{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3404bf4b",
   "metadata": {},
   "source": [
    "# Bocklandt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5be08441",
   "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": "b86ff88a",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a0350a8c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:44.798790Z",
     "iopub.status.busy": "2026-07-04T19:51:44.798594Z",
     "iopub.status.idle": "2026-07-04T19:51:46.788880Z",
     "shell.execute_reply": "2026-07-04T19:51:46.788370Z"
    }
   },
   "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": "437360aa",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f3c51b8c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:46.790778Z",
     "iopub.status.busy": "2026-07-04T19:51:46.790590Z",
     "iopub.status.idle": "2026-07-04T19:51:46.793335Z",
     "shell.execute_reply": "2026-07-04T19:51:46.792938Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Bocklandt(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.Bocklandt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d98fcf32",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:46.794721Z",
     "iopub.status.busy": "2026-07-04T19:51:46.794635Z",
     "iopub.status.idle": "2026-07-04T19:51:46.796144Z",
     "shell.execute_reply": "2026-07-04T19:51:46.795832Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Bocklandt()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b99faa7",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "3244b4c2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:46.797346Z",
     "iopub.status.busy": "2026-07-04T19:51:46.797276Z",
     "iopub.status.idle": "2026-07-04T19:51:46.799277Z",
     "shell.execute_reply": "2026-07-04T19:51:46.798934Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"bocklandt\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The predictor uses CpG methylation percentages.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The study analyzed human saliva.\n",
    "model.metadata[\"year\"] = 2011\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Bocklandt, S., Lin, W., Sehl, M.E. et al. Epigenetic predictor of age. PLoS ONE 6, e14821 (2011).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1371/journal.pone.0014821\"\n",
    "model.metadata[\"notes\"] = \"Package-facing one-CpG identity score: pyaging returns raw cg09809672 methylation with coefficient 1 and zero intercept. The published saliva age regression instead uses EDARADD and NPTX2, including an EDARADD-squared basis term; that published age model is not implemented.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"saliva\"]  # Paper: Both discovery and validation samples were saliva.\n",
    "model.metadata[\"predicts\"] = [\"EDARADD methylation\"]  # Paper: The packaged object contains only cg09809672 with coefficient 1.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: Chronological age was the regression outcome.\n",
    "model.metadata[\"unit\"] = [\"beta value\"]  # Paper: The packaged single-CpG output is raw cg09809672/EDARADD methylation on the beta-value scale.\n",
    "model.metadata[\"model_type\"] = \"single-CpG score\"  # Paper: The packaged object contains only cg09809672 with coefficient 1.\n",
    "model.metadata[\"platform\"] = [\"Illumina 27K\"]  # Paper: Feature discovery used the Illumina HumanMethylation27 array.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: Discovery used 34 male monozygotic twin pairs aged 21–55; validation included unrelated adults aged 18–70.\n",
    "model.metadata[\"journal\"] = \"PLoS ONE\"\n",
    "model.metadata[\"last_author\"] = \"Éric Vilain\"\n",
    "model.metadata[\"n_features\"] = 1\n",
    "model.metadata[\"citations\"] = 1057\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1969c45d",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fbec7754",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:46.800635Z",
     "iopub.status.busy": "2026-07-04T19:51:46.800565Z",
     "iopub.status.idle": "2026-07-04T19:51:47.096539Z",
     "shell.execute_reply": "2026-07-04T19:51:47.095755Z"
    }
   },
   "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/Bocklandt.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10132cba",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9ed051ad",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.099015Z",
     "iopub.status.busy": "2026-07-04T19:51:47.098817Z",
     "iopub.status.idle": "2026-07-04T19:51:47.104628Z",
     "shell.execute_reply": "2026-07-04T19:51:47.104201Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('coefficients.csv')\n",
    "mask = df['CpGmarker'].astype(str).str.lower().isin(['intercept', '(intercept)'])\n",
    "intercept_value = float(df.loc[mask, 'CoefficientTraining'].iloc[0]) if mask.any() else 0.0\n",
    "coef_df = df.loc[~mask].reset_index(drop=True)\n",
    "model.features = coef_df['CpGmarker'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ccd7b0d1",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5419b258",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.106553Z",
     "iopub.status.busy": "2026-07-04T19:51:47.106419Z",
     "iopub.status.idle": "2026-07-04T19:51:47.109264Z",
     "shell.execute_reply": "2026-07-04T19:51:47.108836Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['CoefficientTraining'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "37219f91",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.110948Z",
     "iopub.status.busy": "2026-07-04T19:51:47.110788Z",
     "iopub.status.idle": "2026-07-04T19:51:47.113691Z",
     "shell.execute_reply": "2026-07-04T19:51:47.113220Z"
    }
   },
   "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": "d011f410",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "93e047a7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.115284Z",
     "iopub.status.busy": "2026-07-04T19:51:47.115168Z",
     "iopub.status.idle": "2026-07-04T19:51:47.117052Z",
     "shell.execute_reply": "2026-07-04T19:51:47.116600Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d644fecc",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "336cb3dd",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.118469Z",
     "iopub.status.busy": "2026-07-04T19:51:47.118361Z",
     "iopub.status.idle": "2026-07-04T19:51:47.120131Z",
     "shell.execute_reply": "2026-07-04T19:51:47.119690Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "b82cc9eb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.121556Z",
     "iopub.status.busy": "2026-07-04T19:51:47.121443Z",
     "iopub.status.idle": "2026-07-04T19:51:47.123251Z",
     "shell.execute_reply": "2026-07-04T19:51:47.122825Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7435a8fd",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "bfd61c96",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.124707Z",
     "iopub.status.busy": "2026-07-04T19:51:47.124606Z",
     "iopub.status.idle": "2026-07-04T19:51:47.128446Z",
     "shell.execute_reply": "2026-07-04T19:51:47.127896Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Bocklandt, Sven, et al. \"Epigenetic predictor of age.\" PloS one '\n",
      "             '6.6 (2011): e14821.',\n",
      " 'clock_name': 'bocklandt',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1371/journal.pone.0014821',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2011}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg09809672']\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=1, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[1.]])\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ffa4bf22",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "14e5bafe",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.130040Z",
     "iopub.status.busy": "2026-07-04T19:51:47.129942Z",
     "iopub.status.idle": "2026-07-04T19:51:47.134584Z",
     "shell.execute_reply": "2026-07-04T19:51:47.134136Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 0.3367],\n",
       "        [ 0.1288],\n",
       "        [ 0.2345],\n",
       "        [ 0.2303],\n",
       "        [-1.1229],\n",
       "        [-0.1863],\n",
       "        [ 2.2082],\n",
       "        [-0.6380],\n",
       "        [ 0.4617],\n",
       "        [ 0.2674]], 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": "20017283",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "bbd4a9b0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.136020Z",
     "iopub.status.busy": "2026-07-04T19:51:47.135936Z",
     "iopub.status.idle": "2026-07-04T19:51:47.139291Z",
     "shell.execute_reply": "2026-07-04T19:51:47.138858Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f090274",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "dacbc85b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:51:47.140562Z",
     "iopub.status.busy": "2026-07-04T19:51:47.140481Z",
     "iopub.status.idle": "2026-07-04T19:51:47.143967Z",
     "shell.execute_reply": "2026-07-04T19:51:47.143640Z"
    }
   },
   "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
}