• Home
  • Search
  • Multi-Omic Age Associations Identified With Artificial Intelligence (AI)
  • https://doi.org/10.1093/geroni/igaf122.473Copy DOI Icon

Multi-Omic Age Associations Identified With Artificial Intelligence (AI)

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Abstract There is substantial interest in using Machine Learning (ML) and Artificial Intelligence (AI) approaches to integrate multi-omics data to identify molecular factors associated with age. Multi-omic AI models can be used to predict “biological age” and to identify age-associated molecular features. To-date, predictions from traditional ML methods like elastic-net have outperformed AI models like deep learning with tabular (spreadsheet-like) data. However, new developments in transformer architectures have led to AI models that can outperform traditional ML methods. In this work, a tabular foundation AI model (TabPFN) built on transformer-based in-context learning (ICL) algorithms is used to integrate proteomics and metabolomics to identify models for age in a cohort study of older men, the Osteoporotic Fractures in Men (MrOS) Study. The serum proteomics assay was the SomaLogic 7K panel, and the serum metabolomics assay was the Metabolon Discovery HD platform. In 493 male participants split into training and test partitions, TabPFN models for age adjusted for body mass index (BMI) and estimated glomerular filtration rate (eGFR) achieved a root mean square error (RMSE) in the test set of 2.75 years, which outperformed an elastic-net model RMSE in the test set of 3.1 years. Proteins and metabolites contributing to the TabPFN model for age identified by Shapley Additive exPlanations (SHAP) included Pleiotrophin, Frizzled-7, secreted frizzled-related protein 1, and N-acetylcarnosine. Multi-omic AI models outperformed traditional ML models for age and identified biologically relevant features. Future directions include replication of findings in other studies and assessment of model performance in females.

Similar Papers
  • Research Article
  • Citations4

Artificial Intelligence for CT and MRI Protocoling: A Meta-Analysis of Traditional Machine Learning, BERT, and Large Language Models.

  • Oct 29, 2025
  • AJR. American journal of roentgenology
  • Ethan Sacoransky +2
  • Research Article
  • Citations9

Leveraging Attention-Based Deep Learning in Binary Classification for Early-Stage Breast Cancer Diagnosis.

  • Mar 13, 2025
  • Diagnostics (Basel, Switzerland)
  • Lama A Aldakhil +3
  • Research Article
  • Citations4

Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers.

  • Mar 08, 2025
  • International journal of molecular sciences
  • Kesheng Wang +6
  • Research Article
  • Citations15

Integrating Artificial Intelligence in the Diagnosis and Management of Metabolic Syndrome: A Comprehensive Review.

  • Mar 27, 2025
  • Diabetes/metabolism research and reviews
  • Jingjing Liu +5
  • Research Article
  • Citations18

Small data, big challenges: Machine- and deep-learning strategies for data-limited drug discovery.

  • Feb 01, 2026
  • Advanced drug delivery reviews
  • Nazreen Pallikkavaliyaveetil +1
  • Research Article

Empirical Analysis of the State-of-the-Art Models for Handling Polarity Shifts Due to Implicit Negation in Mobile Phone Reviews

  • Jan 01, 2025
  • International Journal of Computing Sciences Research
  • Millicent Murithi +2
  • Research Article
  • Citations82

Evaluating the accuracy of a state-of-the-art large language model for prediction of admissions from the emergency room.

  • May 21, 2024
  • Journal of the American Medical Informatics Association : JAMIA
  • Benjamin S Glicksberg +11
  • Conference Article
  • Citations1

Comparative Analysis of Transformer Models in Disaster Tweet Classification for Public Safety

  • Sep 23, 2025
  • Sharif Noor Zisad +2
  • Research Article
  • Citations2

GPTs are not the silver bullet: Performance and challenges of using GPTs for security bug report identification

  • Sep 01, 2025
  • Information and Software Technology
  • Horácio L França +3
  • Research Article

Accessible AI: comparing ChatGPT and traditional machine learning for sentiment analysis

  • Apr 08, 2026
  • International Journal of Contemporary Hospitality Management
  • Irem Önder
  • Research Article
  • Citations6

Comparison review of image classification techniques for early diagnosis of diabetic retinopathy

  • Sep 05, 2024
  • Biomedical Physics & Engineering Express
  • Chayarat Wangweera +1
  • Research Article
  • Citations39

Machine learning-based prediction of health outcomes in pediatric organ transplantation recipients.

  • Mar 01, 2021
  • JAMIA Open
  • Michael O Killian +4
  • Research Article
  • Citations100

Hybrid machine learning approach to prediction of the compressive and flexural strengths of UHPC and parametric analysis with shapley additive explanations

  • Nov 29, 2023
  • Case Studies in Construction Materials
  • Pobithra Das +1
  • Research Article
  • Citations5

Predicting mortality in critically ill patients with hypertension using machine learning and deep learning models

  • Aug 08, 2025
  • Frontiers in Cardiovascular Medicine
  • Ziyang Zhang +1
  • Research Article

Novel Convolution Neural Network for Enhanced Network Attack Pattern Recognition

  • Sep 19, 2025
  • University of Bisha Journal for Basic and Applied Sciences
  • Salahaldeen Duraibi
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.