{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "75120104",
   "metadata": {},
   "source": [
    "# HepatoXu"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9423ade4",
   "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": "27f44369",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d5eb6946",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:06.847167Z",
     "iopub.status.busy": "2026-07-04T20:01:06.846870Z",
     "iopub.status.idle": "2026-07-04T20:01:09.018804Z",
     "shell.execute_reply": "2026-07-04T20:01:09.018315Z"
    }
   },
   "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": "a4323330",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b856a836",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.020556Z",
     "iopub.status.busy": "2026-07-04T20:01:09.020342Z",
     "iopub.status.idle": "2026-07-04T20:01:09.023367Z",
     "shell.execute_reply": "2026-07-04T20:01:09.022973Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class HepatoXu(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.HepatoXu)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b59c8043",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.024760Z",
     "iopub.status.busy": "2026-07-04T20:01:09.024670Z",
     "iopub.status.idle": "2026-07-04T20:01:09.026371Z",
     "shell.execute_reply": "2026-07-04T20:01:09.026039Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.HepatoXu()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c74f8138",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "06084b28",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.027947Z",
     "iopub.status.busy": "2026-07-04T20:01:09.027775Z",
     "iopub.status.idle": "2026-07-04T20:01:09.029957Z",
     "shell.execute_reply": "2026-07-04T20:01:09.029544Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"hepatoxu\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The study developed circulating tumour-DNA methylation markers.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: Plasma samples came from human HCC patients and normal controls.\n",
    "model.metadata[\"year\"] = 2017\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Xu, R.-H., et al. “Circulating tumour DNA methylation markers for diagnosis and prognosis of hepatocellular carcinoma.” Nature Materials 16: 1155–1161 (2017).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/nmat4997\"\n",
    "model.metadata[\"notes\"] = \"Ten-marker plasma cfDNA methylation logistic model producing the combined HCC diagnosis score (cd-score); this packaged model does not implement the separate eight-marker prognosis score.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"plasma cell-free DNA\"]  # Paper: The diagnostic dataset comprised plasma cfDNA from HCC patients and normal controls.\n",
    "model.metadata[\"predicts\"] = [\"hepatocellular carcinoma\"]  # Paper: The ten-marker model produced a combined diagnosis score designated cd-score.\n",
    "model.metadata[\"training_target\"] = [\"hepatocellular carcinoma\"]  # Paper: The logistic regression was fitted as a binary prediction of HCC versus normal plasma samples.\n",
    "model.metadata[\"unit\"] = [\"unitless\"]  # Paper: The packaged LinearReferenceClock returns the weighted linear score without a sigmoid transformation.\n",
    "model.metadata[\"model_type\"] = \"feature-selected logistic regression\"  # Paper: Ten overlapping markers from LASSO and random forest were used as covariates in logistic regression.\n",
    "model.metadata[\"platform\"] = [\"targeted bisulfite sequencing\"]  # Paper: Chinese plasma methylation values were obtained by targeted bisulfite sequencing using molecular inversion probes.\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: The 1,933-sample dataset was split 2:1; the training set had 1,275 samples from 715 HCC and 560 normal samples.\n",
    "model.metadata[\"journal\"] = \"Nature Materials\"\n",
    "model.metadata[\"last_author\"] = \"Kang Zhang\"\n",
    "model.metadata[\"n_features\"] = 10\n",
    "model.metadata[\"citations\"] = 884\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "84f7d40b",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2caf0f4e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.031390Z",
     "iopub.status.busy": "2026-07-04T20:01:09.031300Z",
     "iopub.status.idle": "2026-07-04T20:01:09.326457Z",
     "shell.execute_reply": "2026-07-04T20:01:09.324898Z"
    }
   },
   "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/HepatoXu.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7201a362",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "db59d912",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.329567Z",
     "iopub.status.busy": "2026-07-04T20:01:09.329308Z",
     "iopub.status.idle": "2026-07-04T20:01:09.335291Z",
     "shell.execute_reply": "2026-07-04T20:01:09.334753Z"
    }
   },
   "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": "8bd3ed80",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "cea12cd0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.337020Z",
     "iopub.status.busy": "2026-07-04T20:01:09.336909Z",
     "iopub.status.idle": "2026-07-04T20:01:09.339348Z",
     "shell.execute_reply": "2026-07-04T20:01:09.338919Z"
    }
   },
   "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": "6dc7b67c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.340661Z",
     "iopub.status.busy": "2026-07-04T20:01:09.340558Z",
     "iopub.status.idle": "2026-07-04T20:01:09.343969Z",
     "shell.execute_reply": "2026-07-04T20:01:09.343023Z"
    }
   },
   "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": "ff84857e",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "6ba5764a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.346856Z",
     "iopub.status.busy": "2026-07-04T20:01:09.346595Z",
     "iopub.status.idle": "2026-07-04T20:01:09.349300Z",
     "shell.execute_reply": "2026-07-04T20:01:09.348309Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2873ddaa",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9531ad3b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.351357Z",
     "iopub.status.busy": "2026-07-04T20:01:09.351016Z",
     "iopub.status.idle": "2026-07-04T20:01:09.353613Z",
     "shell.execute_reply": "2026-07-04T20:01:09.353154Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "66e4dd16",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.355183Z",
     "iopub.status.busy": "2026-07-04T20:01:09.355063Z",
     "iopub.status.idle": "2026-07-04T20:01:09.357162Z",
     "shell.execute_reply": "2026-07-04T20:01:09.356738Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7b957c4",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "5cb0746c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.358629Z",
     "iopub.status.busy": "2026-07-04T20:01:09.358518Z",
     "iopub.status.idle": "2026-07-04T20:01:09.361896Z",
     "shell.execute_reply": "2026-07-04T20:01:09.361525Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Xu, Ruo-Han, et al. \"Circulating tumour DNA methylation markers '\n",
      "             'for diagnosis and prognosis of hepatocellular carcinoma.\" Nature '\n",
      "             'Materials 16.11 (2017): 1155-1161.',\n",
      " 'clock_name': 'hepatoxu',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/nmat4997',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2017}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg10428836',\n",
      " 'cg26668608',\n",
      " 'cg25754195',\n",
      " 'cg05205842',\n",
      " 'cg11606215',\n",
      " 'cg24067911',\n",
      " 'cg18196829',\n",
      " 'cg23211949',\n",
      " 'cg17213048',\n",
      " 'cg25459300']\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=10, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[11.5430,  4.5570,  2.5190, -3.6120,  6.8650, -5.4390, -9.0780, -5.2090,\n",
      "          6.6600,  1.9940]])\n",
      "base_model.linear.bias: tensor([15.5950])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6082f471",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "196acf66",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.363133Z",
     "iopub.status.busy": "2026-07-04T20:01:09.363062Z",
     "iopub.status.idle": "2026-07-04T20:01:09.367344Z",
     "shell.execute_reply": "2026-07-04T20:01:09.366970Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[49.1148],\n",
       "        [40.0752],\n",
       "        [23.5150],\n",
       "        [ 1.2405],\n",
       "        [ 2.2419],\n",
       "        [-6.4443],\n",
       "        [ 1.1513],\n",
       "        [33.1075],\n",
       "        [61.1116],\n",
       "        [22.9915]], 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": "7026f16d",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "3cca4d29",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.369544Z",
     "iopub.status.busy": "2026-07-04T20:01:09.369413Z",
     "iopub.status.idle": "2026-07-04T20:01:09.373084Z",
     "shell.execute_reply": "2026-07-04T20:01:09.372451Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "618d9a6f",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "a1281a8d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:09.374470Z",
     "iopub.status.busy": "2026-07-04T20:01:09.374369Z",
     "iopub.status.idle": "2026-07-04T20:01:09.381861Z",
     "shell.execute_reply": "2026-07-04T20:01:09.377484Z"
    }
   },
   "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
}