{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# Thompson"
   ]
  },
  {
   "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": "2024-03-05T21:23:50.590960Z",
     "iopub.status.busy": "2024-03-05T21:23:50.590526Z",
     "iopub.status.idle": "2024-03-05T21:23:51.909586Z",
     "shell.execute_reply": "2024-03-05T21:23:51.909287Z"
    }
   },
   "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": "2024-03-05T21:23:51.911447Z",
     "iopub.status.busy": "2024-03-05T21:23:51.911275Z",
     "iopub.status.idle": "2024-03-05T21:23:51.920416Z",
     "shell.execute_reply": "2024-03-05T21:23:51.920153Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Thompson(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.Thompson)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:23:51.921838Z",
     "iopub.status.busy": "2024-03-05T21:23:51.921758Z",
     "iopub.status.idle": "2024-03-05T21:23:51.923419Z",
     "shell.execute_reply": "2024-03-05T21:23:51.923202Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Thompson()"
   ]
  },
  {
   "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": "2024-03-05T21:23:51.924881Z",
     "iopub.status.busy": "2024-03-05T21:23:51.924805Z",
     "iopub.status.idle": "2024-03-05T21:23:51.926695Z",
     "shell.execute_reply": "2024-03-05T21:23:51.926466Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"thompson\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The clocks use mouse CpG DNA-methylation frequencies.\n",
    "model.metadata[\"species\"] = \"Mus musculus\"  # Paper: The study develops full-lifespan epigenetic clocks for mice.\n",
    "model.metadata[\"year\"] = 2018\n",
    "model.metadata[\"approved_by_author\"] = \"✅\"\n",
    "model.metadata[\"citation\"] = \"Thompson, M. J., Chwiałkowska, K., Rubbi, L. et al. A multi-tissue full lifespan epigenetic clock for mice. Aging (Albany NY) 10, 2832–2854 (2018).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.18632/aging.101590\"\n",
    "model.metadata[\"notes\"] = \"Full-lifespan multi-tissue mouse DNA-methylation clock fit by elastic net to RRBS CpG methylation across 1,147 samples from ten tissues and multiple strains; the 582-site all-CpG model estimates chronological age and detects intervention- and genotype-associated age acceleration.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"adipose tissue\", \"blood\", \"cerebellum\", \"brain cortex\", \"heart\", \"kidney\", \"liver\", \"lung\", \"skeletal muscle\", \"spleen\"]  # Paper: Table 2 lists adipose, blood, kidney, liver, lung, muscle, cortex, heart, cerebellum, and spleen datasets.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: The clock estimates chronological age at DNA sample collection.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: Penalized regression predicts sample chronological age in months from CpG methylation.\n",
    "model.metadata[\"unit\"] = [\"months\"]  # Paper: Age errors and predictions are reported in months, and the released workflow returns predicted age in months.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: The all-CpG clock uses elastic net with alpha equal to 0.5.\n",
    "model.metadata[\"platform\"] = [\"RRBS\"]  # Paper: Methylation was measured with reduced-representation bisulfite sequencing.\n",
    "model.metadata[\"population\"] = \"mice\"  # Paper: The combined datasets span prenatal age through 32.2 months and include C57BL/6, BALB/c, Diversity Outbred, dwarf, GHRKO, and HMDP strains.\n",
    "model.metadata[\"journal\"] = \"Aging (Albany NY)\"\n",
    "model.metadata[\"last_author\"] = \"Matteo Pellegrini\"\n",
    "model.metadata[\"n_features\"] = 582\n",
    "model.metadata[\"citations\"] = 236\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": "08180e89-7f9b-4c12-ae7d-057c2e27effa",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a57b7849-9210-43d0-9c47-db7b524f6858",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:23:51.928212Z",
     "iopub.status.busy": "2024-03-05T21:23:51.928139Z",
     "iopub.status.idle": "2024-03-05T21:23:52.918934Z",
     "shell.execute_reply": "2024-03-05T21:23:52.918386Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/kerepesi/MouseAgingClocks.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": "2024-03-05T21:23:52.922018Z",
     "iopub.status.busy": "2024-03-05T21:23:52.921828Z",
     "iopub.status.idle": "2024-03-05T21:23:52.929443Z",
     "shell.execute_reply": "2024-03-05T21:23:52.929039Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_table('MouseAgingClocks/ClockData/Thompson2018-ElasticNet_aging_clock.txt', skiprows=1)\n",
    "intercept = df['Coefficient'].iloc[0]\n",
    "df = df[1:]\n",
    "df['feature'] = df['Chromosome'].astype(str) + ':' + df['Coordinate'].astype(int).astype(str)\n",
    "df['coefficient'] = df['Coefficient']\n",
    "\n",
    "model.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": "2024-03-05T21:23:52.931889Z",
     "iopub.status.busy": "2024-03-05T21:23:52.931727Z",
     "iopub.status.idle": "2024-03-05T21:23:52.934651Z",
     "shell.execute_reply": "2024-03-05T21:23:52.934242Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'].tolist()).unsqueeze(0)\n",
    "intercept = torch.tensor([intercept])"
   ]
  },
  {
   "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": "2024-03-05T21:23:52.936972Z",
     "iopub.status.busy": "2024-03-05T21:23:52.936810Z",
     "iopub.status.idle": "2024-03-05T21:23:52.939876Z",
     "shell.execute_reply": "2024-03-05T21:23:52.939516Z"
    }
   },
   "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": "2024-03-05T21:23:52.941971Z",
     "iopub.status.busy": "2024-03-05T21:23:52.941853Z",
     "iopub.status.idle": "2024-03-05T21:23:52.943777Z",
     "shell.execute_reply": "2024-03-05T21:23:52.943425Z"
    }
   },
   "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": "2024-03-05T21:23:52.945749Z",
     "iopub.status.busy": "2024-03-05T21:23:52.945651Z",
     "iopub.status.idle": "2024-03-05T21:23:52.947449Z",
     "shell.execute_reply": "2024-03-05T21:23:52.947120Z"
    }
   },
   "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": "2024-03-05T21:23:52.949165Z",
     "iopub.status.busy": "2024-03-05T21:23:52.949056Z",
     "iopub.status.idle": "2024-03-05T21:23:52.950882Z",
     "shell.execute_reply": "2024-03-05T21:23:52.950561Z"
    }
   },
   "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": "2024-03-05T21:23:52.952698Z",
     "iopub.status.busy": "2024-03-05T21:23:52.952598Z",
     "iopub.status.idle": "2024-03-05T21:23:52.956062Z",
     "shell.execute_reply": "2024-03-05T21:23:52.955790Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '✅',\n",
      " 'citation': 'Thompson, Michael J., et al. \"A multi-tissue full lifespan '\n",
      "             'epigenetic clock for mice.\" Aging (Albany NY) 10.10 (2018): '\n",
      "             '2832.',\n",
      " 'clock_name': 'thompson',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.18632/aging.101590',\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: ['chr1:9967422', 'chr1:9967428', 'chr1:13126576', 'chr1:15286937', 'chr1:46800385', 'chr1:55087536', 'chr1:63273286', 'chr1:63273288', 'chr1:64690282', 'chr1:71603645', 'chr1:79761546', 'chr1:79858375', 'chr1:84695279', 'chr1:84934769', 'chr1:89455649', 'chr1:92848744', 'chr1:92848748', 'chr1:95666316', 'chr1:103479589', 'chr1:105270925', 'chr1:106758726', 'chr1:118310888', 'chr1:118311288', 'chr1:119648512', 'chr1:120602265', 'chr1:120602331', 'chr1:128359556', 'chr1:132331689', 'chr1:132937328', 'chr1:135374481']... [Total elements: 582]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=582, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [0.7605000138282776, 0.12610000371932983, 4.3765997886657715, 5.6855998039245605, -0.5194000005722046, -0.6355000138282776, 0.41659998893737793, 1.2926000356674194, 5.576700210571289, -0.9544000029563904, -5.0493998527526855, -0.2711000144481659, 0.24879999458789825, -0.8901000022888184, 0.7444000244140625, 0.03920000046491623, 0.40560001134872437, -2.0560998916625977, 0.5519000291824341, -0.663100004196167, -0.8413000106811523, -3.921999931335449, -3.1031999588012695, -1.9629000425338745, 2.824700117111206, -0.3255000114440918, 1.7187999486923218, -1.5643999576568604, -0.7063000202178955, -2.196000099182129]... [Tensor of shape torch.Size([1, 582])]\n",
      "base_model.linear.bias: tensor([30.3172])\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": "2024-03-05T21:23:52.957798Z",
     "iopub.status.busy": "2024-03-05T21:23:52.957702Z",
     "iopub.status.idle": "2024-03-05T21:23:52.961506Z",
     "shell.execute_reply": "2024-03-05T21:23:52.961222Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[102.1936],\n",
       "        [ 83.5008],\n",
       "        [ 61.2582],\n",
       "        [-60.8014],\n",
       "        [-27.0123],\n",
       "        [ 77.8211],\n",
       "        [ 51.7655],\n",
       "        [ 57.8975],\n",
       "        [167.7028],\n",
       "        [ 52.8332]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "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": "2024-03-05T21:23:52.963133Z",
     "iopub.status.busy": "2024-03-05T21:23:52.963039Z",
     "iopub.status.idle": "2024-03-05T21:23:52.966262Z",
     "shell.execute_reply": "2024-03-05T21:23:52.965996Z"
    }
   },
   "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": "2024-03-05T21:23:52.967858Z",
     "iopub.status.busy": "2024-03-05T21:23:52.967773Z",
     "iopub.status.idle": "2024-03-05T21:23:52.973752Z",
     "shell.execute_reply": "2024-03-05T21:23:52.973497Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted folder: MouseAgingClocks\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
}