{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fce1f113",
   "metadata": {},
   "source": [
    "# ReedBMI"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "39972ff2",
   "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": "eee019dd",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b5882df9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:52.354226Z",
     "iopub.status.busy": "2026-07-04T20:00:52.354087Z",
     "iopub.status.idle": "2026-07-04T20:00:54.669364Z",
     "shell.execute_reply": "2026-07-04T20:00:54.668870Z"
    }
   },
   "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": "7d8f1eb5",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c5f2907a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:54.671055Z",
     "iopub.status.busy": "2026-07-04T20:00:54.670865Z",
     "iopub.status.idle": "2026-07-04T20:00:54.673901Z",
     "shell.execute_reply": "2026-07-04T20:00:54.673498Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class ReedBMI(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.ReedBMI)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "2347b342",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:54.675282Z",
     "iopub.status.busy": "2026-07-04T20:00:54.675188Z",
     "iopub.status.idle": "2026-07-04T20:00:54.678287Z",
     "shell.execute_reply": "2026-07-04T20:00:54.677573Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.ReedBMI()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "522df83a",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f27f7cb2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:54.680262Z",
     "iopub.status.busy": "2026-07-04T20:00:54.680168Z",
     "iopub.status.idle": "2026-07-04T20:00:54.682449Z",
     "shell.execute_reply": "2026-07-04T20:00:54.682102Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"reedbmi\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: DNA methylation scores for BMI\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: ARIES cohort of mothers and children\n",
    "model.metadata[\"year\"] = 2020\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Reed, Zoe E., et al. \\\"The association of DNA methylation with body mass index: distinguishing between predictors and biomarkers.\\\" Clinical Epigenetics 12 (2020): 50.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1186/s13148-020-00841-5\"\n",
    "model.metadata[\"notes\"] = \"Weighted blood-DNA-methylation score built from published BMI EWAS effect estimates and evaluated across the ARIES life course; it is a biomarker associated with concurrent BMI, not a calibrated prediction in kilograms.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\", \"cord blood\"]  # Paper: DNA methylation measured in peripheral blood; at birth, childhood, adolescence, pregnancy and middle age\n",
    "model.metadata[\"predicts\"] = [\"BMI methylation score\"]  # Paper: methylation score for BMI\n",
    "model.metadata[\"training_target\"] = [\"body mass index\"]  # Paper: 135 CpG sites from ... meta-analysis of DNA methylation and BMI\n",
    "model.metadata[\"unit\"] = [\"unitless\"]  # Paper: CpG methylation levels were multiplied by published effect estimates and summed; analyses report effects per SD of the score.\n",
    "model.metadata[\"model_type\"] = \"weighted methylation aggregation\"  # Paper: multiplying ... methylation levels ... with corresponding published effect estimates and then summing\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: ARIES methylation profiles\n",
    "model.metadata[\"population\"] = \"all ages\"  # Paper: mothers and children ... at multiple time points\n",
    "model.metadata[\"journal\"] = \"Clinical Epigenetics\"\n",
    "model.metadata[\"last_author\"] = \"Gibran Hemani\"\n",
    "model.metadata[\"n_features\"] = 135\n",
    "model.metadata[\"citations\"] = 86\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "28e61558",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2c728268",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:54.683745Z",
     "iopub.status.busy": "2026-07-04T20:00:54.683666Z",
     "iopub.status.idle": "2026-07-04T20:00:55.024150Z",
     "shell.execute_reply": "2026-07-04T20:00:55.023732Z"
    }
   },
   "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/BMI_Reed.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e2511b63",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "97d9e08e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.025624Z",
     "iopub.status.busy": "2026-07-04T20:00:55.025470Z",
     "iopub.status.idle": "2026-07-04T20:00:55.033059Z",
     "shell.execute_reply": "2026-07-04T20:00:55.032624Z"
    }
   },
   "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": "94b130f5",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a8fcf42c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.034746Z",
     "iopub.status.busy": "2026-07-04T20:00:55.034650Z",
     "iopub.status.idle": "2026-07-04T20:00:55.036795Z",
     "shell.execute_reply": "2026-07-04T20:00:55.036440Z"
    }
   },
   "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": "405b96e1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.038151Z",
     "iopub.status.busy": "2026-07-04T20:00:55.038020Z",
     "iopub.status.idle": "2026-07-04T20:00:55.040284Z",
     "shell.execute_reply": "2026-07-04T20:00:55.039918Z"
    }
   },
   "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": "650ab22a",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "fd5a060a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.041505Z",
     "iopub.status.busy": "2026-07-04T20:00:55.041416Z",
     "iopub.status.idle": "2026-07-04T20:00:55.043025Z",
     "shell.execute_reply": "2026-07-04T20:00:55.042667Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2963260d",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5ba1bb4c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.044562Z",
     "iopub.status.busy": "2026-07-04T20:00:55.044435Z",
     "iopub.status.idle": "2026-07-04T20:00:55.046192Z",
     "shell.execute_reply": "2026-07-04T20:00:55.045804Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "3f76fe43",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.047432Z",
     "iopub.status.busy": "2026-07-04T20:00:55.047359Z",
     "iopub.status.idle": "2026-07-04T20:00:55.050006Z",
     "shell.execute_reply": "2026-07-04T20:00:55.049102Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69cfcda4",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "5ebcc8f1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.052939Z",
     "iopub.status.busy": "2026-07-04T20:00:55.052708Z",
     "iopub.status.idle": "2026-07-04T20:00:55.058185Z",
     "shell.execute_reply": "2026-07-04T20:00:55.057696Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Reed, Zoe E., et al. \"Perinatal and childhood epigenetic '\n",
      "             'biomarkers of body composition.\" Clinical Epigenetics 12.1 '\n",
      "             '(2020): 156.',\n",
      " 'clock_name': 'reedbmi',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1186/s13148-020-00841-5',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2020}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00108715', 'cg00222799', 'cg00574958', 'cg01130991', 'cg01243823', 'cg01368219', 'cg01455178', 'cg01526748', 'cg01597398', 'cg01671681', 'cg01751802', 'cg01798813', 'cg01881899', 'cg02286155', 'cg02571142', 'cg02711608', 'cg02716826', 'cg03078551', 'cg03218374', 'cg03500056', 'cg03682690', 'cg03725309', 'cg04011474', 'cg04286697', 'cg04483863', 'cg04557677', 'cg04816311', 'cg04927537', 'cg05119988', 'cg06192883']... [Total elements: 135]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=135, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.007000000216066837, 0.007000000216066837, -0.019999999552965164, 0.009999999776482582, -0.00800000037997961, 0.00800000037997961, 0.008999999612569809, 0.008999999612569809, -0.006000000052154064, -0.00800000037997961, 0.00800000037997961, 0.009999999776482582, 0.009999999776482582, 0.006000000052154064, 0.00800000037997961, -0.00800000037997961, -0.00800000037997961, -0.009999999776482582, 0.008999999612569809, 0.006000000052154064, 0.009999999776482582, -0.009999999776482582, -0.00800000037997961, 0.007000000216066837, 0.008999999612569809, -0.00800000037997961, 0.009999999776482582, 0.009999999776482582, -0.008999999612569809, 0.00800000037997961]... [Tensor of shape torch.Size([1, 135])]\n",
      "base_model.linear.bias: tensor([0.])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "607e396a",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "778690b4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.059649Z",
     "iopub.status.busy": "2026-07-04T20:00:55.059559Z",
     "iopub.status.idle": "2026-07-04T20:00:55.063874Z",
     "shell.execute_reply": "2026-07-04T20:00:55.063467Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 0.1953],\n",
       "        [-0.0139],\n",
       "        [ 0.0094],\n",
       "        [-0.0168],\n",
       "        [ 0.0056],\n",
       "        [ 0.0452],\n",
       "        [ 0.0059],\n",
       "        [ 0.0187],\n",
       "        [ 0.1456],\n",
       "        [-0.0608]], 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": "6868ca12",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e2c058ee",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.065428Z",
     "iopub.status.busy": "2026-07-04T20:00:55.065333Z",
     "iopub.status.idle": "2026-07-04T20:00:55.068815Z",
     "shell.execute_reply": "2026-07-04T20:00:55.068406Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "423bb494",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b1703823",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:00:55.070186Z",
     "iopub.status.busy": "2026-07-04T20:00:55.070113Z",
     "iopub.status.idle": "2026-07-04T20:00:55.073720Z",
     "shell.execute_reply": "2026-07-04T20:00:55.073268Z"
    }
   },
   "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
}