{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# MammalianLifespan"
   ]
  },
  {
   "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": "2025-04-07T18:02:45.960676Z",
     "iopub.status.busy": "2025-04-07T18:02:45.960314Z",
     "iopub.status.idle": "2025-04-07T18:02:47.353828Z",
     "shell.execute_reply": "2025-04-07T18:02:47.353514Z"
    }
   },
   "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": "2025-04-07T18:02:47.355528Z",
     "iopub.status.busy": "2025-04-07T18:02:47.355313Z",
     "iopub.status.idle": "2025-04-07T18:02:47.363690Z",
     "shell.execute_reply": "2025-04-07T18:02:47.363417Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class MammalianLifespan(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-log transformation.\n",
      "        \"\"\"\n",
      "        return torch.exp(x)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.MammalianLifespan)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:02:47.364994Z",
     "iopub.status.busy": "2025-04-07T18:02:47.364911Z",
     "iopub.status.idle": "2025-04-07T18:02:47.366564Z",
     "shell.execute_reply": "2025-04-07T18:02:47.366333Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.MammalianLifespan()"
   ]
  },
  {
   "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": "2025-04-07T18:02:47.367840Z",
     "iopub.status.busy": "2025-04-07T18:02:47.367757Z",
     "iopub.status.idle": "2025-04-07T18:02:47.369735Z",
     "shell.execute_reply": "2025-04-07T18:02:47.369481Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"mammalianlifespan\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The model is based on DNA methylation measurements.\n",
    "model.metadata[\"species\"] = \"multiple species\"  # Paper: The study samples are multi.\n",
    "model.metadata[\"year\"] = 2024\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Li, Caesar Z., et al. \\\"Epigenetic predictors of species maximum life span and other life-history traits in mammals.\\\" Science Advances 10.23 (2024): eadm7273.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1126/sciadv.adm7273\"\n",
    "model.metadata[\"notes\"] = \"Pan-mammalian tissue-agnostic elastic-net predictor fitted to log species maximum life span from conserved CpG methylation; pyaging exponentiates the linear output to years.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"multi-tissue\"]  # Paper: These samples spanned 59 unique tissue types and originated from 348 distinct mammalian species across 25 taxonomic orders.\n",
    "model.metadata[\"predicts\"] = [\"species maximum lifespan\"]  # Paper: We will refer to the predicted maximum life span, expressed in log years, as either the epigenetic maximum life span or DNAm maximum life span.\n",
    "model.metadata[\"training_target\"] = [\"species maximum lifespan\"]  # Paper: We used three distinct penalized regression models to predict the log-transformed values of maximum life span, gestation time, and age at sexual maturity for each species.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: We will refer to the predicted maximum life span, expressed in log years, as either the epigenetic maximum life span or DNAm maximum life span.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: First, we used elastic net regression models to predict maximum life span using both CpG methylation data and taxonomic order indicators.\n",
    "model.metadata[\"platform\"] = [\"Horvath MammalMethylChip40\"]  # Paper: All data were generated using the mammalian methylation array (HorvathMammalMethylChip40), which provides high sequencing depth of highly conserved CpGs in mammals.\n",
    "model.metadata[\"population\"] = \"multiple mammalian species\"  # Paper: Leveraging our publicly accessible data from the Mammalian Methylation Consortium, we focused on highly conserved cytosine methylation profiles from n = 15,000 DNA samples. These samples spanned 59 unique tissue types and originated from 348 distinct mammalian species across 25 taxonomic orders.\n",
    "model.metadata[\"journal\"] = \"Science Advances\"\n",
    "model.metadata[\"last_author\"] = \"Steve Horvath\"\n",
    "model.metadata[\"n_features\"] = 152  # Paper: The official LifespanPredictor_40K_Li2021.csv contains 152 nonzero non-intercept CpG coefficients.\n",
    "model.metadata[\"citations\"] = 5\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": "60a207cd-1a40-43bd-a93f-73de43358162",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fc5e4c40-38e1-4db5-9dcd-15379d32aa90",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T18:02:47.371056Z",
     "iopub.status.busy": "2025-04-07T18:02:47.370971Z",
     "iopub.status.idle": "2025-04-07T18:02:48.784711Z",
     "shell.execute_reply": "2025-04-07T18:02:48.784376Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/caeseriousli/MammalianMethylationPredictors.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": "2025-04-07T18:02:48.786289Z",
     "iopub.status.busy": "2025-04-07T18:02:48.786178Z",
     "iopub.status.idle": "2025-04-07T18:02:48.795076Z",
     "shell.execute_reply": "2025-04-07T18:02:48.794785Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('MammalianMethylationPredictors/Predictors/LifespanPredictor_40K_Li2021.csv')\n",
    "df['feature'] = df['CpG']\n",
    "df['coefficient'] = df['Coefficient']\n",
    "df = df[df.Coefficient != 0]\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": "2025-04-07T18:02:48.796541Z",
     "iopub.status.busy": "2025-04-07T18:02:48.796451Z",
     "iopub.status.idle": "2025-04-07T18:02:48.798520Z",
     "shell.execute_reply": "2025-04-07T18:02:48.798269Z"
    }
   },
   "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": "2025-04-07T18:02:48.799874Z",
     "iopub.status.busy": "2025-04-07T18:02:48.799784Z",
     "iopub.status.idle": "2025-04-07T18:02:48.801901Z",
     "shell.execute_reply": "2025-04-07T18:02:48.801647Z"
    }
   },
   "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": "2025-04-07T18:02:48.803212Z",
     "iopub.status.busy": "2025-04-07T18:02:48.803129Z",
     "iopub.status.idle": "2025-04-07T18:02:48.804672Z",
     "shell.execute_reply": "2025-04-07T18:02:48.804404Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = [0.5] * len(model.features)"
   ]
  },
  {
   "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": "2025-04-07T18:02:48.805882Z",
     "iopub.status.busy": "2025-04-07T18:02:48.805801Z",
     "iopub.status.idle": "2025-04-07T18:02:48.807253Z",
     "shell.execute_reply": "2025-04-07T18:02:48.807012Z"
    }
   },
   "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": "2025-04-07T18:02:48.808914Z",
     "iopub.status.busy": "2025-04-07T18:02:48.808789Z",
     "iopub.status.idle": "2025-04-07T18:02:48.810395Z",
     "shell.execute_reply": "2025-04-07T18:02:48.810138Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'anti_log'\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": "2025-04-07T18:02:48.811618Z",
     "iopub.status.busy": "2025-04-07T18:02:48.811535Z",
     "iopub.status.idle": "2025-04-07T18:02:48.814854Z",
     "shell.execute_reply": "2025-04-07T18:02:48.814613Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Li, Caesar Z., et al. \"Epigenetic predictors of species maximum '\n",
      "             'lifespan and other life history traits in mammals.\" bioRxiv '\n",
      "             '(2023): 2023-11.',\n",
      " 'clock_name': 'mammalianlifespan',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1101/2023.11.02.565286',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'multi',\n",
      " 'version': None,\n",
      " 'year': 2023}\n",
      "reference_values: [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5]... [Total elements: 152]\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'anti_log'\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00039845', 'cg00300233', 'cg00810217', 'cg01020408', 'cg01266508', 'cg01309159', 'cg01786675', 'cg02476543', 'cg02574410', 'cg02725055', 'cg02871478', 'cg03230916', 'cg03264110', 'cg03280886', 'cg03528345', 'cg03537184', 'cg03684591', 'cg03820088', 'cg04065686', 'cg04118146', 'cg04313551', 'cg04324237', 'cg04486940', 'cg04499301', 'cg04725401', 'cg04918691', 'cg04958799', 'cg05035746', 'cg05039938', 'cg05151611']... [Total elements: 152]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=152, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.04147933050990105, 0.4304673969745636, 0.07260479032993317, 0.10754379630088806, 0.05837688222527504, 0.21564741432666779, 0.22965361177921295, 0.0423436276614666, -0.6524762511253357, -0.3474166989326477, 0.05646226927638054, 0.046050943434238434, -0.03867235779762268, -0.14654619991779327, 0.29777470231056213, -0.22357487678527832, 0.19166646897792816, 0.015969855710864067, 0.12260589003562927, 0.07850058376789093, 0.11844679713249207, 0.1271219253540039, -0.3257320821285248, -0.0814819186925888, 0.1456708163022995, 0.037799667567014694, 0.19944973289966583, -0.14140872657299042, -0.0007183622219599783, 0.28238773345947266]... [Tensor of shape torch.Size([1, 152])]\n",
      "base_model.linear.bias: tensor([-2.8285])\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": "2025-04-07T18:02:48.816277Z",
     "iopub.status.busy": "2025-04-07T18:02:48.816155Z",
     "iopub.status.idle": "2025-04-07T18:02:48.819909Z",
     "shell.execute_reply": "2025-04-07T18:02:48.819653Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[1.8245e+00],\n",
       "        [7.4422e-04],\n",
       "        [1.6053e+00],\n",
       "        [2.6872e-01],\n",
       "        [3.1673e-03],\n",
       "        [2.4528e+01],\n",
       "        [5.4639e+00],\n",
       "        [1.6672e-02],\n",
       "        [1.2177e-01],\n",
       "        [1.5087e-02]], dtype=torch.float64, grad_fn=<ExpBackward0>)"
      ]
     },
     "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": "2025-04-07T18:02:48.821162Z",
     "iopub.status.busy": "2025-04-07T18:02:48.821083Z",
     "iopub.status.idle": "2025-04-07T18:02:48.823582Z",
     "shell.execute_reply": "2025-04-07T18:02:48.823330Z"
    }
   },
   "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": "2025-04-07T18:02:48.824844Z",
     "iopub.status.busy": "2025-04-07T18:02:48.824751Z",
     "iopub.status.idle": "2025-04-07T18:02:48.833418Z",
     "shell.execute_reply": "2025-04-07T18:02:48.833160Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted folder: MammalianMethylationPredictors\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
}