{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0ffcfb02",
   "metadata": {},
   "source": [
    "# ADBahadoSingh"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f7d79fb",
   "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": "9a7dfb8c",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2fed02ab",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:23.516525Z",
     "iopub.status.busy": "2026-07-04T20:25:23.516388Z",
     "iopub.status.idle": "2026-07-04T20:25:26.060894Z",
     "shell.execute_reply": "2026-07-04T20:25:26.060447Z"
    }
   },
   "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": "e57c051e",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0b7ec122",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.062543Z",
     "iopub.status.busy": "2026-07-04T20:25:26.062344Z",
     "iopub.status.idle": "2026-07-04T20:25:26.066252Z",
     "shell.execute_reply": "2026-07-04T20:25:26.065457Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class ADBahadoSingh(LinearReferenceClock):\n",
      "    def postprocess(self, x):\n",
      "        \"\"\"Logistic transform to an Alzheimer's disease risk probability.\n",
      "\n",
      "        The published logit constant (-0.072) is carried in the linear intercept.\n",
      "        \"\"\"\n",
      "        return torch.sigmoid(x)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.ADBahadoSingh)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f419d49e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.068511Z",
     "iopub.status.busy": "2026-07-04T20:25:26.068372Z",
     "iopub.status.idle": "2026-07-04T20:25:26.070387Z",
     "shell.execute_reply": "2026-07-04T20:25:26.070016Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.ADBahadoSingh()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a7d830f3",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "3192412b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.071716Z",
     "iopub.status.busy": "2026-07-04T20:25:26.071645Z",
     "iopub.status.idle": "2026-07-04T20:25:26.073738Z",
     "shell.execute_reply": "2026-07-04T20:25:26.073337Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"adbahadosingh\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: Genome-wide DNA methylation analysis\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: 24 late-onset AD and 24 cognitively healthy subjects\n",
    "model.metadata[\"year\"] = 2021\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Bahado-Singh, R. O., Vishweswaraiah, S., Aydas, B., et al. (2021). Artificial intelligence and leukocyte epigenomics: Evaluation and prediction of late-onset Alzheimer's disease. PLOS ONE, 16(4), e0248375.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1371/journal.pone.0248375\"\n",
    "model.metadata[\"notes\"] = \"PyAging implements the paper’s conventional four-CpG logistic-regression equation and applies a sigmoid to return LOAD case probability; it does not implement the separate high-dimensional deep-learning classifiers also evaluated in the paper.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: Genomic DNA was extracted from whole blood samples; leukocyte epigenomic biomarkers\n",
    "model.metadata[\"predicts\"] = [\"late-onset Alzheimer's disease\"]  # Paper: where P is Pr(y = 1|x)\n",
    "model.metadata[\"training_target\"] = [\"late-onset Alzheimer's disease\"]  # Paper: 24 late-onset AD and 24 cognitively healthy subjects\n",
    "model.metadata[\"unit\"] = [\"probability\"]  # Paper: return torch.sigmoid(x)\n",
    "model.metadata[\"model_type\"] = \"logistic regression\"  # Paper: The logistic regression model is represented below\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: Infinium MethylationEPIC array in 24 LOAD and 24 healthy subjects\n",
    "model.metadata[\"population\"] = \"older adults\"  # Paper: Cases: 83.17 (7.97); Controls: 80.04 (8.42)\n",
    "model.metadata[\"journal\"] = \"PLOS ONE\"\n",
    "model.metadata[\"last_author\"] = \"Uppala Radhakrishna\"\n",
    "model.metadata[\"n_features\"] = 4\n",
    "model.metadata[\"citations\"] = 33\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "83246005",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "182bc2c1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.074885Z",
     "iopub.status.busy": "2026-07-04T20:25:26.074814Z",
     "iopub.status.idle": "2026-07-04T20:25:26.345655Z",
     "shell.execute_reply": "2026-07-04T20:25:26.343440Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o coefficients.csv https://raw.githubusercontent.com/bio-learn/biolearn/180852e2bab473303cb85da627178b1695ee9d86/biolearn/data/AD_Bahado-Singh.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a9680f0",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d4699f05",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.350516Z",
     "iopub.status.busy": "2026-07-04T20:25:26.350127Z",
     "iopub.status.idle": "2026-07-04T20:25:26.359398Z",
     "shell.execute_reply": "2026-07-04T20:25:26.358217Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('coefficients.csv')\n",
    "mask = df['CpGmarker'].astype(str).str.lower().isin(['intercept', '(intercept)'])\n",
    "coef_df = df.loc[~mask].reset_index(drop=True)\n",
    "model.features = coef_df['CpGmarker'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "123e9bba",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e268eb33",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.362892Z",
     "iopub.status.busy": "2026-07-04T20:25:26.362583Z",
     "iopub.status.idle": "2026-07-04T20:25:26.366289Z",
     "shell.execute_reply": "2026-07-04T20:25:26.365442Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['CoefficientTraining'].tolist()).unsqueeze(0).float()\n",
    "# Published logistic-regression constant (Bahado-Singh 2021, eq. e001)\n",
    "intercept = torch.tensor([-0.072]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "319ef876",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.368300Z",
     "iopub.status.busy": "2026-07-04T20:25:26.368187Z",
     "iopub.status.idle": "2026-07-04T20:25:26.370906Z",
     "shell.execute_reply": "2026-07-04T20:25:26.370469Z"
    }
   },
   "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": "9e022528",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "8c128c95",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.372269Z",
     "iopub.status.busy": "2026-07-04T20:25:26.372195Z",
     "iopub.status.idle": "2026-07-04T20:25:26.373829Z",
     "shell.execute_reply": "2026-07-04T20:25:26.373491Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "398afb53",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c91c6c17",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.375177Z",
     "iopub.status.busy": "2026-07-04T20:25:26.375079Z",
     "iopub.status.idle": "2026-07-04T20:25:26.376723Z",
     "shell.execute_reply": "2026-07-04T20:25:26.376259Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "34369a68",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.377825Z",
     "iopub.status.busy": "2026-07-04T20:25:26.377750Z",
     "iopub.status.idle": "2026-07-04T20:25:26.379437Z",
     "shell.execute_reply": "2026-07-04T20:25:26.378962Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'sigmoid'\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ff8801c7",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "34823472",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.383261Z",
     "iopub.status.busy": "2026-07-04T20:25:26.382974Z",
     "iopub.status.idle": "2026-07-04T20:25:26.390843Z",
     "shell.execute_reply": "2026-07-04T20:25:26.390123Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Bahado-Singh, Ray O., et al. \"Artificial intelligence and '\n",
      "             'leukocyte epigenomics: Evaluation and prediction of late-onset '\n",
      "             'Alzheimer\\'s disease.\" PLOS ONE 16.4 (2021): e0248375.',\n",
      " 'clock_name': 'adbahadosingh',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1371/journal.pone.0248375',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2021}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'sigmoid'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg02356786', 'cg04515524', 'cg00613827', 'cg07509935']\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=4, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[-0.9920, -1.5000, -1.9010, -1.3580]])\n",
      "base_model.linear.bias: tensor([-0.0720])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd46c341",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "1f86769b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.392620Z",
     "iopub.status.busy": "2026-07-04T20:25:26.392500Z",
     "iopub.status.idle": "2026-07-04T20:25:26.397490Z",
     "shell.execute_reply": "2026-07-04T20:25:26.396912Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[0.2779],\n",
       "        [0.9795],\n",
       "        [0.1451],\n",
       "        [0.7133],\n",
       "        [0.0025],\n",
       "        [0.1557],\n",
       "        [0.9681],\n",
       "        [0.7552],\n",
       "        [0.9825],\n",
       "        [0.5411]], dtype=torch.float64, grad_fn=<SigmoidBackward0>)"
      ]
     },
     "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": "db3d55f5",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "afc5f9b7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.399340Z",
     "iopub.status.busy": "2026-07-04T20:25:26.399216Z",
     "iopub.status.idle": "2026-07-04T20:25:26.403718Z",
     "shell.execute_reply": "2026-07-04T20:25:26.403323Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "620bbb0b",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "77fd8481",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:25:26.405201Z",
     "iopub.status.busy": "2026-07-04T20:25:26.405118Z",
     "iopub.status.idle": "2026-07-04T20:25:26.408698Z",
     "shell.execute_reply": "2026-07-04T20:25:26.408230Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: coefficients.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
}