{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e58b07ae",
   "metadata": {},
   "source": [
    "# DepressionBarbu"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a5b2dfff",
   "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": "42cecc19",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bfee4ece",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:46.229738Z",
     "iopub.status.busy": "2026-07-04T20:00:46.229459Z",
     "iopub.status.idle": "2026-07-04T20:00:49.765438Z",
     "shell.execute_reply": "2026-07-04T20:00:49.764986Z"
    }
   },
   "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": "e368d8d0",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f15496a1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:49.767636Z",
     "iopub.status.busy": "2026-07-04T20:00:49.767354Z",
     "iopub.status.idle": "2026-07-04T20:00:49.770430Z",
     "shell.execute_reply": "2026-07-04T20:00:49.770010Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class DepressionBarbu(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        return 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.DepressionBarbu)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "81dd476a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:49.771697Z",
     "iopub.status.busy": "2026-07-04T20:00:49.771614Z",
     "iopub.status.idle": "2026-07-04T20:00:49.773340Z",
     "shell.execute_reply": "2026-07-04T20:00:49.772952Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.DepressionBarbu()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "34e56746",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "82fe3ca8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:49.774676Z",
     "iopub.status.busy": "2026-07-04T20:00:49.774569Z",
     "iopub.status.idle": "2026-07-04T20:00:49.776834Z",
     "shell.execute_reply": "2026-07-04T20:00:49.776372Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"depressionbarbu\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The model is based on DNA methylation measurements.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The study samples are Homo sapiens.\n",
    "model.metadata[\"year\"] = 2021\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Barbu, Miruna C., et al. \\\"Epigenetic prediction of major depressive disorder.\\\" Molecular Psychiatry 26.9 (2021): 5112-5123.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s41380-020-0808-3\"\n",
    "model.metadata[\"notes\"] = \"Blood methylation risk score for major depressive disorder built with penalised regression on genome-wide EPIC-array CpGs, trained on over 1,200 cases and 1,800 controls. Discriminates prevalent from incident MDD independently of polygenic risk, with a smoking-independent variant also derived.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\"]  # Paper: The listed tissue is the model-development sample material.\n",
    "model.metadata[\"predicts\"] = [\"major depressive disorder\"]  # Paper: The reported predictor output is major depressive disorder (MDD) status/risk.\n",
    "model.metadata[\"training_target\"] = [\"major depressive disorder\"]  # Paper: The fitting outcome is major depressive disorder (MDD) status/risk.\n",
    "model.metadata[\"unit\"] = [\"unitless\"]  # Paper: The returned construct is expressed as score (arbitrary).\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: The clock was fitted using Elastic net.\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: Training/selection used Illumina EPIC.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: adults (Generation Scotland cohort)\n",
    "model.metadata[\"journal\"] = \"Molecular Psychiatry\"\n",
    "model.metadata[\"last_author\"] = \"Andrew M. McIntosh\"\n",
    "model.metadata[\"n_features\"] = 196\n",
    "model.metadata[\"citations\"] = 93\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5e4d5532",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a42a7858",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:49.778064Z",
     "iopub.status.busy": "2026-07-04T20:00:49.777968Z",
     "iopub.status.idle": "2026-07-04T20:00:49.993181Z",
     "shell.execute_reply": "2026-07-04T20:00:49.992441Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o depressionbarbu.xlsx https://static-content.springer.com/esm/art%3A10.1038%2Fs41380-020-0808-3/MediaObjects/41380_2020_808_MOESM4_ESM.xlsx\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ad1b660",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "416a8640",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:49.994772Z",
     "iopub.status.busy": "2026-07-04T20:00:49.994633Z",
     "iopub.status.idle": "2026-07-04T20:00:50.099976Z",
     "shell.execute_reply": "2026-07-04T20:00:50.099045Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_excel('depressionbarbu.xlsx', sheet_name='MRS - CpG sites and weights')\n",
    "model.features = df['CpG site'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d99f553",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e934cab8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.101935Z",
     "iopub.status.busy": "2026-07-04T20:00:50.101819Z",
     "iopub.status.idle": "2026-07-04T20:00:50.108965Z",
     "shell.execute_reply": "2026-07-04T20:00:50.108074Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['Beta'].tolist()).unsqueeze(0).float()\n",
    "# Methylation risk score calibration intercept\n",
    "intercept = torch.tensor([12.2169841]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a597cfd9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.110269Z",
     "iopub.status.busy": "2026-07-04T20:00:50.110176Z",
     "iopub.status.idle": "2026-07-04T20:00:50.115858Z",
     "shell.execute_reply": "2026-07-04T20:00:50.115359Z"
    }
   },
   "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": "d21caa34",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9ab1c357",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.117544Z",
     "iopub.status.busy": "2026-07-04T20:00:50.117437Z",
     "iopub.status.idle": "2026-07-04T20:00:50.119228Z",
     "shell.execute_reply": "2026-07-04T20:00:50.118807Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba0650a3",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a5ee3961",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.120331Z",
     "iopub.status.busy": "2026-07-04T20:00:50.120262Z",
     "iopub.status.idle": "2026-07-04T20:00:50.121879Z",
     "shell.execute_reply": "2026-07-04T20:00:50.121512Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "afd51b7b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.123050Z",
     "iopub.status.busy": "2026-07-04T20:00:50.122968Z",
     "iopub.status.idle": "2026-07-04T20:00:50.124660Z",
     "shell.execute_reply": "2026-07-04T20:00:50.124250Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d17ce2cd",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "5757450e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.125753Z",
     "iopub.status.busy": "2026-07-04T20:00:50.125691Z",
     "iopub.status.idle": "2026-07-04T20:00:50.145562Z",
     "shell.execute_reply": "2026-07-04T20:00:50.145102Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Barbu, Miruna C., et al. \"Epigenetic prediction of major '\n",
      "             'depressive disorder.\" Molecular Psychiatry 26.9 (2021): '\n",
      "             '5112-5123.',\n",
      " 'clock_name': 'depressionbarbu',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s41380-020-0808-3',\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: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg02115394', 'cg15971980', 'cg03054303', 'cg09791621', 'cg12736206', 'cg22225420', 'cg22407822', 'cg02998018', 'cg07459409', 'cg20496693', 'cg15251779', 'cg03070922', 'cg04142555', 'cg18090197', 'cg14728380', 'cg09929180', 'cg13529291', 'cg19474047', 'cg04191989', 'cg03607825', 'cg05575921', 'cg03307749', 'cg12832498', 'cg10623600', 'cg15847996', 'cg25242471', 'cg10928544', 'cg02636222', 'cg08464831', 'cg15586193']... [Total elements: 196]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=196, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.13174669444561005, 0.017368832603096962, 0.07059700042009354, -0.018956167623400688, 0.35600546002388, 0.2889443039894104, 0.0505455806851387, -0.4532535970211029, -0.2310783565044403, 0.006119664758443832, -0.07810869812965393, 0.0040334537625312805, 0.005831866059452295, 0.21422632038593292, 0.07561899721622467, 0.13462267816066742, 0.37971192598342896, -0.21138310432434082, 0.1820078045129776, 0.06565909832715988, -0.14514309167861938, -0.3468712866306305, 0.13083887100219727, 0.03079209290444851, -0.06906116753816605, 0.11012744158506393, 0.01911790855228901, 0.5892500281333923, -0.025107210502028465, -0.22120502591133118]... [Tensor of shape torch.Size([1, 196])]\n",
      "base_model.linear.bias: tensor([12.2170])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fca627cb",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "739f2cc9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.146806Z",
     "iopub.status.busy": "2026-07-04T20:00:50.146730Z",
     "iopub.status.idle": "2026-07-04T20:00:50.156509Z",
     "shell.execute_reply": "2026-07-04T20:00:50.156056Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[11.7817],\n",
       "        [12.6549],\n",
       "        [11.4798],\n",
       "        [12.3791],\n",
       "        [11.4735],\n",
       "        [ 7.2415],\n",
       "        [18.4420],\n",
       "        [14.8113],\n",
       "        [14.2788],\n",
       "        [13.7944]], 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": "2edd337e",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "6465d933",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.157819Z",
     "iopub.status.busy": "2026-07-04T20:00:50.157737Z",
     "iopub.status.idle": "2026-07-04T20:00:50.162507Z",
     "shell.execute_reply": "2026-07-04T20:00:50.162039Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c873651b",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "7d926633",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:50.163947Z",
     "iopub.status.busy": "2026-07-04T20:00:50.163863Z",
     "iopub.status.idle": "2026-07-04T20:00:50.167522Z",
     "shell.execute_reply": "2026-07-04T20:00:50.167065Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: depressionbarbu.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
}