{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8dcf2da8",
   "metadata": {},
   "source": [
    "# McCartneyTotalHDLRatio"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b059f182",
   "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": "1aa2a0ab",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bdc0586b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:28.608178Z",
     "iopub.status.busy": "2026-07-04T19:26:28.606958Z",
     "iopub.status.idle": "2026-07-04T19:26:32.797901Z",
     "shell.execute_reply": "2026-07-04T19:26:32.797421Z"
    }
   },
   "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": "75674269",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3324948f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:32.799674Z",
     "iopub.status.busy": "2026-07-04T19:26:32.799433Z",
     "iopub.status.idle": "2026-07-04T19:26:32.803129Z",
     "shell.execute_reply": "2026-07-04T19:26:32.802662Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class McCartneyTotalHDLRatio(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.McCartneyTotalHDLRatio)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cd056339",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:32.804708Z",
     "iopub.status.busy": "2026-07-04T19:26:32.804603Z",
     "iopub.status.idle": "2026-07-04T19:26:32.806539Z",
     "shell.execute_reply": "2026-07-04T19:26:32.806089Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.McCartneyTotalHDLRatio()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b5f9857",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "612ed553",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:32.807855Z",
     "iopub.status.busy": "2026-07-04T19:26:32.807763Z",
     "iopub.status.idle": "2026-07-04T19:26:32.809884Z",
     "shell.execute_reply": "2026-07-04T19:26:32.809443Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"mccartneytotalhdlratio\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The predictors use DNA methylation states at CpG sites.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: Generation Scotland is a population-based cohort of human participants.\n",
    "model.metadata[\"year\"] = 2018\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"McCartney, D. L., et al. “Epigenetic prediction of complex traits and death.” Genome Biology 19, 136 (2018).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1186/s13059-018-1514-1\"\n",
    "model.metadata[\"notes\"] = \"Whole-blood DNAm LASSO score for total-to-HDL cholesterol ratio, trained in Generation Scotland on an age-, sex-, and ancestry-adjusted phenotype residual and evaluated out of sample in LBC1936.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: Stored DNA from baseline blood samples was used to build the predictors.\n",
    "model.metadata[\"predicts\"] = [\"total-to-HDL cholesterol ratio\"]  # Paper: The study developed a DNAm predictor for total-to-HDL cholesterol ratio.\n",
    "model.metadata[\"training_target\"] = [\"total-to-HDL cholesterol ratio\"]  # Paper: The total-to-HDL cholesterol ratio phenotype was regressed on age, sex and ten genetic principal components; its residual was the LASSO outcome.\n",
    "model.metadata[\"unit\"] = [\"ratio\"]  # Paper: No output transformation is applied; the score retains the dimensionless ratio-residual scale.\n",
    "model.metadata[\"model_type\"] = \"LASSO regression\"  # Paper: The glmnet mixing parameter alpha was set to 1, applying a LASSO penalty with tenfold cross-validation.\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: Predictor training used quality-controlled HumanMethylationEPIC blood data; probes absent from 450K were filtered only to enable LBC1936 prediction.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: The predictors were built on a subset of 5,087 Generation Scotland participants; the parent cohort spans ages 18–99.\n",
    "model.metadata[\"journal\"] = \"Genome Biology\"\n",
    "model.metadata[\"last_author\"] = \"Riccardo E. Marioni\"\n",
    "model.metadata[\"n_features\"] = 412\n",
    "model.metadata[\"citations\"] = 301\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de9c3f78",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d89cefe9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:32.811481Z",
     "iopub.status.busy": "2026-07-04T19:26:32.811363Z",
     "iopub.status.idle": "2026-07-04T19:26:33.204157Z",
     "shell.execute_reply": "2026-07-04T19:26:33.203601Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://static-content.springer.com/esm/art%3A10.1186%2Fs13059-018-1514-1/MediaObjects/13059_2018_1514_MOESM1_ESM.xlsx\"\n",
    "supplementary_file_name = \"mccartney_predictors.xlsx\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ce3afcd3",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d788f48b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.205371Z",
     "iopub.status.busy": "2026-07-04T19:26:33.205281Z",
     "iopub.status.idle": "2026-07-04T19:26:33.361405Z",
     "shell.execute_reply": "2026-07-04T19:26:33.360808Z"
    }
   },
   "outputs": [],
   "source": [
    "# Additional file 1, Table S8 - Total-HDL ratio (McCartney et al. 2018)\n",
    "coef_df = pd.read_excel('mccartney_predictors.xlsx', sheet_name='Table S8 - Total-HDL ratio')\n",
    "model.features = coef_df['CpG'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ea408b14",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c1cbe9ab",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.362813Z",
     "iopub.status.busy": "2026-07-04T19:26:33.362723Z",
     "iopub.status.idle": "2026-07-04T19:26:33.369802Z",
     "shell.execute_reply": "2026-07-04T19:26:33.369239Z"
    }
   },
   "outputs": [],
   "source": [
    "# The penalised (LASSO) predictor has no intercept term\n",
    "weights = torch.tensor(coef_df['Beta'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([0.0]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ea706b57",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.371358Z",
     "iopub.status.busy": "2026-07-04T19:26:33.371247Z",
     "iopub.status.idle": "2026-07-04T19:26:33.376618Z",
     "shell.execute_reply": "2026-07-04T19:26:33.376125Z"
    }
   },
   "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": "f49e5648",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "203cd580",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.378204Z",
     "iopub.status.busy": "2026-07-04T19:26:33.378097Z",
     "iopub.status.idle": "2026-07-04T19:26:33.380049Z",
     "shell.execute_reply": "2026-07-04T19:26:33.379619Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "274e41de",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2dfdd2fd",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.382363Z",
     "iopub.status.busy": "2026-07-04T19:26:33.382222Z",
     "iopub.status.idle": "2026-07-04T19:26:33.383938Z",
     "shell.execute_reply": "2026-07-04T19:26:33.383519Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "50d76ad9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.385087Z",
     "iopub.status.busy": "2026-07-04T19:26:33.385013Z",
     "iopub.status.idle": "2026-07-04T19:26:33.386987Z",
     "shell.execute_reply": "2026-07-04T19:26:33.386505Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c140f14c",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "513c1a26",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.388289Z",
     "iopub.status.busy": "2026-07-04T19:26:33.388209Z",
     "iopub.status.idle": "2026-07-04T19:26:33.403317Z",
     "shell.execute_reply": "2026-07-04T19:26:33.402926Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'McCartney, Daniel L., et al. \"Epigenetic prediction of complex '\n",
      "             'traits and death.\" Genome biology 19.1 (2018): 136.',\n",
      " 'clock_name': 'mccartneytotalhdlratio',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1186/s13059-018-1514-1',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2018}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg24576270', 'cg25158622', 'cg06500161', 'cg26033520', 'cg18615457', 'cg10993470', 'cg19250790', 'cg09177238', 'cg22813794', 'cg01511534', 'cg01559436', 'cg22488164', 'cg05391946', 'cg09503194', 'cg14697880', 'cg06136443', 'cg14545305', 'cg26955383', 'cg26800462', 'cg08854185', 'cg14891022', 'cg23719318', 'cg12332083', 'cg02150767', 'cg08864105', 'cg11770080', 'cg12422930', 'cg06898549', 'cg03546163', 'cg26245667']... [Total elements: 412]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=412, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [16.199861526489258, 1.5791822671890259, 1.3397550582885742, 1.2062699794769287, 1.1696120500564575, 1.1656070947647095, 1.0623283386230469, 0.9755944609642029, 0.9740409851074219, 0.9441574811935425, 0.8715856671333313, 0.8420827984809875, 0.8233152627944946, 0.8100341558456421, 0.7970923781394958, 0.7889676690101624, 0.7783008217811584, 0.7704609632492065, 0.7500393986701965, 0.7299103736877441, 0.7206714153289795, 0.6958703994750977, 0.6573514342308044, 0.6428144574165344, 0.637154221534729, 0.6069923043251038, 0.600265383720398, 0.5983773469924927, 0.5772433876991272, 0.5692275166511536]... [Tensor of shape torch.Size([1, 412])]\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5897924e",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "2676cde5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.404694Z",
     "iopub.status.busy": "2026-07-04T19:26:33.404602Z",
     "iopub.status.idle": "2026-07-04T19:26:33.422273Z",
     "shell.execute_reply": "2026-07-04T19:26:33.421879Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 17.9949],\n",
       "        [ -3.0065],\n",
       "        [-38.9142],\n",
       "        [  1.3466],\n",
       "        [  9.2999],\n",
       "        [  5.4597],\n",
       "        [ 14.3734],\n",
       "        [ -9.2779],\n",
       "        [ -9.3156],\n",
       "        [-27.2043]], 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": "96600ffc",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "cfbede23",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.423648Z",
     "iopub.status.busy": "2026-07-04T19:26:33.423558Z",
     "iopub.status.idle": "2026-07-04T19:26:33.428839Z",
     "shell.execute_reply": "2026-07-04T19:26:33.428242Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5764882c",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "3c1cb37b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:33.430461Z",
     "iopub.status.busy": "2026-07-04T19:26:33.430314Z",
     "iopub.status.idle": "2026-07-04T19:26:33.434239Z",
     "shell.execute_reply": "2026-07-04T19:26:33.433753Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: mccartney_predictors.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
}