{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "46d559da",
   "metadata": {},
   "source": [
    "# ProstateCancerKirby"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8aa57c2e",
   "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": "d3308068",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "09724621",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:02.011903Z",
     "iopub.status.busy": "2026-07-04T20:01:02.011805Z",
     "iopub.status.idle": "2026-07-04T20:01:04.436127Z",
     "shell.execute_reply": "2026-07-04T20:01:04.435660Z"
    }
   },
   "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": "82e72927",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6eb80685",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.437965Z",
     "iopub.status.busy": "2026-07-04T20:01:04.437749Z",
     "iopub.status.idle": "2026-07-04T20:01:04.440859Z",
     "shell.execute_reply": "2026-07-04T20:01:04.440486Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class ProstateCancerKirby(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.ProstateCancerKirby)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b3729166",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.442075Z",
     "iopub.status.busy": "2026-07-04T20:01:04.441997Z",
     "iopub.status.idle": "2026-07-04T20:01:04.443726Z",
     "shell.execute_reply": "2026-07-04T20:01:04.443361Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.ProstateCancerKirby()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7ee5a04",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "10191303",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.445001Z",
     "iopub.status.busy": "2026-07-04T20:01:04.444905Z",
     "iopub.status.idle": "2026-07-04T20:01:04.447074Z",
     "shell.execute_reply": "2026-07-04T20:01:04.446613Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"prostatecancerkirby\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The classifier uses methylation beta values at three CpGs.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: Prostate tissues were collected from human patients undergoing radical prostatectomy.\n",
    "model.metadata[\"year\"] = 2017\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Kirby, M. K., et al. “Genome-wide DNA methylation measurements in prostate tissues uncovers novel prostate cancer diagnostic biomarkers and transcription factor binding patterns.” BMC Cancer 17: 273 (2017).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1186/s12885-017-3252-2\"\n",
    "model.metadata[\"notes\"] = \"Three-CpG prostate-tissue diagnostic classifier distinguishing malignant from benign-adjacent tissue; it was trained on 73 tumors and 63 benign-adjacent samples and externally validated in TCGA.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"prostate\"]  # Paper: Fresh-frozen prostate cancers and benign-adjacent prostate tissues were profiled.\n",
    "model.metadata[\"predicts\"] = [\"prostate cancer\"]  # Paper: The score distinguishes malignant prostate tissue from benign-adjacent tissue.\n",
    "model.metadata[\"training_target\"] = [\"prostate cancer\"]  # Paper: Binomial logistic regression was fit to tumor versus benign-adjacent tissue status.\n",
    "model.metadata[\"unit\"] = [\"log odds\"]  # Paper: The published classifier is the untransformed binomial-GLM linear predictor 6.52 − 17.04β1 + 24.18β2 − 13.82β3.\n",
    "model.metadata[\"model_type\"] = \"logistic regression\"  # Paper: Logistic regression used glm with family=binomial.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Training tissues were measured with the Illumina HumanMethylation450 BeadChip.\n",
    "model.metadata[\"population\"] = \"adult men\"  # Paper: The training cohort had ages 43–73 years and supplied tumor/benign-adjacent prostate tissues.\n",
    "model.metadata[\"journal\"] = \"BMC Cancer\"\n",
    "model.metadata[\"last_author\"] = \"Richard M. Myers\"\n",
    "model.metadata[\"n_features\"] = 3\n",
    "model.metadata[\"citations\"] = 61\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54a55994",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1fd58807",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.448613Z",
     "iopub.status.busy": "2026-07-04T20:01:04.448493Z",
     "iopub.status.idle": "2026-07-04T20:01:04.610452Z",
     "shell.execute_reply": "2026-07-04T20:01:04.609920Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o prostatecancerkirby.xlsx https://static-content.springer.com/esm/art%3A10.1186%2Fs12885-017-3252-2/MediaObjects/12885_2017_3252_MOESM4_ESM.xlsx\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6fba8167",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f5753676",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.611793Z",
     "iopub.status.busy": "2026-07-04T20:01:04.611688Z",
     "iopub.status.idle": "2026-07-04T20:01:04.682819Z",
     "shell.execute_reply": "2026-07-04T20:01:04.682348Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/lucascamillo/pyaging/.venv/lib/python3.13/site-packages/openpyxl/worksheet/_reader.py:329: UserWarning: Unknown extension is not supported and will be removed\n",
      "  warn(msg)\n"
     ]
    }
   ],
   "source": [
    "raw = pd.read_excel('prostatecancerkirby.xlsx', sheet_name=0, header=None)\n",
    "hdr_cell = val_cell = None\n",
    "for i in range(len(raw)):\n",
    "    for j in range(raw.shape[1]):\n",
    "        c = str(raw.iloc[i, j])\n",
    "        if '(Intercept)' in c and 'cg' in c:\n",
    "            hdr_cell = c\n",
    "            val_cell = str(raw.iloc[i + 1, j])\n",
    "            break\n",
    "    if hdr_cell:\n",
    "        break\n",
    "names = hdr_cell.split()\n",
    "nums = [float(x) for x in val_cell.split()]\n",
    "intercept_value = 0.0\n",
    "feats, coefs = [], []\n",
    "for name, num in zip(names, nums):\n",
    "    if 'Intercept' in name:\n",
    "        intercept_value = num\n",
    "    else:\n",
    "        feats.append(name)\n",
    "        coefs.append(num)\n",
    "model.features = feats"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "abef587e",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "033fa993",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.684168Z",
     "iopub.status.busy": "2026-07-04T20:01:04.684081Z",
     "iopub.status.idle": "2026-07-04T20:01:04.686271Z",
     "shell.execute_reply": "2026-07-04T20:01:04.685879Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coefs).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b5266595",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.687494Z",
     "iopub.status.busy": "2026-07-04T20:01:04.687427Z",
     "iopub.status.idle": "2026-07-04T20:01:04.689681Z",
     "shell.execute_reply": "2026-07-04T20:01:04.689156Z"
    }
   },
   "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": "ae2ea44c",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9e2f57ff",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.691061Z",
     "iopub.status.busy": "2026-07-04T20:01:04.690973Z",
     "iopub.status.idle": "2026-07-04T20:01:04.692653Z",
     "shell.execute_reply": "2026-07-04T20:01:04.692259Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e03cc985",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "636576a0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.693727Z",
     "iopub.status.busy": "2026-07-04T20:01:04.693661Z",
     "iopub.status.idle": "2026-07-04T20:01:04.695117Z",
     "shell.execute_reply": "2026-07-04T20:01:04.694820Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "bbe0d70a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.696276Z",
     "iopub.status.busy": "2026-07-04T20:01:04.696194Z",
     "iopub.status.idle": "2026-07-04T20:01:04.697894Z",
     "shell.execute_reply": "2026-07-04T20:01:04.697410Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "30c86da3",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8aa16777",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.699182Z",
     "iopub.status.busy": "2026-07-04T20:01:04.699100Z",
     "iopub.status.idle": "2026-07-04T20:01:04.702742Z",
     "shell.execute_reply": "2026-07-04T20:01:04.702328Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Kirby, Michael K., et al. \"Genome-wide DNA methylation '\n",
      "             'measurements in prostate tissues uncovers novel prostate cancer '\n",
      "             'diagnostic biomarkers and predictors of progression.\" BMC Cancer '\n",
      "             '17.1 (2017): 273.',\n",
      " 'clock_name': 'prostatecancerkirby',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1186/s12885-017-3252-2',\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: ['cg00054525', 'cg16794576', 'cg24581650']\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=3, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: tensor([[-17.0370,  24.1830, -13.8250]])\n",
      "base_model.linear.bias: tensor([6.5240])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "750d6998",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "c6827524",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.704066Z",
     "iopub.status.busy": "2026-07-04T20:01:04.703985Z",
     "iopub.status.idle": "2026-07-04T20:01:04.708391Z",
     "shell.execute_reply": "2026-07-04T20:01:04.707965Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[  3.3665],\n",
       "        [ 15.9152],\n",
       "        [ -7.6545],\n",
       "        [  9.1350],\n",
       "        [  7.7513],\n",
       "        [ 24.9928],\n",
       "        [ -6.7956],\n",
       "        [ 17.0494],\n",
       "        [ 17.7305],\n",
       "        [-18.3624]], 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": "85485e51",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "bfdbe168",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.709761Z",
     "iopub.status.busy": "2026-07-04T20:01:04.709681Z",
     "iopub.status.idle": "2026-07-04T20:01:04.713060Z",
     "shell.execute_reply": "2026-07-04T20:01:04.712563Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d00d59db",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "3181609a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T20:01:04.714598Z",
     "iopub.status.busy": "2026-07-04T20:01:04.714510Z",
     "iopub.status.idle": "2026-07-04T20:01:04.719003Z",
     "shell.execute_reply": "2026-07-04T20:01:04.717784Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: prostatecancerkirby.xlsx\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
}