{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "810b3f5e",
   "metadata": {},
   "source": [
    "# EPICGA"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "510d6245",
   "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": "b58e42f2",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "36802d76",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:55.568991Z",
     "iopub.status.busy": "2026-07-04T20:24:55.568771Z",
     "iopub.status.idle": "2026-07-04T20:24:58.572759Z",
     "shell.execute_reply": "2026-07-04T20:24:58.572263Z"
    }
   },
   "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": "c8d0d60d",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "95f20ea5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.574434Z",
     "iopub.status.busy": "2026-07-04T20:24:58.574265Z",
     "iopub.status.idle": "2026-07-04T20:24:58.576916Z",
     "shell.execute_reply": "2026-07-04T20:24:58.576531Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class EPICGA(LinearReferenceClock):\n",
      "    def postprocess(self, x):\n",
      "        \"\"\"Model returns gestational age in days; convert to weeks.\"\"\"\n",
      "        return x / 7.0\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.EPICGA)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6b7c3e02",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.578056Z",
     "iopub.status.busy": "2026-07-04T20:24:58.577976Z",
     "iopub.status.idle": "2026-07-04T20:24:58.579590Z",
     "shell.execute_reply": "2026-07-04T20:24:58.579099Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.EPICGA()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7b6c0d1a",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2b547148",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.580834Z",
     "iopub.status.busy": "2026-07-04T20:24:58.580742Z",
     "iopub.status.idle": "2026-07-04T20:24:58.583147Z",
     "shell.execute_reply": "2026-07-04T20:24:58.582657Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"epicga\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: An EPIC DNA-methylation predictor of gestational age.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: An EPIC DNA-methylation predictor of gestational age.\n",
    "model.metadata[\"year\"] = 2021\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Haftorn, K. L. et al. An EPIC predictor of gestational age and its application to newborns conceived by assisted reproductive technologies. Clinical Epigenetics 13, 82 (2021).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1186/s13148-021-01055-z\"\n",
    "model.metadata[\"notes\"] = \"LASSO predictor of ultrasound-estimated gestational age in days from umbilical cord-blood DNA methylation, trained in 755 non-ART START newborns.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"cord blood\"]  # Paper: Cord blood samples were taken immediately after birth.\n",
    "model.metadata[\"predicts\"] = [\"gestational age\"]  # Paper: An EPIC DNA-methylation predictor of gestational age.\n",
    "model.metadata[\"training_target\"] = [\"gestational age\"]  # Paper: Clinically estimated gestational age was regressed on CpGs.\n",
    "model.metadata[\"unit\"] = [\"days\"]  # Paper: Intercept 293.4557 and coefficients reproduce gestational age in days.\n",
    "model.metadata[\"model_type\"] = \"LASSO regression\"  # Paper: Lasso regression selected 176 CpGs.\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: An EPIC DNA-methylation predictor of gestational age.\n",
    "model.metadata[\"population\"] = \"newborns\"  # Paper: The clock was trained on 755 non-ART newborns from START.\n",
    "model.metadata[\"journal\"] = \"Clinical Epigenetics\"\n",
    "model.metadata[\"last_author\"] = \"Jon Bohlin\"\n",
    "model.metadata[\"n_features\"] = 176\n",
    "model.metadata[\"citations\"] = 54\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "46a068ec",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "49f837fb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.584590Z",
     "iopub.status.busy": "2026-07-04T20:24:58.584487Z",
     "iopub.status.idle": "2026-07-04T20:24:58.847372Z",
     "shell.execute_reply": "2026-07-04T20:24:58.845659Z"
    }
   },
   "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%2Fs13148-021-01055-z/MediaObjects/13148_2021_1055_MOESM7_ESM.csv\"\n",
    "supplementary_file_name = \"epic_ga_coefs.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "208f2bfe",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b7bcb893",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.850865Z",
     "iopub.status.busy": "2026-07-04T20:24:58.850575Z",
     "iopub.status.idle": "2026-07-04T20:24:58.865186Z",
     "shell.execute_reply": "2026-07-04T20:24:58.864499Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('epic_ga_coefs.csv')\n",
    "mask = df['cpgs'].astype(str).str.lower().isin(['intercept', '(intercept)'])\n",
    "intercept_value = float(df.loc[mask, 's0'].iloc[0]) if mask.any() else 0.0\n",
    "coef_df = df.loc[~mask].reset_index(drop=True)\n",
    "model.features = coef_df['cpgs'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "783c47e0",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c1fc937c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.866831Z",
     "iopub.status.busy": "2026-07-04T20:24:58.866686Z",
     "iopub.status.idle": "2026-07-04T20:24:58.872418Z",
     "shell.execute_reply": "2026-07-04T20:24:58.872012Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['s0'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2877d12c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.873915Z",
     "iopub.status.busy": "2026-07-04T20:24:58.873831Z",
     "iopub.status.idle": "2026-07-04T20:24:58.879196Z",
     "shell.execute_reply": "2026-07-04T20:24:58.878756Z"
    }
   },
   "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": "167840d2",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "a1446f13",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.881152Z",
     "iopub.status.busy": "2026-07-04T20:24:58.881012Z",
     "iopub.status.idle": "2026-07-04T20:24:58.883082Z",
     "shell.execute_reply": "2026-07-04T20:24:58.882563Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f8c7fca0",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "e1811c4c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.884651Z",
     "iopub.status.busy": "2026-07-04T20:24:58.884530Z",
     "iopub.status.idle": "2026-07-04T20:24:58.886392Z",
     "shell.execute_reply": "2026-07-04T20:24:58.885944Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "81acef67",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.887594Z",
     "iopub.status.busy": "2026-07-04T20:24:58.887507Z",
     "iopub.status.idle": "2026-07-04T20:24:58.889336Z",
     "shell.execute_reply": "2026-07-04T20:24:58.888870Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'days_to_weeks'\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36789dee",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "6bf7b63e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.890523Z",
     "iopub.status.busy": "2026-07-04T20:24:58.890437Z",
     "iopub.status.idle": "2026-07-04T20:24:58.909113Z",
     "shell.execute_reply": "2026-07-04T20:24:58.908664Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Haftorn, Kristine L., et al. \"An EPIC predictor of gestational '\n",
      "             'age and its application to newborns conceived by assisted '\n",
      "             'reproductive technologies.\" Clinical Epigenetics 13.1 (2021): '\n",
      "             '82.',\n",
      " 'clock_name': 'epicga',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1186/s13148-021-01055-z',\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: 'days_to_weeks'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg12701018', 'cg00078456', 'cg14958032', 'cg00735586', 'cg09035049', 'cg23915699', 'cg24741609', 'cg00996847', 'cg12079303', 'cg20301308', 'cg21141647', 'cg13189264', 'cg16246545', 'cg06902698', 'cg01281797', 'cg01833485', 'cg12434132', 'cg06046912', 'cg11147204', 'cg19672145', 'cg02968445', 'cg09116068', 'cg07749613', 'cg21155834', 'cg15433843', 'cg12685296', 'cg22871331', 'cg25241559', 'cg06900004', 'cg20582941']... [Total elements: 176]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=176, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-0.09159819036722183, -2.3058528900146484, -0.4794044494628906, -11.715208053588867, -8.509488105773926, -0.5367807149887085, -0.32814541459083557, 1.0927908420562744, 1.626057744026184, -10.894654273986816, 1.7147382497787476, -8.59422492980957, 0.3499724566936493, 2.7312521934509277, 3.7085211277008057, 6.265093803405762, -3.1235597133636475, -0.5551669597625732, -4.767549991607666, 25.61239242553711, 1.6901012659072876, 1.5959044694900513, -32.38628387451172, -2.249823808670044, 11.97744369506836, 6.300745010375977, -0.7150956988334656, -0.45685043931007385, 3.390894889831543, -7.354003429412842]... [Tensor of shape torch.Size([1, 176])]\n",
      "base_model.linear.bias: tensor([293.4557])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9ee5b8cf",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "4f77e279",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.910492Z",
     "iopub.status.busy": "2026-07-04T20:24:58.910415Z",
     "iopub.status.idle": "2026-07-04T20:24:58.920215Z",
     "shell.execute_reply": "2026-07-04T20:24:58.919766Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[60.5326],\n",
       "        [42.4761],\n",
       "        [51.9958],\n",
       "        [58.1296],\n",
       "        [27.9050],\n",
       "        [42.0799],\n",
       "        [33.6746],\n",
       "        [32.6965],\n",
       "        [63.3254],\n",
       "        [42.7455]], dtype=torch.float64, grad_fn=<DivBackward0>)"
      ]
     },
     "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": "dc494a80",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "78d3742d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.921643Z",
     "iopub.status.busy": "2026-07-04T20:24:58.921526Z",
     "iopub.status.idle": "2026-07-04T20:24:58.927373Z",
     "shell.execute_reply": "2026-07-04T20:24:58.926772Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0da0589",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "e34db386",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:24:58.929047Z",
     "iopub.status.busy": "2026-07-04T20:24:58.928919Z",
     "iopub.status.idle": "2026-07-04T20:24:58.933245Z",
     "shell.execute_reply": "2026-07-04T20:24:58.932768Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: epic_ga_coefs.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
}