{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "539a5b53",
   "metadata": {},
   "source": [
    "# McCartneyAlcohol"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "97fb0a27",
   "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": "4fd72f26",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "5ef5fbe0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:41.810213Z",
     "iopub.status.busy": "2026-07-04T19:10:41.809920Z",
     "iopub.status.idle": "2026-07-04T19:10:47.260983Z",
     "shell.execute_reply": "2026-07-04T19:10:47.259455Z"
    }
   },
   "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": "205370f7",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f2216aa5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:47.264687Z",
     "iopub.status.busy": "2026-07-04T19:10:47.264293Z",
     "iopub.status.idle": "2026-07-04T19:10:47.269795Z",
     "shell.execute_reply": "2026-07-04T19:10:47.268885Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class McCartneyAlcohol(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        if self.reference_values is None:\n",
      "            return x\n",
      "        if isinstance(self.reference_values, torch.Tensor):\n",
      "            reference = self.reference_values.to(device=x.device, dtype=x.dtype)\n",
      "        else:\n",
      "            reference = torch.tensor(self.reference_values, device=x.device, dtype=x.dtype)\n",
      "        return torch.where(torch.isnan(x), reference, x)\n",
      "\n",
      "    def postprocess(self, x):\n",
      "        return x\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.McCartneyAlcohol)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e66011d2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:47.273368Z",
     "iopub.status.busy": "2026-07-04T19:10:47.273100Z",
     "iopub.status.idle": "2026-07-04T19:10:47.277387Z",
     "shell.execute_reply": "2026-07-04T19:10:47.276165Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.McCartneyAlcohol()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a21d2c60",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4f2e25da",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:47.280572Z",
     "iopub.status.busy": "2026-07-04T19:10:47.280332Z",
     "iopub.status.idle": "2026-07-04T19:10:47.285854Z",
     "shell.execute_reply": "2026-07-04T19:10:47.284653Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"mccartneyalcohol\"\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 alcohol consumption, 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\"] = [\"alcohol consumption\"]  # Paper: The study developed a DNAm predictor for alcohol consumption.\n",
    "model.metadata[\"training_target\"] = [\"alcohol consumption\"]  # Paper: The alcohol consumption phenotype was regressed on age, sex and ten genetic principal components; its residual was the LASSO outcome.\n",
    "model.metadata[\"unit\"] = [\"units per week\"]  # Paper: No output transformation is applied; the score retains the residual's units-per-week 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\"] = 450\n",
    "model.metadata[\"citations\"] = 301\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "71976082",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2daab0ce",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:47.289175Z",
     "iopub.status.busy": "2026-07-04T19:10:47.288861Z",
     "iopub.status.idle": "2026-07-04T19:10:47.757882Z",
     "shell.execute_reply": "2026-07-04T19:10:47.756140Z"
    }
   },
   "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": "3b4aabe3",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "94c4d7e5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:47.760782Z",
     "iopub.status.busy": "2026-07-04T19:10:47.760579Z",
     "iopub.status.idle": "2026-07-04T19:10:48.007876Z",
     "shell.execute_reply": "2026-07-04T19:10:48.006978Z"
    }
   },
   "outputs": [],
   "source": [
    "# Additional file 1, Table S3 - Alcohol (McCartney et al. 2018)\n",
    "coef_df = pd.read_excel('mccartney_predictors.xlsx', sheet_name='Table S3 - Alcohol')\n",
    "model.features = coef_df['CpG'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6e545546",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2f895ef3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.010164Z",
     "iopub.status.busy": "2026-07-04T19:10:48.009956Z",
     "iopub.status.idle": "2026-07-04T19:10:48.014051Z",
     "shell.execute_reply": "2026-07-04T19:10:48.012738Z"
    }
   },
   "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": "f541eb0d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.018314Z",
     "iopub.status.busy": "2026-07-04T19:10:48.017658Z",
     "iopub.status.idle": "2026-07-04T19:10:48.023798Z",
     "shell.execute_reply": "2026-07-04T19:10:48.022961Z"
    }
   },
   "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": "dfd56006",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "4aef2faa",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.026019Z",
     "iopub.status.busy": "2026-07-04T19:10:48.025839Z",
     "iopub.status.idle": "2026-07-04T19:10:48.028576Z",
     "shell.execute_reply": "2026-07-04T19:10:48.027629Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "841edecc",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a9973413",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.031380Z",
     "iopub.status.busy": "2026-07-04T19:10:48.031190Z",
     "iopub.status.idle": "2026-07-04T19:10:48.034004Z",
     "shell.execute_reply": "2026-07-04T19:10:48.032843Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ad20d35e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.037929Z",
     "iopub.status.busy": "2026-07-04T19:10:48.037531Z",
     "iopub.status.idle": "2026-07-04T19:10:48.041406Z",
     "shell.execute_reply": "2026-07-04T19:10:48.040310Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd897ae9",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "c9e624da",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.043707Z",
     "iopub.status.busy": "2026-07-04T19:10:48.043487Z",
     "iopub.status.idle": "2026-07-04T19:10:48.051092Z",
     "shell.execute_reply": "2026-07-04T19:10:48.049872Z"
    }
   },
   "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': 'mccartneyalcohol',\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: ['cg16113793', 'cg15970375', 'cg16057915', 'cg01503881', 'cg02650017', 'cg08174504', 'cg19613400', 'cg15537269', 'cg08033031', 'cg27078522', 'cg15804767', 'cg27118035', 'cg03440556', 'cg05926784', 'cg24011637', 'cg25215890', 'cg16298547', 'cg05322916', 'cg10785793', 'cg15348839', 'cg20060185', 'cg10747118', 'cg02402946', 'cg00107782', 'cg17301216', 'cg22857025', 'cg27020362', 'cg26516004', 'cg21376883', 'cg13215995']... [Total elements: 450]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=450, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [3.862548351287842, 2.5282623767852783, 2.1660773754119873, 1.7681397199630737, 1.6551880836486816, 1.3851169347763062, 1.1948226690292358, 1.0830217599868774, 0.9930517077445984, 0.9852260947227478, 0.9295053482055664, 0.9087173342704773, 0.7987855672836304, 0.7958981990814209, 0.7665864825248718, 0.7589118480682373, 0.7468999624252319, 0.6992080807685852, 0.6736985445022583, 0.6460532546043396, 0.6401790380477905, 0.6225373148918152, 0.5754739046096802, 0.5703202486038208, 0.5235690474510193, 0.5012584924697876, 0.4931233823299408, 0.49302104115486145, 0.49224457144737244, 0.48730146884918213]... [Tensor of shape torch.Size([1, 450])]\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0ac57dcd",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "8c5bd728",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.054209Z",
     "iopub.status.busy": "2026-07-04T19:10:48.053838Z",
     "iopub.status.idle": "2026-07-04T19:10:48.066163Z",
     "shell.execute_reply": "2026-07-04T19:10:48.065403Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[  2.0260],\n",
       "        [ -7.1355],\n",
       "        [ 13.1317],\n",
       "        [ 23.1027],\n",
       "        [  8.5896],\n",
       "        [ 17.2480],\n",
       "        [  7.9061],\n",
       "        [-11.0824],\n",
       "        [ -4.6274],\n",
       "        [ -4.5061]], 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": "93c2ec51",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "13d0dd7e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.070878Z",
     "iopub.status.busy": "2026-07-04T19:10:48.070541Z",
     "iopub.status.idle": "2026-07-04T19:10:48.080112Z",
     "shell.execute_reply": "2026-07-04T19:10:48.078937Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7d36df3c",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "a50b5cf7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:10:48.084413Z",
     "iopub.status.busy": "2026-07-04T19:10:48.083927Z",
     "iopub.status.idle": "2026-07-04T19:10:48.093803Z",
     "shell.execute_reply": "2026-07-04T19:10:48.092303Z"
    }
   },
   "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
}