{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "18c4d6a7",
   "metadata": {},
   "source": [
    "# RepliTaliNorm"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e659d200",
   "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": "e7d50618",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "5e426b95",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:02.585274Z",
     "iopub.status.busy": "2026-07-04T19:52:02.585131Z",
     "iopub.status.idle": "2026-07-04T19:52:04.618526Z",
     "shell.execute_reply": "2026-07-04T19:52:04.617995Z"
    }
   },
   "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": "cd74f2a1",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1a817cfe",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:04.620450Z",
     "iopub.status.busy": "2026-07-04T19:52:04.620244Z",
     "iopub.status.idle": "2026-07-04T19:52:04.623172Z",
     "shell.execute_reply": "2026-07-04T19:52:04.622699Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class RepliTaliNorm(LinearReferenceClock):\n",
      "    pass\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.RepliTaliNorm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1ded1023",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:04.624273Z",
     "iopub.status.busy": "2026-07-04T19:52:04.624191Z",
     "iopub.status.idle": "2026-07-04T19:52:04.625794Z",
     "shell.execute_reply": "2026-07-04T19:52:04.625482Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.RepliTaliNorm()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "12ec3578",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b3f11541",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:04.627112Z",
     "iopub.status.busy": "2026-07-04T19:52:04.627020Z",
     "iopub.status.idle": "2026-07-04T19:52:04.629204Z",
     "shell.execute_reply": "2026-07-04T19:52:04.628820Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"replitalinorm\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: Both models use DNA methylation at CpGs in common partially methylated domains.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The models were developed in primary human cells.\n",
    "model.metadata[\"year\"] = 2022\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Endicott, J.L., Nolte, P.A., Shen, H. & Laird, P.W. Cell division drives DNA methylation loss in late-replicating domains in primary human cells. Nature Communications 13, 6659 (2022).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s41467-022-34268-8\"\n",
    "model.metadata[\"notes\"] = \"Upstream starting-PD normalization model used during RepliTali construction. It was trained only in the chronologically youngest fetal skin fibroblast line (AG06561) to estimate the unobserved pre-culture replicative-history offset; it is not the final 87-CpG RepliTali model.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"cultured fibroblasts\"]  # Paper: The normalizer was trained on the chronologically youngest primary cell, fetal skin fibroblast AG06561.\n",
    "model.metadata[\"predicts\"] = [\"replicative history\"]  # Paper: The model estimates the starting-passage PD used to correct unknown pre-culture cell divisions.\n",
    "model.metadata[\"training_target\"] = [\"population doublings\"]  # Paper: The normalizer was fitted to the measured PD trajectory of AG06561.\n",
    "model.metadata[\"unit\"] = [\"population doublings\"]  # Paper: The calibration outcome is cumulative population doublings.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: Both the starting-PD normalizer and final RepliTali use elastic-net regression with alpha 0.5.\n",
    "model.metadata[\"platform\"] = [\"Illumina EPIC\"]  # Paper: Training methylation was measured using the Infinium MethylationEPIC array.\n",
    "model.metadata[\"population\"] = \"human cell cultures\"  # Paper: Only the chronologically youngest fetal fibroblast line was used to train the starting-PD normalizer.\n",
    "model.metadata[\"journal\"] = \"Nature Communications\"\n",
    "model.metadata[\"last_author\"] = \"Peter W. Laird\"\n",
    "model.metadata[\"n_features\"] = 218\n",
    "model.metadata[\"citations\"] = 86\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ca60fea5",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fbcda558",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:04.630292Z",
     "iopub.status.busy": "2026-07-04T19:52:04.630221Z",
     "iopub.status.idle": "2026-07-04T19:52:05.266315Z",
     "shell.execute_reply": "2026-07-04T19:52:05.265464Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(f\"curl -sL -o RepliTaliNorm_CpGs.rda https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data/RepliTaliNorm_CpGs.rda\")\n",
    "os.system(f\"curl -sL -o RepliTaliNorm_ref.rda https://raw.githubusercontent.com/HigginsChenLab/methylCIPHER/19b12296b0d7eb7055a97d068064df635f44ce3e/data/RepliTaliNorm_ref.rda\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "67ac3d2e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.268512Z",
     "iopub.status.busy": "2026-07-04T19:52:05.268336Z",
     "iopub.status.idle": "2026-07-04T19:52:05.272288Z",
     "shell.execute_reply": "2026-07-04T19:52:05.271717Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing download.r\n"
     ]
    }
   ],
   "source": [
    "%%writefile download.r\n",
    "\n",
    "library(jsonlite)\n",
    "load(\"RepliTaliNorm_CpGs.rda\")\n",
    "load(\"RepliTaliNorm_ref.rda\")\n",
    "write_json(RepliTaliNorm_CpGs, \"coefficients.json\", digits = 10)\n",
    "write_json(RepliTaliNorm_ref$intercept, \"intercept.json\", digits = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "053ad203",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.274226Z",
     "iopub.status.busy": "2026-07-04T19:52:05.274098Z",
     "iopub.status.idle": "2026-07-04T19:52:05.733935Z",
     "shell.execute_reply": "2026-07-04T19:52:05.733448Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(\"Rscript download.r\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04e7dcd1",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "198f3104",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.735345Z",
     "iopub.status.busy": "2026-07-04T19:52:05.735236Z",
     "iopub.status.idle": "2026-07-04T19:52:05.738232Z",
     "shell.execute_reply": "2026-07-04T19:52:05.737779Z"
    }
   },
   "outputs": [],
   "source": [
    "coef_df = pd.DataFrame(json.load(open('coefficients.json')))\n",
    "model.features = coef_df['CpG'].tolist()\n",
    "iv = json.load(open('intercept.json'))\n",
    "intercept_value = iv[0] if isinstance(iv, list) else iv"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f74b2a4d",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3425943e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.739414Z",
     "iopub.status.busy": "2026-07-04T19:52:05.739330Z",
     "iopub.status.idle": "2026-07-04T19:52:05.741105Z",
     "shell.execute_reply": "2026-07-04T19:52:05.740755Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(coef_df['coefficient'].tolist()).unsqueeze(0).float()\n",
    "intercept = torch.tensor([intercept_value]).float()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9981bd78",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.742216Z",
     "iopub.status.busy": "2026-07-04T19:52:05.742137Z",
     "iopub.status.idle": "2026-07-04T19:52:05.744169Z",
     "shell.execute_reply": "2026-07-04T19:52:05.743851Z"
    }
   },
   "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": "837c0c69",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "db8dbe0d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.745363Z",
     "iopub.status.busy": "2026-07-04T19:52:05.745295Z",
     "iopub.status.idle": "2026-07-04T19:52:05.746796Z",
     "shell.execute_reply": "2026-07-04T19:52:05.746439Z"
    }
   },
   "outputs": [],
   "source": [
    "model.reference_values = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "210e66bb",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f4b41ee0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.747831Z",
     "iopub.status.busy": "2026-07-04T19:52:05.747770Z",
     "iopub.status.idle": "2026-07-04T19:52:05.749135Z",
     "shell.execute_reply": "2026-07-04T19:52:05.748815Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "4f9de32e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.750369Z",
     "iopub.status.busy": "2026-07-04T19:52:05.750283Z",
     "iopub.status.idle": "2026-07-04T19:52:05.751747Z",
     "shell.execute_reply": "2026-07-04T19:52:05.751453Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "064cbe98",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "93273584",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.752995Z",
     "iopub.status.busy": "2026-07-04T19:52:05.752920Z",
     "iopub.status.idle": "2026-07-04T19:52:05.756529Z",
     "shell.execute_reply": "2026-07-04T19:52:05.756089Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Endicott, Jamie L., et al. \"Cell division drives DNA methylation '\n",
      "             'loss in late-replicating domains in primary human cells.\" Nature '\n",
      "             'Communications 13.1 (2022): 6659.',\n",
      " 'clock_name': 'replitalinorm',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s41467-022-34268-8',\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: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg00065944', 'cg00077044', 'cg00156723', 'cg00278655', 'cg00434151', 'cg00564996', 'cg00824087', 'cg00832327', 'cg01052456', 'cg01129509', 'cg01249202', 'cg01463644', 'cg01922998', 'cg02002355', 'cg02110836', 'cg02148017', 'cg02576202', 'cg02607176', 'cg02653473', 'cg03041877', 'cg03137548', 'cg03257387', 'cg03312661', 'cg03364201', 'cg03445914', 'cg03464371', 'cg03490300', 'cg03644817', 'cg04246882', 'cg04395911']... [Total elements: 218]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=218, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-0.6055963635444641, -1.0204650163650513, -0.39693695306777954, -0.13793666660785675, -0.19817344844341278, -0.4360240697860718, -0.005339149385690689, -0.6537990570068359, -0.4812646210193634, -1.2297855615615845, -0.5315495133399963, -0.41737160086631775, -0.3746994137763977, -1.131536602973938, -0.010423482395708561, -0.3394857943058014, -0.2915678024291992, -2.6015284061431885, -0.0052614822052419186, -0.27036532759666443, -2.179006814956665, 0.6976109147071838, -1.055829405784607, -0.5952957272529602, -0.0049955337308347225, 0.4774562418460846, -1.847993016242981, -0.5958481431007385, -0.1950979232788086, -0.007305147126317024]... [Tensor of shape torch.Size([1, 218])]\n",
      "base_model.linear.bias: tensor([75.8801])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d4c1bc6",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "59b48fb9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.757781Z",
     "iopub.status.busy": "2026-07-04T19:52:05.757703Z",
     "iopub.status.idle": "2026-07-04T19:52:05.761720Z",
     "shell.execute_reply": "2026-07-04T19:52:05.761361Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[76.1917],\n",
       "        [62.6222],\n",
       "        [78.3400],\n",
       "        [75.3361],\n",
       "        [71.4866],\n",
       "        [67.6907],\n",
       "        [74.4185],\n",
       "        [71.8606],\n",
       "        [72.5646],\n",
       "        [88.5451]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "execution_count": 15,
     "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": "28becd60",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "486e7036",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.762987Z",
     "iopub.status.busy": "2026-07-04T19:52:05.762917Z",
     "iopub.status.idle": "2026-07-04T19:52:05.766022Z",
     "shell.execute_reply": "2026-07-04T19:52:05.765567Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "890b9045",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "0ece2c83",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-07-04T19:52:05.767268Z",
     "iopub.status.busy": "2026-07-04T19:52:05.767195Z",
     "iopub.status.idle": "2026-07-04T19:52:05.770711Z",
     "shell.execute_reply": "2026-07-04T19:52:05.770336Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: intercept.json\n",
      "Deleted file: download.r\n",
      "Deleted file: RepliTaliNorm_CpGs.rda\n",
      "Deleted file: RepliTaliNorm_ref.rda\n",
      "Deleted file: coefficients.json\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 (ipykernel)",
   "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": "3.13.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}