{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f049633",
   "metadata": {},
   "source": [
    "# McCartneyWHR"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e489b066",
   "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": "85073d3d",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "904e837f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:35.602200Z",
     "iopub.status.busy": "2026-07-04T19:26:35.602113Z",
     "iopub.status.idle": "2026-07-04T19:26:37.833821Z",
     "shell.execute_reply": "2026-07-04T19:26:37.833329Z"
    }
   },
   "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": "bad5435e",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3bbed7ed",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:37.835675Z",
     "iopub.status.busy": "2026-07-04T19:26:37.835467Z",
     "iopub.status.idle": "2026-07-04T19:26:37.838181Z",
     "shell.execute_reply": "2026-07-04T19:26:37.837848Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class McCartneyWHR(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.McCartneyWHR)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e3611a69",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:37.839593Z",
     "iopub.status.busy": "2026-07-04T19:26:37.839493Z",
     "iopub.status.idle": "2026-07-04T19:26:37.841189Z",
     "shell.execute_reply": "2026-07-04T19:26:37.840729Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.McCartneyWHR()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "93ef7fbb",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "83d7f31b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:37.842548Z",
     "iopub.status.busy": "2026-07-04T19:26:37.842442Z",
     "iopub.status.idle": "2026-07-04T19:26:37.844707Z",
     "shell.execute_reply": "2026-07-04T19:26:37.844246Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"mccartneywhr\"\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 waist-to-hip 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\"] = [\"waist-to-hip ratio\"]  # Paper: The study developed a DNAm predictor for waist-to-hip ratio.\n",
    "model.metadata[\"training_target\"] = [\"waist-to-hip ratio\"]  # Paper: The waist-to-hip 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\"] = 226\n",
    "model.metadata[\"citations\"] = 301\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e99584dc",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "48ccfb0f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:37.845923Z",
     "iopub.status.busy": "2026-07-04T19:26:37.845822Z",
     "iopub.status.idle": "2026-07-04T19:26:38.064258Z",
     "shell.execute_reply": "2026-07-04T19:26:38.063791Z"
    }
   },
   "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": "2a2d56ff",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "538c921a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.066420Z",
     "iopub.status.busy": "2026-07-04T19:26:38.066287Z",
     "iopub.status.idle": "2026-07-04T19:26:38.158868Z",
     "shell.execute_reply": "2026-07-04T19:26:38.158309Z"
    }
   },
   "outputs": [],
   "source": [
    "# Additional file 1, Table S9 - Waist-to-Hip ratio (McCartney et al. 2018)\n",
    "coef_df = pd.read_excel('mccartney_predictors.xlsx', sheet_name='Table S9 - Waist-to-Hip ratio')\n",
    "model.features = coef_df['CpG'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b08e819d",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "d0df6cda",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.160391Z",
     "iopub.status.busy": "2026-07-04T19:26:38.160308Z",
     "iopub.status.idle": "2026-07-04T19:26:38.162629Z",
     "shell.execute_reply": "2026-07-04T19:26:38.162163Z"
    }
   },
   "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": "c25386fb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.163847Z",
     "iopub.status.busy": "2026-07-04T19:26:38.163769Z",
     "iopub.status.idle": "2026-07-04T19:26:38.165958Z",
     "shell.execute_reply": "2026-07-04T19:26:38.165597Z"
    }
   },
   "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": "dbd88d91",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "6d954324",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.167189Z",
     "iopub.status.busy": "2026-07-04T19:26:38.167108Z",
     "iopub.status.idle": "2026-07-04T19:26:38.168690Z",
     "shell.execute_reply": "2026-07-04T19:26:38.168254Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a412367e",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2a9e673c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.169926Z",
     "iopub.status.busy": "2026-07-04T19:26:38.169841Z",
     "iopub.status.idle": "2026-07-04T19:26:38.171582Z",
     "shell.execute_reply": "2026-07-04T19:26:38.171134Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "0924078e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.172596Z",
     "iopub.status.busy": "2026-07-04T19:26:38.172524Z",
     "iopub.status.idle": "2026-07-04T19:26:38.174089Z",
     "shell.execute_reply": "2026-07-04T19:26:38.173671Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b2a06522",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "6e2333ba",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.175126Z",
     "iopub.status.busy": "2026-07-04T19:26:38.175047Z",
     "iopub.status.idle": "2026-07-04T19:26:38.178121Z",
     "shell.execute_reply": "2026-07-04T19:26:38.177755Z"
    }
   },
   "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': 'mccartneywhr',\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: ['cg03005261', 'cg21637050', 'cg16728516', 'cg14267725', 'cg06500161', 'cg04804648', 'cg18909879', 'cg25921813', 'cg21020089', 'cg16284674', 'cg15092239', 'cg07769588', 'cg07215298', 'cg09249494', 'cg10474597', 'cg11832534', 'cg25110523', 'cg04453364', 'cg19519737', 'cg18515624', 'cg18054578', 'cg18011760', 'cg08563994', 'cg01616956', 'cg02079413', 'cg06192883', 'cg15132749', 'cg22669566', 'cg25349939', 'cg04816311']... [Total elements: 226]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=226, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.47226133942604065, 0.2731764614582062, 0.23187954723834991, 0.20890694856643677, 0.18225495517253876, 0.12761914730072021, 0.08936703205108643, 0.08627176284790039, 0.0851999968290329, 0.07440463453531265, 0.061605945229530334, 0.05795585736632347, 0.053718939423561096, 0.05213217809796333, 0.05174638330936432, 0.04884398728609085, 0.04772736132144928, 0.046122852712869644, 0.04307003319263458, 0.04154041036963463, 0.03536680340766907, 0.03154837712645531, 0.030331037938594818, 0.029633039608597755, 0.02755829133093357, 0.026697693392634392, 0.02443346194922924, 0.023988846689462662, 0.023213393986225128, 0.02202027104794979]... [Tensor of shape torch.Size([1, 226])]\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36ea9c99",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "edf0ac81",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.179269Z",
     "iopub.status.busy": "2026-07-04T19:26:38.179201Z",
     "iopub.status.idle": "2026-07-04T19:26:38.183684Z",
     "shell.execute_reply": "2026-07-04T19:26:38.183205Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 0.9362],\n",
       "        [ 1.4919],\n",
       "        [ 0.3194],\n",
       "        [-0.1748],\n",
       "        [ 0.6122],\n",
       "        [ 0.8324],\n",
       "        [-0.0945],\n",
       "        [-0.4978],\n",
       "        [ 1.0881],\n",
       "        [-0.8827]], 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": "330a77f1",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "476318c7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.184871Z",
     "iopub.status.busy": "2026-07-04T19:26:38.184800Z",
     "iopub.status.idle": "2026-07-04T19:26:38.188425Z",
     "shell.execute_reply": "2026-07-04T19:26:38.188013Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc1ca3bf",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "da3b542a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:26:38.189730Z",
     "iopub.status.busy": "2026-07-04T19:26:38.189651Z",
     "iopub.status.idle": "2026-07-04T19:26:38.192886Z",
     "shell.execute_reply": "2026-07-04T19:26:38.192562Z"
    }
   },
   "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
}