Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 9, 2026

Dual-modality Molecular Cartography: Integrating Multiplex mRNA Detection with Protein Imaging Mass Cytometry

Dual-modality Molecular Cartography: Integrating Multiplex mRNA Detection with Protein Imaging Mass Cytometry

Published on: November 14, 2025

MOCDT: multi-cancer detection and tissue-of-origin classification via cfDNA multi-modal integration.

Gihyeon Kim¹, Seungyeon Rhee², Yumi Lee²

¹Department of Artificial Intelligence, Ewha Womans University, Seoul 03760, Republic of Korea.

Bioinformatics (Oxford, England)

|July 7, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Activation of KIT signaling promotes early tumorigenesis through the AP-1 pathway in APC/TP53 double-knockout human colon organoids.

Cell death & disease·2026

Same author

Enhanced multicancer screening assay through whole-genome methylation sequencing-based multimodal cell-free DNA analysis.

Experimental & molecular medicine·2026

Same author

SMARCA4 activation engages FOSL1 to drive enhancer reprogramming and tumorigenic phenotypes in SMARCA4-deficient LUAD cells.

Cell death discovery·2026

Same author

AWG-Based Spectral Multiplexing for Unambiguous Range-Extended FMCW LiDAR.

Sensors (Basel, Switzerland)·2026

Same author

<i>CEBPB</i> Expression in Tumor Cells Drives Immune Evasion in Colorectal Cancer via <i>CTLA4</i> Up-regulation in T Cells.

Cancer communications (London, England)·2026

Same author

Characterization of Korean Colorectal Cancer Reveals Novel Driver Gene and Clinically Relevant Mutations.

MedComm·2026

This study introduces MOCDT, a novel computational framework for analyzing cell-free DNA (cfDNA) to detect cancer and identify its tissue of origin. MOCDT achieves high accuracy in cancer detection and tissue classification using multi-omics data.

Area of Science:

Genomics
Bioinformatics
Computational Biology

Background:

Circulating tumor DNA (ctDNA) in blood offers molecular insights for cancer identification and origin mapping.
Existing multi-modal computational methods struggle to integrate heterogeneous ctDNA signals effectively, limiting cancer detection and tissue-of-origin classification.
Robust computational integration is crucial for leveraging ctDNA's potential in liquid biopsies.

Purpose of the Study:

To develop and validate MOCDT, a multi-omics framework for cell-free DNA (cfDNA) analysis.
To enable high-specificity cancer detection (CD) and accurate tissue-of-origin (TOO) classification using a two-stage clinical pipeline.
To improve the integration of multi-modal cfDNA data for enhanced liquid biopsy applications.

Main Methods:

More Related Videos

Multiomics Analysis of TMEM200A as a Pan-Cancer Biomarker

Multiomics Analysis of TMEM200A as a Pan-Cancer Biomarker

Published on: September 15, 2023

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Published on: September 22, 2013

Related Experiment Videos

Last Updated: Jul 9, 2026

Dual-modality Molecular Cartography: Integrating Multiplex mRNA Detection with Protein Imaging Mass Cytometry

Dual-modality Molecular Cartography: Integrating Multiplex mRNA Detection with Protein Imaging Mass Cytometry

Published on: November 14, 2025

Multiomics Analysis of TMEM200A as a Pan-Cancer Biomarker

Multiomics Analysis of TMEM200A as a Pan-Cancer Biomarker

Published on: September 15, 2023

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Published on: September 22, 2013

Proposed MOCDT, a cfDNA multi-omics framework utilizing a supervised multi-modal autoencoder with adversarial alignment and contrastive geometry shaping.
Incorporated a latent space patient similarity network and a residual Graph Convolutional Network for relational learning.
Employed a two-stage pipeline: high-specificity CD followed by conditional TOO classification on a cfDNA cohort.

Main Results:

MOCDT achieved 95.74% specificity and 96.22% sensitivity for cancer detection.
The framework demonstrated 75.2% Top1 and 91.06% Top3 accuracy for tissue-of-origin classification.
Latent attribution analysis confirmed the model learns tissue-specific features, enhancing interpretability.

Conclusions:

MOCDT provides accurate and interpretable multi-omics integration of cfDNA data.
The framework supports clinically relevant liquid biopsy applications for cancer detection and origin identification.
The study highlights the potential of advanced computational methods in cfDNA analysis.