{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# Meer"
   ]
  },
  {
   "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": "2025-04-07T18:07:26.345739Z",
     "iopub.status.busy": "2025-04-07T18:07:26.345377Z",
     "iopub.status.idle": "2025-04-07T18:07:27.890266Z",
     "shell.execute_reply": "2025-04-07T18:07:27.889940Z"
    }
   },
   "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": "2025-04-07T18:07:27.891920Z",
     "iopub.status.busy": "2025-04-07T18:07:27.891696Z",
     "iopub.status.idle": "2025-04-07T18:07:27.900254Z",
     "shell.execute_reply": "2025-04-07T18:07:27.899972Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Meer(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",
      "        Transforms age in days to age in months.\n",
      "        \"\"\"\n",
      "        return x / 30.5\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.Meer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:27.901558Z",
     "iopub.status.busy": "2025-04-07T18:07:27.901460Z",
     "iopub.status.idle": "2025-04-07T18:07:27.903244Z",
     "shell.execute_reply": "2025-04-07T18:07:27.902985Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Meer()"
   ]
  },
  {
   "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": "2025-04-07T18:07:27.904531Z",
     "iopub.status.busy": "2025-04-07T18:07:27.904447Z",
     "iopub.status.idle": "2025-04-07T18:07:27.906569Z",
     "shell.execute_reply": "2025-04-07T18:07:27.906335Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"meer\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: A whole-lifespan mouse multi-tissue DNA methylation age predictor.\n",
    "model.metadata[\"species\"] = \"Mus musculus\"  # Paper: A whole-lifespan mouse multi-tissue DNA methylation age predictor.\n",
    "model.metadata[\"year\"] = 2018\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Meer, M. V., Podolskiy, D. I., Tyshkovskiy, A. & Gladyshev, V. N. A whole lifespan mouse multi-tissue DNA methylation clock. eLife 7, e40675 (2018).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.7554/elife.40675\"\n",
    "model.metadata[\"notes\"] = \"Whole Lifespan Multi-Tissue (WLMT) mouse clock trained by elastic net on RRBS methylation percentages from untreated wild-type C57BL/6 samples.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"multi-tissue\"]  # Paper: The combined dataset represented 11 tissues and cell types.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: A whole-lifespan mouse multi-tissue DNA methylation age predictor.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: The method is based on chronological age.\n",
    "model.metadata[\"unit\"] = [\"days\"]  # Paper: Training and test MAE were reported in days.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: Elastic net regression with 10-fold cross-validation.\n",
    "model.metadata[\"platform\"] = [\"RRBS\"]  # Paper: Only RRBS data were used to construct the clock.\n",
    "model.metadata[\"population\"] = \"mice\"  # Paper: Mice ranged from 1 week to 35 months; untreated wild-type C57BL/6 were used.\n",
    "model.metadata[\"journal\"] = \"eLife\"\n",
    "model.metadata[\"last_author\"] = \"Vadim N. Gladyshev\"\n",
    "model.metadata[\"n_features\"] = 435\n",
    "model.metadata[\"citations\"] = 203\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": "d382bb34-56d2-498f-b5a6-22cde82a5790",
   "metadata": {},
   "source": [
    "#### Download directly with curl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b48a0c22-99c0-4e11-95ce-05ff2a556e06",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:27.907899Z",
     "iopub.status.busy": "2025-04-07T18:07:27.907820Z",
     "iopub.status.idle": "2025-04-07T18:07:28.427572Z",
     "shell.execute_reply": "2025-04-07T18:07:28.426774Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supplementary_url = \"https://elifesciences.org/download/aHR0cHM6Ly9jZG4uZWxpZmVzY2llbmNlcy5vcmcvYXJ0aWNsZXMvNDA2NzUvZWxpZmUtNDA2NzUtc3VwcDMtdjIueGxzeA--/elife-40675-supp3-v2.xlsx?_hash=qzOMc4yUFACfDFG%2FlgxkFTHWt%2BSXSmP9zz1BM3oOTRM%3D\"\n",
    "supplementary_file_name = \"coefficients.xlsx\"\n",
    "os.system(f\"curl -o {supplementary_file_name} {supplementary_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5035b180-3d1b-4432-8ebe-b9c92bd93a7f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "793d7b24-b1ef-4dd2-ac26-079f7b67fba7",
   "metadata": {},
   "source": [
    "#### From Excel file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "110a5ded-d25f-4cef-8e84-4f51210dfc26",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.431037Z",
     "iopub.status.busy": "2025-04-07T18:07:28.430745Z",
     "iopub.status.idle": "2025-04-07T18:07:28.555299Z",
     "shell.execute_reply": "2025-04-07T18:07:28.554961Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_excel('coefficients.xlsx', sheet_name='Whole lifespan multi-tissue', nrows=435)\n",
    "df['feature'] = df['Chromosome'].astype(str) + ':' + df['Position'].astype(int).astype(str)\n",
    "df['coefficient'] = df['Weight']*100\n",
    "\n",
    "model.features = features = df['feature'].tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee6d8fa0-4767-4c45-9717-eb1c95e2ddc0",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e09b3463-4fd4-41b1-ac21-e63ddd223fe0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.556898Z",
     "iopub.status.busy": "2025-04-07T18:07:28.556799Z",
     "iopub.status.idle": "2025-04-07T18:07:28.558889Z",
     "shell.execute_reply": "2025-04-07T18:07:28.558655Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'].tolist()).unsqueeze(0)\n",
    "intercept = torch.tensor([234.64])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad261636-5b00-4979-bb1d-67a851f7aa19",
   "metadata": {},
   "source": [
    "#### Linear model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d7f43b99-26f2-4622-9a76-316712058877",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.560223Z",
     "iopub.status.busy": "2025-04-07T18:07:28.560120Z",
     "iopub.status.idle": "2025-04-07T18:07:28.562273Z",
     "shell.execute_reply": "2025-04-07T18:07:28.562021Z"
    }
   },
   "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": "code",
   "execution_count": 9,
   "id": "ade0f4c9-2298-4fc3-bb72-d200907dd731",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.563535Z",
     "iopub.status.busy": "2025-04-07T18:07:28.563424Z",
     "iopub.status.idle": "2025-04-07T18:07:28.565041Z",
     "shell.execute_reply": "2025-04-07T18:07:28.564807Z"
    }
   },
   "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": 10,
   "id": "7a22fb20-c605-424d-8efb-7620c2c0755c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.566363Z",
     "iopub.status.busy": "2025-04-07T18:07:28.566280Z",
     "iopub.status.idle": "2025-04-07T18:07:28.567955Z",
     "shell.execute_reply": "2025-04-07T18:07:28.567709Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ff4a21cb-cf41-44dc-9ed1-95cf8aa15772",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.569136Z",
     "iopub.status.busy": "2025-04-07T18:07:28.569055Z",
     "iopub.status.idle": "2025-04-07T18:07:28.570649Z",
     "shell.execute_reply": "2025-04-07T18:07:28.570378Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\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": 12,
   "id": "2168355c-47d9-475d-b816-49f65e74887c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.571859Z",
     "iopub.status.busy": "2025-04-07T18:07:28.571779Z",
     "iopub.status.idle": "2025-04-07T18:07:28.575093Z",
     "shell.execute_reply": "2025-04-07T18:07:28.574864Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Meer, Margarita V., et al. \"A whole lifespan mouse multi-tissue '\n",
      "             'DNA methylation clock.\" Elife 7 (2018): e40675.',\n",
      " 'clock_name': 'meer',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.7554/eLife.40675',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Mus musculus',\n",
      " 'version': None,\n",
      " 'year': 2018}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['chr10:111559529', 'chr10:115250413', 'chr10:118803606', 'chr10:121498258', 'chr10:127620127', 'chr10:19970189', 'chr10:19970209', 'chr10:33624567', 'chr10:42644582', 'chr10:4621215', 'chr10:57795976', 'chr10:60698046', 'chr10:61828281', 'chr10:63820265', 'chr10:67979197', 'chr10:68137630', 'chr10:75014983', 'chr10:78273866', 'chr10:78487669', 'chr10:80182188', 'chr10:80534973', 'chr10:84760142', 'chr11:100367639', 'chr11:102255939', 'chr11:107372077', 'chr11:114423667', 'chr11:114479395', 'chr11:115989660', 'chr11:116515706', 'chr11:117175709']... [Total elements: 435]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=435, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [9.368049621582031, -4.492888927459717, -2.932995080947876, -2.1226966381073, -16.623489379882812, -2.7541234493255615, -9.462428092956543, 15.378312110900879, 22.142602920532227, 2.114746570587158, -7.513723373413086, 11.303533554077148, -12.452217102050781, -0.46204015612602234, -14.366745948791504, -9.18408203125, -6.437520503997803, -8.584598541259766, -7.610683917999268, -6.5796918869018555, 5.641702175140381, 1.8415330648422241, -12.470565795898438, 1.1288938522338867, -17.48339080810547, 14.172774314880371, 0.42071831226348877, -0.3068951964378357, 0.634797215461731, 6.434844493865967]... [Tensor of shape torch.Size([1, 435])]\n",
      "base_model.linear.bias: tensor([234.6400])\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": 13,
   "id": "936b9877-d076-4ced-99aa-e8d4c58c5caf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.576366Z",
     "iopub.status.busy": "2025-04-07T18:07:28.576280Z",
     "iopub.status.idle": "2025-04-07T18:07:28.580120Z",
     "shell.execute_reply": "2025-04-07T18:07:28.579879Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[20.9082],\n",
       "        [ 4.7668],\n",
       "        [17.3136],\n",
       "        [12.6321],\n",
       "        [-2.8595],\n",
       "        [ 1.7717],\n",
       "        [-4.0258],\n",
       "        [ 8.8037],\n",
       "        [21.6245],\n",
       "        [13.8154]], dtype=torch.float64, grad_fn=<DivBackward0>)"
      ]
     },
     "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": "fe8299d7-9285-4e22-82fd-b664434b4369",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "5ef2fa8d-c80b-4fdd-8555-79c0d541788e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.581350Z",
     "iopub.status.busy": "2025-04-07T18:07:28.581263Z",
     "iopub.status.idle": "2025-04-07T18:07:28.583879Z",
     "shell.execute_reply": "2025-04-07T18:07:28.583639Z"
    }
   },
   "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": 15,
   "id": "11aeaa70-44c0-42f9-86d7-740e3849a7a6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:07:28.585094Z",
     "iopub.status.busy": "2025-04-07T18:07:28.585008Z",
     "iopub.status.idle": "2025-04-07T18:07:28.588129Z",
     "shell.execute_reply": "2025-04-07T18:07:28.587904Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: coefficients.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",
   "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
}