{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# Mammalian1"
   ]
  },
  {
   "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": "2025-04-07T17:52:25.879427Z",
     "iopub.status.busy": "2025-04-07T17:52:25.879024Z",
     "iopub.status.idle": "2025-04-07T17:52:27.262351Z",
     "shell.execute_reply": "2025-04-07T17:52:27.262006Z"
    }
   },
   "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": "2025-04-07T17:52:27.264090Z",
     "iopub.status.busy": "2025-04-07T17:52:27.263870Z",
     "iopub.status.idle": "2025-04-07T17:52:27.271225Z",
     "shell.execute_reply": "2025-04-07T17:52:27.270947Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Mammalian1(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 transformation with an offset of -2.\n",
      "        \"\"\"\n",
      "        return torch.exp(x) - 2\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.Mammalian1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:52:27.272501Z",
     "iopub.status.busy": "2025-04-07T17:52:27.272412Z",
     "iopub.status.idle": "2025-04-07T17:52:27.274021Z",
     "shell.execute_reply": "2025-04-07T17:52:27.273779Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Mammalian1()"
   ]
  },
  {
   "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": "2025-04-07T17:52:27.275343Z",
     "iopub.status.busy": "2025-04-07T17:52:27.275261Z",
     "iopub.status.idle": "2025-04-07T17:52:27.277257Z",
     "shell.execute_reply": "2025-04-07T17:52:27.276995Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"mammalian1\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: methylation\n",
    "model.metadata[\"species\"] = \"multiple species\"  # Paper: multi\n",
    "model.metadata[\"year\"] = 2023\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Lu, A. T., et al. \\\"Universal DNA methylation age across mammalian tissues.\\\" Nature Aging 3.9 (2023): 1144-1166.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s43587-023-00462-6\"\n",
    "model.metadata[\"notes\"] = \"Universal pan-mammalian clock 1: elastic-net regression of log-transformed chronological age on conserved mammalian-array CpGs, back-transformed to years.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"multi-tissue\"]  # Paper: multi-tissue\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: The official inverse transformation returns DNAm chronological age in years.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: log-transformed chronological age\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: The official inverse transformation returns DNAm chronological age in years.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: Elastic net\n",
    "model.metadata[\"platform\"] = [\"Horvath MammalMethylChip40\"]  # Paper: HorvathMammalMethylChip40\n",
    "model.metadata[\"population\"] = \"multiple mammalian species\"  # Paper: 11,754 samples from 185 mammalian species, prenatal to 139 years\n",
    "model.metadata[\"journal\"] = \"Nature Aging\"\n",
    "model.metadata[\"last_author\"] = \"Steve Horvath\"\n",
    "model.metadata[\"n_features\"] = 335\n",
    "model.metadata[\"citations\"] = 390\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": "5881f33e-0486-45d1-bd87-9c995f47ca62",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "e85525f7-6da4-4962-a7d5-0607e76eea33",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:52:27.278605Z",
     "iopub.status.busy": "2025-04-07T17:52:27.278524Z",
     "iopub.status.idle": "2025-04-07T17:54:14.063611Z",
     "shell.execute_reply": "2025-04-07T17:54:14.063129Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/shorvath/MammalianMethylationConsortium.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": 6,
   "id": "8a3d5de6-6303-487a-8b4d-e6345792f7be",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:54:14.066374Z",
     "iopub.status.busy": "2025-04-07T17:54:14.066025Z",
     "iopub.status.idle": "2025-04-07T17:54:14.072573Z",
     "shell.execute_reply": "2025-04-07T17:54:14.072206Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('MammalianMethylationConsortium/UniversalPanMammalianClock/ClockParameters/clock1.csv')\n",
    "df['feature'] = df['var']\n",
    "df['coefficient'] = df['beta_clock1']\n",
    "\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": 7,
   "id": "e09b3463-4fd4-41b1-ac21-e63ddd223fe0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:54:14.074085Z",
     "iopub.status.busy": "2025-04-07T17:54:14.073988Z",
     "iopub.status.idle": "2025-04-07T17:54:14.076024Z",
     "shell.execute_reply": "2025-04-07T17:54:14.075774Z"
    }
   },
   "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": 8,
   "id": "d7f43b99-26f2-4622-9a76-316712058877",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:54:14.077367Z",
     "iopub.status.busy": "2025-04-07T17:54:14.077278Z",
     "iopub.status.idle": "2025-04-07T17:54:14.079581Z",
     "shell.execute_reply": "2025-04-07T17:54:14.079343Z"
    }
   },
   "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": "2025-04-07T17:54:14.080784Z",
     "iopub.status.busy": "2025-04-07T17:54:14.080705Z",
     "iopub.status.idle": "2025-04-07T17:54:14.082183Z",
     "shell.execute_reply": "2025-04-07T17:54:14.081924Z"
    }
   },
   "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": "2025-04-07T17:54:14.083447Z",
     "iopub.status.busy": "2025-04-07T17:54:14.083365Z",
     "iopub.status.idle": "2025-04-07T17:54:14.084680Z",
     "shell.execute_reply": "2025-04-07T17:54:14.084455Z"
    }
   },
   "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": "2025-04-07T17:54:14.085902Z",
     "iopub.status.busy": "2025-04-07T17:54:14.085803Z",
     "iopub.status.idle": "2025-04-07T17:54:14.087266Z",
     "shell.execute_reply": "2025-04-07T17:54:14.087037Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'anti_logp2'\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": "2025-04-07T17:54:14.088406Z",
     "iopub.status.busy": "2025-04-07T17:54:14.088324Z",
     "iopub.status.idle": "2025-04-07T17:54:14.092557Z",
     "shell.execute_reply": "2025-04-07T17:54:14.092248Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Lu, A. T., et al. \"Universal DNA methylation age across '\n",
      "             'mammalian tissues.\" Nature aging 3.9 (2023): 1144-1166.',\n",
      " 'clock_name': 'mammalian1',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s43587-023-00462-6',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'multi',\n",
      " 'version': None,\n",
      " 'year': 2023}\n",
      "reference_values: None\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'anti_logp2'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00249943', 'cg00250826', 'cg00292639', 'cg00362836', 'cg00411555', 'cg00513357', 'cg00587168', 'cg00593462', 'cg00687674', 'cg00694357', 'cg00900456', 'cg00954002', 'cg01009870', 'cg01019040', 'cg01059743', 'cg01136078', 'cg01153166', 'cg01169686', 'cg01246498', 'cg01429475', 'cg01511232', 'cg01656216', 'cg01698540', 'cg01794235', 'cg01975510', 'cg02474352', 'cg02499612', 'cg02532525', 'cg02606236', 'cg02692845']... [Total elements: 335]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=335, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.1527862846851349, 0.0027701049111783504, -0.12989148497581482, 0.048629630357027054, -0.03136558085680008, 0.09142599999904633, 0.055298686027526855, 0.4379110336303711, -0.1408686339855194, -0.808471143245697, -0.03339824452996254, -0.12297524511814117, 0.10108527541160583, -0.004560905043035746, -0.20634084939956665, -0.0016184860141947865, 0.07213742285966873, -0.03695621341466904, 0.052970658987760544, 0.17211447656154633, 0.037939656525850296, 0.04749084636569023, 0.0619727298617363, 0.04738111421465874, 0.05404146388173103, 0.055779341608285904, -0.04102899879217148, 0.1298285871744156, -0.020354116335511208, -0.0109869921579957]... [Tensor of shape torch.Size([1, 335])]\n",
      "base_model.linear.bias: tensor([1.4314])\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": "2025-04-07T17:54:14.093889Z",
     "iopub.status.busy": "2025-04-07T17:54:14.093797Z",
     "iopub.status.idle": "2025-04-07T17:54:14.099279Z",
     "shell.execute_reply": "2025-04-07T17:54:14.098988Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-1.9999e+00],\n",
       "        [-1.2721e+00],\n",
       "        [ 6.0199e+00],\n",
       "        [ 1.5016e+00],\n",
       "        [ 3.6253e+02],\n",
       "        [ 1.1582e+01],\n",
       "        [-1.8921e+00],\n",
       "        [ 2.7133e+03],\n",
       "        [ 2.1860e+01],\n",
       "        [ 8.6071e+00]], dtype=torch.float64, grad_fn=<SubBackward0>)"
      ]
     },
     "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": "2025-04-07T17:54:14.100586Z",
     "iopub.status.busy": "2025-04-07T17:54:14.100486Z",
     "iopub.status.idle": "2025-04-07T17:54:14.102917Z",
     "shell.execute_reply": "2025-04-07T17:54:14.102639Z"
    }
   },
   "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": "2025-04-07T17:54:14.104269Z",
     "iopub.status.busy": "2025-04-07T17:54:14.104178Z",
     "iopub.status.idle": "2025-04-07T17:54:14.244927Z",
     "shell.execute_reply": "2025-04-07T17:54:14.244638Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted folder: MammalianMethylationConsortium\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
}