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7c79478",
   "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": "75628fcc",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "24ab3e42",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:07.313415Z",
     "iopub.status.busy": "2026-07-04T19:46:07.313237Z",
     "iopub.status.idle": "2026-07-04T19:46:09.238799Z",
     "shell.execute_reply": "2026-07-04T19:46:09.238380Z"
    }
   },
   "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": "bd6ccee5",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e4bf5b46",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.240448Z",
     "iopub.status.busy": "2026-07-04T19:46:09.240267Z",
     "iopub.status.idle": "2026-07-04T19:46:09.242826Z",
     "shell.execute_reply": "2026-07-04T19:46:09.242516Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class SenCultureAge(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.SenCultureAge)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "44305393",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.244027Z",
     "iopub.status.busy": "2026-07-04T19:46:09.243948Z",
     "iopub.status.idle": "2026-07-04T19:46:09.245526Z",
     "shell.execute_reply": "2026-07-04T19:46:09.245180Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.SenCultureAge()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ee9fcee",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ea26bb21",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.246877Z",
     "iopub.status.busy": "2026-07-04T19:46:09.246810Z",
     "iopub.status.idle": "2026-07-04T19:46:09.248773Z",
     "shell.execute_reply": "2026-07-04T19:46:09.248402Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"sencultureage\"\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\"] = \"Binomial elastic-net classifier of in-vitro cellular senescence, trained after ComBat correction on pooled human fibroblast and mesenchymal-stromal-cell datasets and restricted to direction-concordant senescence/age/mortality CpGs.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"cultured fibroblasts\", \"cultured mesenchymal stromal cells\"]  # Paper: Training pooled fibroblasts, diploid skin fibroblasts, bone-marrow MSCs and adipose-derived MSCs.\n",
    "model.metadata[\"predicts\"] = [\"cellular senescence\"]  # Paper: SenCultureAge is a binary senescence predictor.\n",
    "model.metadata[\"training_target\"] = [\"cellular senescence\"]  # Paper: Each in-vitro training sample was labeled senescent or control.\n",
    "model.metadata[\"unit\"] = [\"log odds\"]  # Paper: Pyaging applies the binomial-model coefficients without an inverse-logit postprocess.\n",
    "model.metadata[\"model_type\"] = \"elastic net logistic regression\"  # Paper: The model used glmnet with family binomial and alpha 0.5.\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\"] = \"human cell cultures\"  # Paper: Training pooled GSE197723 and GSE227160 senescent and control cultures.\n",
    "model.metadata[\"journal\"] = \"Aging Cell\"\n",
    "model.metadata[\"last_author\"] = \"Albert T. Higgins-Chen\"\n",
    "model.metadata[\"n_features\"] = 142\n",
    "model.metadata[\"citations\"] = 0\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "77896724",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "58754fb5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.249946Z",
     "iopub.status.busy": "2026-07-04T19:46:09.249880Z",
     "iopub.status.idle": "2026-07-04T19:46:09.527232Z",
     "shell.execute_reply": "2026-07-04T19:46:09.526594Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o SenCultureAge_CpGs.csv https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data-raw/SenescenceAge/SenCultureAge_CpGs.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "35686c23",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0d28c823",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.530404Z",
     "iopub.status.busy": "2026-07-04T19:46:09.530171Z",
     "iopub.status.idle": "2026-07-04T19:46:09.536075Z",
     "shell.execute_reply": "2026-07-04T19:46:09.535155Z"
    }
   },
   "outputs": [],
   "source": [
    "coef_df = pd.read_csv('SenCultureAge_CpGs.csv')\n",
    "model.features = coef_df['CpG'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "808175d6",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e1ef3e63",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.538283Z",
     "iopub.status.busy": "2026-07-04T19:46:09.538088Z",
     "iopub.status.idle": "2026-07-04T19:46:09.541471Z",
     "shell.execute_reply": "2026-07-04T19:46:09.540707Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['Coefficient'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([-254.6817]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8a18febb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.543328Z",
     "iopub.status.busy": "2026-07-04T19:46:09.543200Z",
     "iopub.status.idle": "2026-07-04T19:46:09.546261Z",
     "shell.execute_reply": "2026-07-04T19:46:09.545741Z"
    }
   },
   "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": "3375f499",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "525ac21b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.548401Z",
     "iopub.status.busy": "2026-07-04T19:46:09.548265Z",
     "iopub.status.idle": "2026-07-04T19:46:09.550469Z",
     "shell.execute_reply": "2026-07-04T19:46:09.549937Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ef6dd201",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "231dba63",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.551971Z",
     "iopub.status.busy": "2026-07-04T19:46:09.551856Z",
     "iopub.status.idle": "2026-07-04T19:46:09.553797Z",
     "shell.execute_reply": "2026-07-04T19:46:09.553277Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "76517666",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.555327Z",
     "iopub.status.busy": "2026-07-04T19:46:09.555209Z",
     "iopub.status.idle": "2026-07-04T19:46:09.556946Z",
     "shell.execute_reply": "2026-07-04T19:46:09.556543Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8f6a44cb",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1b6dda5e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.558677Z",
     "iopub.status.busy": "2026-07-04T19:46:09.558565Z",
     "iopub.status.idle": "2026-07-04T19:46:09.562407Z",
     "shell.execute_reply": "2026-07-04T19:46:09.561888Z"
    }
   },
   "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': 'sencultureage',\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: ['cg00127591', 'cg00296189', 'cg00518989', 'cg00666978', 'cg00899883', 'cg01587390', 'cg01779934', 'cg01788025', 'cg02389682', 'cg02484633', 'cg03063057', 'cg03917020', 'cg04081392', 'cg04224041', 'cg04514998', 'cg04796775', 'cg04842828', 'cg05076775', 'cg05198969', 'cg05275153', 'cg06955158', 'cg07166216', 'cg07381973', 'cg07390459', 'cg07528772', 'cg07894586', 'cg07959138', 'cg08155338', 'cg08190044', 'cg08600218']... [Total elements: 142]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=142, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [7.832161903381348, 12.214286804199219, 8.027161598205566, 45.58428192138672, 2.2128779888153076, 3.30290150642395, 3.9877500534057617, 0.7730445265769958, 6.563979625701904, 25.338594436645508, 0.7351537942886353, 2.5286097526550293, 2.230402708053589, 0.2821439504623413, 2.5589730739593506, 9.428633689880371, 21.527307510375977, 35.500648498535156, 2.8819007873535156, 3.544675350189209, 6.508420467376709, 6.3784918785095215, 3.5156803131103516, 14.325957298278809, 1.9541112184524536, -0.49621376395225525, 0.5369631052017212, 8.035040855407715, 10.24377727508545, 0.48844996094703674]... [Tensor of shape torch.Size([1, 142])]\n",
      "base_model.linear.bias: tensor([-254.6817])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1424e10e",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "54ed8eef",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.563990Z",
     "iopub.status.busy": "2026-07-04T19:46:09.563874Z",
     "iopub.status.idle": "2026-07-04T19:46:09.568794Z",
     "shell.execute_reply": "2026-07-04T19:46:09.568421Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[  77.5496],\n",
       "        [-329.8605],\n",
       "        [-197.1059],\n",
       "        [-396.4821],\n",
       "        [-519.2351],\n",
       "        [-122.0558],\n",
       "        [-104.6654],\n",
       "        [-262.1782],\n",
       "        [-182.1105],\n",
       "        [-254.5931]], 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": "6ab494dd",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7b68dbde",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.570393Z",
     "iopub.status.busy": "2026-07-04T19:46:09.570291Z",
     "iopub.status.idle": "2026-07-04T19:46:09.573538Z",
     "shell.execute_reply": "2026-07-04T19:46:09.573128Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e7788c2",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "4dc958f9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:46:09.574851Z",
     "iopub.status.busy": "2026-07-04T19:46:09.574769Z",
     "iopub.status.idle": "2026-07-04T19:46:09.578382Z",
     "shell.execute_reply": "2026-07-04T19:46:09.577941Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: SenCultureAge_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
}