{ "cells": [ { "cell_type": "markdown", "id": "2f04eee0-5928-4e74-a754-6dc2e528810c", "metadata": {}, "source": [ "# MammalianFemale" ] }, { "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": "2025-04-07T18:02:40.547739Z", "iopub.status.busy": "2025-04-07T18:02:40.547305Z", "iopub.status.idle": "2025-04-07T18:02:42.025788Z", "shell.execute_reply": "2025-04-07T18:02:42.025473Z" } }, "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": "2025-04-07T18:02:42.027492Z", "iopub.status.busy": "2025-04-07T18:02:42.027260Z", "iopub.status.idle": "2025-04-07T18:02:42.035628Z", "shell.execute_reply": "2025-04-07T18:02:42.035378Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "class MammalianFemale(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 a sigmoid transformation.\n", " \"\"\"\n", " return torch.sigmoid(x)\n", "\n" ] } ], "source": [ "def print_entire_class(cls):\n", " source = inspect.getsource(cls)\n", " print(source)\n", "\n", "print_entire_class(pya.models.MammalianFemale)" ] }, { "cell_type": "code", "execution_count": 3, "id": "78536494-f1d9-44de-8583-c89a310d2307", "metadata": { "execution": { "iopub.execute_input": "2025-04-07T18:02:42.036882Z", "iopub.status.busy": "2025-04-07T18:02:42.036794Z", "iopub.status.idle": "2025-04-07T18:02:42.038453Z", "shell.execute_reply": "2025-04-07T18:02:42.038189Z" } }, "outputs": [], "source": [ "model = pya.models.MammalianFemale()" ] }, { "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": "2025-04-07T18:02:42.039644Z", "iopub.status.busy": "2025-04-07T18:02:42.039562Z", "iopub.status.idle": "2025-04-07T18:02:42.041519Z", "shell.execute_reply": "2025-04-07T18:02:42.041281Z" } }, "outputs": [], "source": [ "model.metadata[\"clock_name\"] = \"mammalianfemale\"\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\"] = 2023\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.\\\" bioRxiv (2023).\"\n", "model.metadata[\"doi\"] = \"https://doi.org/10.1101/2023.11.02.565286\"\n", "model.metadata[\"notes\"] = \"Pan-mammalian elastic-net sex classifier based on conserved CpG methylation; the returned value is the probability that a sample is female.\"\n", "model.metadata[\"research_only\"] = None\n", "model.metadata[\"tissue\"] = [\"multi-tissue\"] # Paper: The listed tissue is the model-development sample material.\n", "model.metadata[\"predicts\"] = [\"sex\"] # Paper: The reported predictor output is probability that the sample is female.\n", "model.metadata[\"training_target\"] = [\"sex\"] # Paper: The fitting outcome is binary sex (female versus male).\n", "model.metadata[\"unit\"] = [\"probability\"] # Paper: The returned construct is expressed as probability (0–1).\n", "model.metadata[\"model_type\"] = \"elastic net regression\" # Paper: The clock was fitted using Elastic net.\n", "model.metadata[\"platform\"] = [\"mammalian methylation array\"] # Paper: Training/selection used Mammalian methylation array.\n", "model.metadata[\"population\"] = \"multiple mammalian species\" # Paper: 15,000 samples from 348 mammalian species; universal sex predictor excludes marmosets\n", "model.metadata[\"journal\"] = \"bioRxiv (Cold Spring Harbor Laboratory)\"\n", "model.metadata[\"last_author\"] = \"Steve Horvath\"\n", "model.metadata[\"n_features\"] = 101\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": "2025-04-07T18:02:42.042897Z", "iopub.status.busy": "2025-04-07T18:02:42.042813Z", "iopub.status.idle": "2025-04-07T18:02:44.018218Z", "shell.execute_reply": "2025-04-07T18:02:44.017914Z" } }, "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": "2025-04-07T18:02:44.019768Z", "iopub.status.busy": "2025-04-07T18:02:44.019650Z", "iopub.status.idle": "2025-04-07T18:02:44.023624Z", "shell.execute_reply": "2025-04-07T18:02:44.023348Z" } }, "outputs": [], "source": [ "df = pd.read_csv('MammalianMethylationPredictors/Predictors/FemalePredictor_Overlap320K40K.csv')\n", "df['feature'] = df['CpG']\n", "df['coefficient'] = df['RegressionCoefficient']\n", "df = df[df.RegressionCoefficient != 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": "2025-04-07T18:02:44.025063Z", "iopub.status.busy": "2025-04-07T18:02:44.024964Z", "iopub.status.idle": "2025-04-07T18:02:44.027104Z", "shell.execute_reply": "2025-04-07T18:02:44.026815Z" } }, "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": "2025-04-07T18:02:44.028410Z", "iopub.status.busy": "2025-04-07T18:02:44.028321Z", "iopub.status.idle": "2025-04-07T18:02:44.030500Z", "shell.execute_reply": "2025-04-07T18:02:44.030214Z" } }, "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": "2025-04-07T18:02:44.031896Z", "iopub.status.busy": "2025-04-07T18:02:44.031803Z", "iopub.status.idle": "2025-04-07T18:02:44.033355Z", "shell.execute_reply": "2025-04-07T18:02:44.033076Z" } }, "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": "2025-04-07T18:02:44.034693Z", "iopub.status.busy": "2025-04-07T18:02:44.034604Z", "iopub.status.idle": "2025-04-07T18:02:44.036130Z", "shell.execute_reply": "2025-04-07T18:02:44.035883Z" } }, "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": "2025-04-07T18:02:44.037339Z", "iopub.status.busy": "2025-04-07T18:02:44.037234Z", "iopub.status.idle": "2025-04-07T18:02:44.038756Z", "shell.execute_reply": "2025-04-07T18:02:44.038512Z" } }, "outputs": [], "source": [ "model.postprocess_name = 'sigmoid'\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": "2025-04-07T18:02:44.040086Z", "iopub.status.busy": "2025-04-07T18:02:44.039983Z", "iopub.status.idle": "2025-04-07T18:02:44.043331Z", "shell.execute_reply": "2025-04-07T18:02:44.043070Z" } }, "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': 'mammalianfemale',\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: None\n", "preprocess_name: None\n", "preprocess_dependencies: None\n", "postprocess_name: 'sigmoid'\n", "postprocess_dependencies: None\n", "features: ['cg00563016', 'cg00878023', 'cg01042193', 'cg01145947', 'cg02053792', 'cg02407848', 'cg02812647', 'cg03039483', 'cg03341064', 'cg03860580', 'cg04272551', 'cg04423201', 'cg04487404', 'cg04493740', 'cg05218225', 'cg05848491', 'cg05901294', 'cg06332339', 'cg06758827', 'cg07121495', 'cg07597118', 'cg07998710', 'cg08162897', 'cg08955338', 'cg09509790', 'cg09658710', 'cg09824710', 'cg10723970', 'cg10730492', 'cg10743840']... [Total elements: 101]\n", "base_model_features: None\n", "\n", "%==================================== Model Details ====================================%\n", "Model Structure:\n", "\n", "base_model: LinearModel(\n", " (linear): Linear(in_features=101, out_features=1, bias=True)\n", ")\n", "\n", "%==================================== Model Details ====================================%\n", "Model Parameters and Weights:\n", "\n", "base_model.linear.weight: [-3.7219111919403076, 0.00039567038766108453, 0.16944003105163574, -0.3170323371887207, 0.09090086817741394, 1.4698140621185303, 0.34378138184547424, 0.37199780344963074, 0.248253732919693, -0.570648729801178, -1.2420387268066406, -0.6031981706619263, 0.2966012954711914, 0.4936045706272125, 1.3543082475662231, -0.5120242834091187, -1.071324110031128, 0.40442875027656555, 0.09175214916467667, -0.3924863040447235, 0.010922560468316078, 0.0004333447141107172, -1.255670428276062, 0.5057510733604431, 0.8768488168716431, -0.12605105340480804, 0.7848129868507385, -2.125744104385376, 0.3008327782154083, -0.014511662535369396]... [Tensor of shape torch.Size([1, 101])]\n", "base_model.linear.bias: tensor([0.7064])\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": "2025-04-07T18:02:44.044736Z", "iopub.status.busy": "2025-04-07T18:02:44.044621Z", "iopub.status.idle": "2025-04-07T18:02:44.049040Z", "shell.execute_reply": "2025-04-07T18:02:44.048799Z" } }, "outputs": [ { "data": { "text/plain": [ "tensor([[9.8883e-01],\n", " [2.9257e-02],\n", " [7.8139e-01],\n", " [1.7065e-05],\n", " [1.3097e-05],\n", " [1.7472e-01],\n", " [7.5826e-01],\n", " [9.9268e-04],\n", " [5.3222e-03],\n", " [9.9953e-01]], dtype=torch.float64, grad_fn=)" ] }, "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": "2025-04-07T18:02:44.050273Z", "iopub.status.busy": "2025-04-07T18:02:44.050185Z", "iopub.status.idle": "2025-04-07T18:02:44.052240Z", "shell.execute_reply": "2025-04-07T18:02:44.052011Z" } }, "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", "" ] }, { "cell_type": "code", "execution_count": 15, "id": "11aeaa70-44c0-42f9-86d7-740e3849a7a6", "metadata": { "execution": { "iopub.execute_input": "2025-04-07T18:02:44.053463Z", "iopub.status.busy": "2025-04-07T18:02:44.053377Z", "iopub.status.idle": "2025-04-07T18:02:44.061957Z", "shell.execute_reply": "2025-04-07T18:02:44.061718Z" } }, "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 }