{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# StocH"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3f514a3-772c-4a14-afdf-5a8376851ff4",
   "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": "d95fafdc-643a-40ea-a689-200bd132e90c",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4adfb4de-cd79-4913-a1af-9e23e9e236c9",
   "metadata": {},
   "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": "145082e5-ced4-47ae-88c0-cb69773e3c5a",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "8aa77372-7ed3-4da7-abc9-d30372106139",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class StocH(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        return x\n",
      "\n",
      "    def postprocess(self, x):\n",
      "        return x\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.StocH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = pya.models.StocH()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51f8615e-01fa-4aa5-b196-3ee2b35d261c",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6601da9e-8adc-44ee-9308-75e3cd31b816",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"stoch\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: DNA methylation clocks\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: human cohort\n",
    "model.metadata[\"year\"] = 2024\n",
    "model.metadata[\"approved_by_author\"] = \"✅\"\n",
    "model.metadata[\"citation\"] = \"Tong, Huige, et al. \\\"Quantifying the stochastic component of epigenetic aging.\\\" Nature Aging 4 (2024): 886–901.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s43587-024-00600-8\"\n",
    "model.metadata[\"notes\"] = \"Stochastic chronological-age clock built from simulated methylation trajectories at the Horvath clock CpGs; it is a stochastic counterpart, not the original Horvath clock.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"sorted monocytes\"]  # Paper: Illumina 450k DNAm data of sorted monocyte samples from 1,202 donors\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: machine learning predictors of chronological age\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: artificial cohorts from which machine learning predictor of age can be derived\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: estimate DNAm-Age\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: elastic-net regression\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\"]  # Paper: Illumina 450k DNAm data of sorted monocyte samples\n",
    "model.metadata[\"population\"] = \"adults\"  # Paper: MESA monocytes: minimum age 44 years, maximum age 83 years\n",
    "model.metadata[\"journal\"] = \"Nature Aging\"\n",
    "model.metadata[\"last_author\"] = \"Andrew E. Teschendorff\"\n",
    "model.metadata[\"n_features\"] = 353\n",
    "model.metadata[\"citations\"] = 66\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "74492239-5aae-4026-9d90-6bc9c574c110",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "192924bd-8553-4840-85e9-3ea02b024b79",
   "metadata": {},
   "source": [
    "#### Download directly with curl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6675770e-a5d1-40ab-93e1-775f288fed1c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://figshare.com/ndownloader/files/42406308\"\n",
    "supplementary_file_name = \"glmStocAll.Rd\"\n",
    "os.system(f\"curl -L -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aeee6c5a-4e0a-4f2a-acef-d657596f453a",
   "metadata": {},
   "source": [
    "#### Download from R package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d81f2c9d-362f-43cb-ad52-012e28217164",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing download.r\n"
     ]
    }
   ],
   "source": [
    "%%writefile download.r\n",
    "\n",
    "options(repos = c(CRAN = \"https://cloud.r-project.org/\"))\n",
    "\n",
    "# Function to extract and save coefficients and intercepts\n",
    "ExtractCoefficients <- function(){\n",
    "  load(\"glmStocALL.Rd\")  # Load in stochastic clock information\n",
    "\n",
    "  # Check the loaded object structure\n",
    "  if (!exists(\"glmStocALL.lo\")) {\n",
    "    stop(\"The object glmStocALL.lo was not found in the loaded .Rd file.\")\n",
    "  }\n",
    "\n",
    "  # List to store coefficients and intercepts for each clock\n",
    "  coefficients_list <- list()\n",
    "\n",
    "  for (c in 1:length(glmStocALL.lo)) {\n",
    "    glm.o <- glmStocALL.lo[[c]]\n",
    "\n",
    "    # Ensure glm.o is a glmnet object\n",
    "    if (!inherits(glm.o, \"glmnet\")) {\n",
    "      warning(paste(\"Object at index\", c, \"is not a glmnet object. Skipping.\"))\n",
    "      next\n",
    "    }\n",
    "\n",
    "    # Extract the coefficients and intercept from the final iteration\n",
    "    intercept <- glm.o$a0[length(glm.o$a0)]\n",
    "    coefficients <- as.matrix(glm.o$beta)[, length(glm.o$lambda)]\n",
    "\n",
    "    print(length(coefficients))\n",
    "    print(length(rownames(coefficients)))\n",
    "\n",
    "    # Create a data frame with feature names and coefficients\n",
    "    coef_df <- data.frame(\n",
    "      Feature = rownames(as.matrix(glm.o$beta)),\n",
    "      Coefficient = as.numeric(coefficients),\n",
    "      Intercept = rep(intercept, length(coefficients))\n",
    "    )\n",
    "    \n",
    "    # Save each clock's coefficients to a CSV file\n",
    "    write.csv(coef_df, file = paste0(\"Coefficients_Clock_\", c, \".csv\"), row.names = FALSE)\n",
    "    \n",
    "    # Append to the list\n",
    "    coefficients_list[[c]] <- coef_df\n",
    "  }\n",
    "\n",
    "  return(coefficients_list)  # Return the list for further inspection if needed\n",
    "}\n",
    "\n",
    "# Run the function\n",
    "coefficients_list <- ExtractCoefficients()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1ce2bac8-dd33-46cb-a7b6-14a1d0976f05",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(\"Rscript download.r\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "84930b94-fff8-4e1f-85ef-2194e8a8ee4f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dbb77f97-01d4-4c63-aa40-ee24de8bc0e9",
   "metadata": {},
   "source": [
    "#### From CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "110a5ded-d25f-4cef-8e84-4f51210dfc26",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('Coefficients_Clock_1.csv')\n",
    "df['feature'] = df['Feature']\n",
    "df['coefficient'] = df['Coefficient']\n",
    "model.features = df['feature'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f81dd175-8773-47da-864a-643f45195bf2",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e09b3463-4fd4-41b1-ac21-e63ddd223fe0",
   "metadata": {},
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'].tolist()).unsqueeze(0)\n",
    "intercept = torch.tensor([df['Intercept'][0]])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3bbfeba6-07a3-49c6-b56a-0b9c1c882167",
   "metadata": {},
   "source": [
    "#### Linear model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d7f43b99-26f2-4622-9a76-316712058877",
   "metadata": {},
   "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": "b43d29e6-ec61-450c-be21-989ad9eaebb4",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ade0f4c9-2298-4fc3-bb72-d200907dd731",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b42caeae-f255-45aa-9f00-3bed6ef7d26f",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7a22fb20-c605-424d-8efb-7620c2c0755c",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ff4a21cb-cf41-44dc-9ed1-95cf8aa15772",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2466d7e7-5f1e-4d4a-81f4-721e56958378",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "2168355c-47d9-475d-b816-49f65e74887c",
   "metadata": {},
   "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. \"Quantifying the stochastic component of '\n",
      "             'epigenetic aging.\" Nature Aging (2024): 1-16.',\n",
      " 'clock_name': 'stoch',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s43587-024-00600-8',\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: ['cg00075967', 'cg00374717', 'cg00864867', 'cg00945507', 'cg01027739', 'cg01353448', 'cg01584473', 'cg01644850', 'cg01656216', 'cg01873645', 'cg01968178', 'cg02085507', 'cg02154074', 'cg02217159', 'cg02331561', 'cg02332492', 'cg02364642', 'cg02388150', 'cg02479575', 'cg02489552', 'cg02580606', 'cg02654291', 'cg02827112', 'cg02972551', 'cg03103192', 'cg03167275', 'cg03270204', 'cg03565323', 'cg03588357', 'cg03760483']... [Total elements: 353]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=353, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [3.585235357284546, 0.29056739807128906, 0.008150330744683743, 7.167356014251709, 0.07318803668022156, 0.14952702820301056, -0.12038026005029678, -0.6500811576843262, -0.24336983263492584, 0.24592465162277222, -8.944670844357461e-05, -0.2048512101173401, 0.3703913986682892, -1.0299664735794067, 1.7403517961502075, -0.7057934403419495, 0.5467443466186523, 5.111024856567383, 7.80165433883667, 4.5496368408203125, 0.3366563022136688, 1.6183545589447021, 0.034926775842905045, -5.03125524520874, 6.2505011558532715, -2.024871349334717, 0.145379438996315, 0.5371573567390442, -0.9422363042831421, 0.05253010243177414]... [Tensor of shape torch.Size([1, 353])]\n",
      "base_model.linear.bias: tensor([59.8016])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "78e2387c-6de1-4073-b4a5-b8b8e430abdb",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "936b9877-d076-4ced-99aa-e8d4c58c5caf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 18.5127],\n",
       "        [146.4057],\n",
       "        [166.5776],\n",
       "        [ 85.6306],\n",
       "        [379.5047],\n",
       "        [-99.5351],\n",
       "        [ 42.5195],\n",
       "        [234.2738],\n",
       "        [213.7955],\n",
       "        [ 62.3945]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "execution_count": 15,
     "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": "75642087-b880-429b-b19b-c1eaea33614f",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "5ef2fa8d-c80b-4fdd-8555-79c0d541788e",
   "metadata": {},
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f65d9bb5-5baa-486b-bf25-f68f542bd5b7",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "11aeaa70-44c0-42f9-86d7-740e3849a7a6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: glmStocAll.Rd\n",
      "Deleted file: download.r\n",
      "Deleted folder: .ipynb_checkpoints\n",
      "Deleted file: Coefficients_Clock_3.csv\n",
      "Deleted file: Coefficients_Clock_2.csv\n",
      "Deleted file: Coefficients_Clock_1.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",
   "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": "3.9.17"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}