{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b98d8bbd",
   "metadata": {},
   "source": [
    "# NeuSin"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a25f3291",
   "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": "70ce8a24",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "529eb4b3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:16.318329Z",
     "iopub.status.busy": "2026-07-04T19:34:16.318218Z",
     "iopub.status.idle": "2026-07-04T19:34:18.210883Z",
     "shell.execute_reply": "2026-07-04T19:34:18.210278Z"
    }
   },
   "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": "0e8071c3",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7c101cb5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.213081Z",
     "iopub.status.busy": "2026-07-04T19:34:18.212867Z",
     "iopub.status.idle": "2026-07-04T19:34:18.215882Z",
     "shell.execute_reply": "2026-07-04T19:34:18.215493Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class NeuSin(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.NeuSin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "99737934",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.217039Z",
     "iopub.status.busy": "2026-07-04T19:34:18.216960Z",
     "iopub.status.idle": "2026-07-04T19:34:18.218791Z",
     "shell.execute_reply": "2026-07-04T19:34:18.218367Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.NeuSin()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7310894e",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d9717346",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.219894Z",
     "iopub.status.busy": "2026-07-04T19:34:18.219818Z",
     "iopub.status.idle": "2026-07-04T19:34:18.221803Z",
     "shell.execute_reply": "2026-07-04T19:34:18.221327Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"neusin\"\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\"] = 2024\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Tong, Huige, et al. \\\"Cell-type specific epigenetic clocks to quantify biological age at cell-type resolution.\\\" Aging 16 (2024): 13452–13504.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.18632/aging.206184\"\n",
    "model.metadata[\"notes\"] = \"Neu-Sin is a neuron semi-intrinsic chronological-age clock: elastic-net regression was restricted to neuron age-DMCTs but fitted to methylation values not adjusted for brain cell fractions.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"brain cortex\"]  # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: Finally, elastic net predictors of chronological age are trained from the Neu-DMCTs parameterized by a penalty parameter.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: Having identified the significant neuron-DMCTs, we next trained Elastic Net regression (glmnet R package) models (alpha = 0.5) for age, each parameterized by a different penalty parameter (lambda) value.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: Having identified the significant neuron-DMCTs, we next trained Elastic Net regression (glmnet R package) models (alpha = 0.5) for age, each parameterized by a different penalty parameter (lambda) value.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: For training the clocks, we used one of the largest collections of prefrontal cortex (PFC) samples profiled with Illumina 450k technology, encompassing 416 samples with a wide age range (18–97 years).\n",
    "model.metadata[\"journal\"] = \"Aging\"\n",
    "model.metadata[\"last_author\"] = \"Andrew E. Teschendorff\"\n",
    "model.metadata[\"n_features\"] = 672  # Paper: The official Neu-SinCoef.rda object contains 673 rows: one (Intercept) row and 672 non-intercept CpG coefficient rows.\n",
    "model.metadata[\"citations\"] = 25\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a913a9f",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2c825a05",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.223013Z",
     "iopub.status.busy": "2026-07-04T19:34:18.222925Z",
     "iopub.status.idle": "2026-07-04T19:34:18.346718Z",
     "shell.execute_reply": "2026-07-04T19:34:18.346138Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://raw.githubusercontent.com/Duzhaozhen/OmniAge/c10fbe8cb92957520fbff1d55ae1def0691252e5/OmniAgePy/src/omniage/data/CTS/Neu-Sin.csv\"\n",
    "supplementary_file_name = \"coefficients.csv\"\n",
    "os.system(f\"curl -sL -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9fe7e1a6",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "822b228a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.348203Z",
     "iopub.status.busy": "2026-07-04T19:34:18.348088Z",
     "iopub.status.idle": "2026-07-04T19:34:18.353294Z",
     "shell.execute_reply": "2026-07-04T19:34:18.352777Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('coefficients.csv')\n",
    "if str(df.columns[0]).startswith('Unnamed'):\n",
    "    df = df.iloc[:, 1:]\n",
    "mask = df['probe'].astype(str).str.lower().isin(['intercept', '(intercept)'])\n",
    "intercept_value = float(df.loc[mask, 'coef'].iloc[0]) if mask.any() else 0.0\n",
    "coef_df = df.loc[~mask].reset_index(drop=True)\n",
    "model.features = coef_df['probe'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "953e20a0",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "b1f43f8f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.355010Z",
     "iopub.status.busy": "2026-07-04T19:34:18.354888Z",
     "iopub.status.idle": "2026-07-04T19:34:18.357299Z",
     "shell.execute_reply": "2026-07-04T19:34:18.356902Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['coef'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e5a88e18",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.358564Z",
     "iopub.status.busy": "2026-07-04T19:34:18.358471Z",
     "iopub.status.idle": "2026-07-04T19:34:18.360706Z",
     "shell.execute_reply": "2026-07-04T19:34:18.360350Z"
    }
   },
   "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": "9a6a19cc",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1dd4cfbf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.362083Z",
     "iopub.status.busy": "2026-07-04T19:34:18.361994Z",
     "iopub.status.idle": "2026-07-04T19:34:18.363689Z",
     "shell.execute_reply": "2026-07-04T19:34:18.363334Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "719143bf",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "1332993b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.364964Z",
     "iopub.status.busy": "2026-07-04T19:34:18.364887Z",
     "iopub.status.idle": "2026-07-04T19:34:18.366576Z",
     "shell.execute_reply": "2026-07-04T19:34:18.366299Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "21e4c8ff",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.367778Z",
     "iopub.status.busy": "2026-07-04T19:34:18.367709Z",
     "iopub.status.idle": "2026-07-04T19:34:18.369415Z",
     "shell.execute_reply": "2026-07-04T19:34:18.369004Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "700bca59",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "19935e87",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.370544Z",
     "iopub.status.busy": "2026-07-04T19:34:18.370476Z",
     "iopub.status.idle": "2026-07-04T19:34:18.373861Z",
     "shell.execute_reply": "2026-07-04T19:34:18.373460Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Tong, Huige, et al. \"Cell-type-specific and '\n",
      "             'cell-type-independent DNA methylation clocks.\" Aging 16 (2024).',\n",
      " 'clock_name': 'neusin',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.18632/aging.206184',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2024}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg10626816', 'cg13571388', 'cg17826530', 'cg06711298', 'cg08193650', 'cg10442729', 'cg17343483', 'cg20361600', 'cg21185289', 'cg16369288', 'cg22702772', 'cg26856080', 'cg06385118', 'cg18171715', 'cg18586891', 'cg05477834', 'cg15690342', 'cg18635552', 'cg18745317', 'cg25108022', 'cg00537387', 'cg08692175', 'cg25739875', 'cg18048071', 'cg19421584', 'cg22493372', 'cg02324367', 'cg05492433', 'cg16241714', 'cg26003909']... [Total elements: 672]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=672, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.6255767941474915, 0.00018867039761971682, 1.4650660753250122, -4.989912986755371, 2.8106305599212646, 3.3365237712860107, -8.365673065185547, -7.561515808105469, -2.2176127433776855, 2.238844394683838, 5.353684425354004, 18.882240295410156, -1.537793755531311, 18.469179153442383, 0.3016071319580078, -0.4679134786128998, 0.7296689748764038, -9.179381370544434, 0.04645940288901329, 7.833886623382568, -2.897672414779663, -21.346012115478516, 9.050196647644043, 0.5711203813552856, 0.47357064485549927, 0.11948469281196594, 0.0023688615765422583, -1.3019375801086426, 57.94570541381836, -2.4218344688415527]... [Tensor of shape torch.Size([1, 672])]\n",
      "base_model.linear.bias: tensor([20.1315])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "374f688c",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "27adbf83",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.375233Z",
     "iopub.status.busy": "2026-07-04T19:34:18.375157Z",
     "iopub.status.idle": "2026-07-04T19:34:18.379712Z",
     "shell.execute_reply": "2026-07-04T19:34:18.379310Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ -26.3359],\n",
       "        [ 213.3675],\n",
       "        [-104.1039],\n",
       "        [-339.0749],\n",
       "        [ -66.5274],\n",
       "        [ 113.9317],\n",
       "        [ 141.6260],\n",
       "        [ -65.5180],\n",
       "        [  -2.5413],\n",
       "        [-400.5478]], 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": "0504f077",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "a0310962",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.380936Z",
     "iopub.status.busy": "2026-07-04T19:34:18.380858Z",
     "iopub.status.idle": "2026-07-04T19:34:18.384506Z",
     "shell.execute_reply": "2026-07-04T19:34:18.384114Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "acbaca64",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "f435c343",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:34:18.385614Z",
     "iopub.status.busy": "2026-07-04T19:34:18.385544Z",
     "iopub.status.idle": "2026-07-04T19:34:18.389006Z",
     "shell.execute_reply": "2026-07-04T19:34:18.388548Z"
    }
   },
   "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
}