From multi-omics to deep learning: advances in cfDNA-based liquid biopsy for multi-cancer screening

Sep 28, 2026

Cancer remains a leading cause of mortality worldwide, and early detection is pivotal for improving survival. Conventional diagnosis using tissue biopsy and imaging is limited by invasiveness, cost, and accessibility, making liquid biopsy a promising non-invasive option. Circulating cell-free DNA (cfDNA) captures tumor-derived genetic and epigenetic alterations. This review summarizes cfDNA biomarkers—including mutations, CNVs, DNA methylation, fragmentation patterns, and end motifs (EMs)—and shows how multi-modal feature fusion improves classification stability under low-abundance signals, while machine learning and deep learning enhance predictive performance in clinical settings.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Background

Limits of tissue biopsy and the need for scalable early diagnosis

cfDNA and ctDNA as molecular windows for cancer biology

Multi-omics cfDNA biomarkers and feature fusion

Machine learning and deep learning for liquid biopsy

Luo etal. Biomarker Research (2026) 14:3 Biomarker Research [https://doi.org/10.1186/s40364-025-00874-z](https://doi.org/10.1186/s40364-025-00874-z) REVIEW Open Access From multi-omics to deep learning: advancesin cfDNA-based liquid biopsy for multi-cancer screening Xinwei Luo 1, Sijia Xie 1, Feitong Hong 1, Xiaolong Li 1, Yijie Wei 1, Yuwei Zhou 1, Wei Su 1, Yuhe Yang 1, Lixia Tang 1, Fuying Dao2, Peiling Cai3, Hao Lin 1*, Hongyan Lai4* and Hao Lyu 1* Abstract Cancer remains a leading cause of mortality worldwide, with early detection being critical for improving survival rates. Traditional diagnostic methods, such as tissue biopsies and imaging, face limitations in invasiveness, cost, and accessibility, making liquid biopsy a compelling non-invasive alternative. Among liquid biopsy approaches, circulating cell-free DNA (cfDNA) analysis has gained prominence for its ability to capture tumor-derived genetic and epigenetic alterations. This review summarizes key cfDNA biomarkers, including gene mutations, copy number variations (CNVs), DNA methylation, fragmentation patterns, and end motifs (EMs), and highlights their utility in cancer detection and monitoring. By integrating these multi-modal cfDNA biomarkers, feature fusion approaches have not only enhanced the performance of cancer classification models but also stabilized low-abundance signals, thus ensuring more reliable cancer detection and monitoring. Furthermore, the diagnostic power of cfDNA analysis has been further amplified by machine learning (ML), with both traditional ML and deep learning (DL) methods demonstrating strong predictive performance in routine clinical liquid biopsy applications. However, challenges remain, including tumor heterogeneity, standardization of data processing, model explainability, and cost constraints. Future advancements should focus on refining multi-modal feature integration, developing explainable AI (XAI) models, and optimizing cost-effective strategies to enhance clinical applicability. As computational methodologies advance, the integration of cfDNA biomarkers with ML frameworks holds great promise toreshape non-invasive cancer detection by enabling earlier diagnostics, more accurate prognostic evaluation and personalized treatment strategies. Keywords Cell-free DNA, Circulating tumor DNA, Artificial intelligence, Deep learning, Biomarker discovery, Liquid biopsy *Correspondence: Hao Lin[hlin@uestc.edu.cn](hlin@uestc.edu.cn)[ ](hlin@uestc.edu.cn)Hongyan Lai [laihy@cqupt.edu.cn](laihy@cqupt.edu.cn)[ ](laihy@cqupt.edu.cn)Hao Lyu [hao.lyu@uestc.edu.cn](hao.lyu@uestc.edu.cn) 1Department of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China 2School of Biological Sciences, Nanyang Technological University, Singapore 639798, Singapore 3School of Basic Medical Sciences, Chengdu University, Chengdu, China 4Chongqing Key Laboratory of Big Data for Bio Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and yo

FAQs

Why is early cancer detection important in this review?

Early detection improves survival outcomes. The review emphasizes that delayed diagnosis is a key contributor to mortality worldwide.

What makes cfDNA-based liquid biopsy a compelling non-invasive alternative?

Liquid biopsy reduces invasiveness and can provide tumor-derived genetic and epigenetic information through circulating cell-free DNA, enabling monitoring without tissue sampling.

Which cfDNA biomarker types are highlighted for cancer detection and monitoring?

The review covers gene mutations, copy number variations (CNVs), DNA methylation, fragmentation patterns, and end motifs (EMs).

Sep 28, 2026

Uploaded by Blue Pony