{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# PipekElasticNet"
   ]
  },
  {
   "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": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:35.543046Z",
     "iopub.status.busy": "2024-03-05T20:17:35.542686Z",
     "iopub.status.idle": "2024-03-05T20:17:36.906933Z",
     "shell.execute_reply": "2024-03-05T20:17:36.906611Z"
    }
   },
   "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": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:36.908872Z",
     "iopub.status.busy": "2024-03-05T20:17:36.908692Z",
     "iopub.status.idle": "2024-03-05T20:17:36.916189Z",
     "shell.execute_reply": "2024-03-05T20:17:36.915931Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class PipekElasticNet(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        return x\n",
      "\n",
      "    def postprocess(self, x):\n",
      "        \"\"\"\n",
      "        Applies an anti-logarithmic linear transformation to a PyTorch tensor.\n",
      "        \"\"\"\n",
      "        adult_age = 20\n",
      "\n",
      "        # Create a mask for negative and non-negative values\n",
      "        mask_negative = x < 0\n",
      "        mask_non_negative = ~mask_negative\n",
      "\n",
      "        # Initialize the result tensor\n",
      "        age_tensor = torch.empty_like(x)\n",
      "\n",
      "        # Exponential transformation for negative values\n",
      "        age_tensor[mask_negative] = (1 + adult_age) * torch.exp(x[mask_negative]) - 1\n",
      "\n",
      "        # Linear transformation for non-negative values\n",
      "        age_tensor[mask_non_negative] = (1 + adult_age) * x[mask_non_negative] + adult_age\n",
      "\n",
      "        return age_tensor\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.PipekElasticNet)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:36.917755Z",
     "iopub.status.busy": "2024-03-05T20:17:36.917671Z",
     "iopub.status.idle": "2024-03-05T20:17:36.919275Z",
     "shell.execute_reply": "2024-03-05T20:17:36.919020Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.PipekElasticNet()"
   ]
  },
  {
   "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": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:36.920750Z",
     "iopub.status.busy": "2024-03-05T20:17:36.920670Z",
     "iopub.status.idle": "2024-03-05T20:17:36.922611Z",
     "shell.execute_reply": "2024-03-05T20:17:36.922360Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"pipekelasticnet\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: DNA methylation age\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: human samples\n",
    "model.metadata[\"year\"] = 2022\n",
    "model.metadata[\"approved_by_author\"] = \"✅\"\n",
    "model.metadata[\"citation\"] = \"Pipek, Orsolya Anna, and István Csabai. \\\"A revised multi-tissue, multi-platform epigenetic clock model for methylation array data.\\\" Journal of Mathematical Chemistry 61 (2023): 376–388.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1007/s10910-022-01381-4\"\n",
    "model.metadata[\"notes\"] = \"Pan-tissue, cross-platform elastic-net chronological-age clock trained on all eligible CpGs; 239 CpGs retained non-zero coefficients.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"multi-tissue\"]  # Paper: samples of various source tissues\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: predicted DNAm age in years versus actual chronological age\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: chronological age information\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: chronological age (years); predicted DNAm age (years)\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: elasticNet (239) was trained on all training data and resulted in 239 CpG sites with a non-zero coefficient\n",
    "model.metadata[\"platform\"] = [\"Illumina 27K\", \"Illumina 450K\", \"Illumina EPIC\"]  # Paper: 27K, 450K and EPIC data\n",
    "model.metadata[\"population\"] = \"all ages\"  # Paper: training data covered a broad chronological-age range\n",
    "model.metadata[\"journal\"] = \"Journal of Mathematical Chemistry\"\n",
    "model.metadata[\"last_author\"] = \"István Csabai\"\n",
    "model.metadata[\"n_features\"] = 239\n",
    "model.metadata[\"citations\"] = 2\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": "9a5b163b-1b25-4c2f-ad0c-86f0f2ed39d0",
   "metadata": {},
   "source": [
    "#### Download directly with curl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "28fdcad4-1f62-4da7-b556-1ecc8cf3d0e0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:36.924119Z",
     "iopub.status.busy": "2024-03-05T20:17:36.924044Z",
     "iopub.status.idle": "2024-03-05T20:17:37.181539Z",
     "shell.execute_reply": "2024-03-05T20:17:37.180660Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "32768"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/pipekorsi/MepiClock.git\"\n",
    "github_folder_name = github_url.split('/')[-1].split('.')[0]\n",
    "os.system(f\"git clone {github_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5035b180-3d1b-4432-8ebe-b9c92bd93a7f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15f4af76-b93c-438c-b57f-f129d6e9ec99",
   "metadata": {},
   "source": [
    "#### From CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "6899a4e6",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('MepiClock/resources/model_coefficients.csv', sep=';')\n",
    "df['feature'] = df['probeID']\n",
    "df['coefficient'] = df['elasticNet (239)']\n",
    "df = df[df['coefficient'] != 0]\n",
    "model.features = df['feature'][1:].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee6d8fa0-4767-4c45-9717-eb1c95e2ddc0",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e09b3463-4fd4-41b1-ac21-e63ddd223fe0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.679505Z",
     "iopub.status.busy": "2024-03-05T20:17:37.679254Z",
     "iopub.status.idle": "2024-03-05T20:17:37.682953Z",
     "shell.execute_reply": "2024-03-05T20:17:37.682389Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'][1:].tolist()).unsqueeze(0)\n",
    "intercept = torch.tensor([df['coefficient'][0]])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad261636-5b00-4979-bb1d-67a851f7aa19",
   "metadata": {},
   "source": [
    "#### Linear model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d7f43b99-26f2-4622-9a76-316712058877",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.686070Z",
     "iopub.status.busy": "2024-03-05T20:17:37.685886Z",
     "iopub.status.idle": "2024-03-05T20:17:37.689293Z",
     "shell.execute_reply": "2024-03-05T20:17:37.688835Z"
    }
   },
   "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": "ad8b4c1d-9d57-48b7-9a30-bcfea7b747b1",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f7fdae64-096a-4640-ade7-6a17b78a01d5",
   "metadata": {},
   "source": [
    "#### From CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "86de757f-fb38-4bcb-b91e-fc3372d22aad",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.691973Z",
     "iopub.status.busy": "2024-03-05T20:17:37.691810Z",
     "iopub.status.idle": "2024-03-05T20:17:37.713422Z",
     "shell.execute_reply": "2024-03-05T20:17:37.713076Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af3bcf7b-74a8-4d21-9ccb-4de0c2b0516b",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "7a22fb20-c605-424d-8efb-7620c2c0755c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.715600Z",
     "iopub.status.busy": "2024-03-05T20:17:37.715468Z",
     "iopub.status.idle": "2024-03-05T20:17:37.717220Z",
     "shell.execute_reply": "2024-03-05T20:17:37.716911Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ff4a21cb-cf41-44dc-9ed1-95cf8aa15772",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.719024Z",
     "iopub.status.busy": "2024-03-05T20:17:37.718901Z",
     "iopub.status.idle": "2024-03-05T20:17:37.720622Z",
     "shell.execute_reply": "2024-03-05T20:17:37.720306Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'anti_log_linear'\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86e3d6b1-e67e-4f3d-bd39-0ebec5726c3c",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "2168355c-47d9-475d-b816-49f65e74887c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.722338Z",
     "iopub.status.busy": "2024-03-05T20:17:37.722225Z",
     "iopub.status.idle": "2024-03-05T20:17:37.725744Z",
     "shell.execute_reply": "2024-03-05T20:17:37.725443Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '✅',\n",
      " 'citation': 'Pipek, Orsolya Anna, and István Csabai. \"A revised multi-tissue, '\n",
      "             'multi-platform epigenetic clock model for methylation array '\n",
      "             'data.\" Journal of Mathematical Chemistry 61.2 (2023): 376-388.',\n",
      " 'clock_name': 'pipekelasticnet',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1007/s10910-022-01381-4',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2022}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'anti_log_linear'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00027083', 'cg00059225', 'cg00075967', 'cg00168942', 'cg00290506', 'cg00343092', 'cg00528967', 'cg00651216', 'cg00812502', 'cg00864867', 'cg01222684', 'cg01262913', 'cg01294695', 'cg01353448', 'cg01407797', 'cg01459453', 'cg01485645', 'cg01507173', 'cg01511567', 'cg01570885', 'cg01580568', 'cg01580888', 'cg01860753', 'cg01968793', 'cg01994328', 'cg02217159', 'cg02275294', 'cg02332492', 'cg02335441', 'cg02388150']... [Total elements: 239]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=239, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.1439734548330307, 1.4801537990570068, 0.03225376456975937, -0.0058419122360646725, -0.9698857665061951, -0.02445327118039131, -0.25678759813308716, -0.1429552286863327, -0.45733991265296936, 0.03336525335907936, 0.06893794238567352, -0.016240336000919342, -0.028347602114081383, 0.08623908460140228, -0.006927416194230318, -0.4072648584842682, -0.11168642342090607, 0.0335581935942173, -1.1504876613616943, -0.18203186988830566, 0.06303419172763824, 0.7362451553344727, -0.01122856605798006, -0.1645817756652832, -0.3766438066959381, -0.22185027599334717, -0.14580827951431274, 0.11524636298418045, -0.07323136180639267, 0.19775758683681488]... [Tensor of shape torch.Size([1, 239])]\n",
      "base_model.linear.bias: tensor([0.3361])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "986d0262-e0c7-4036-b687-dee53ba392fb",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "936b9877-d076-4ced-99aa-e8d4c58c5caf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.727432Z",
     "iopub.status.busy": "2024-03-05T20:17:37.727339Z",
     "iopub.status.idle": "2024-03-05T20:17:37.731216Z",
     "shell.execute_reply": "2024-03-05T20:17:37.730942Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 26.4756],\n",
       "        [ 69.0214],\n",
       "        [ -0.9994],\n",
       "        [ -0.9954],\n",
       "        [  9.0836],\n",
       "        [204.6643],\n",
       "        [146.1240],\n",
       "        [ -0.9388],\n",
       "        [ 94.5212],\n",
       "        [ 54.5029]], dtype=torch.float64, grad_fn=<IndexPutBackward0>)"
      ]
     },
     "execution_count": 14,
     "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": "fe8299d7-9285-4e22-82fd-b664434b4369",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "5ef2fa8d-c80b-4fdd-8555-79c0d541788e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.732855Z",
     "iopub.status.busy": "2024-03-05T20:17:37.732762Z",
     "iopub.status.idle": "2024-03-05T20:17:37.735692Z",
     "shell.execute_reply": "2024-03-05T20:17:37.735426Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bac6257b-8d08-4a90-8d0b-7f745dc11ac1",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "11aeaa70-44c0-42f9-86d7-740e3849a7a6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T20:17:37.737247Z",
     "iopub.status.busy": "2024-03-05T20:17:37.737152Z",
     "iopub.status.idle": "2024-03-05T20:17:37.740189Z",
     "shell.execute_reply": "2024-03-05T20:17:37.739959Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: reference_feature_values.csv\n",
      "Deleted folder: MepiClock\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": "research",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}