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: Jun 17, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Unlocking precision diagnostics: A multimodal framework integrating metabolomics with advanced machine learning

Parisa Shahnazari^1,2, Kaveh Kavousi^1,2, Hamid Reza Khorram Khorshid^3,4

¹Laboratory of Complex Biological Systems and Bioinformatics (CBB), Department of Bioinformatics, Institute of Biochemistry and Biophysics (IBB), University of Tehran, Tehran, Iran.

|June 15, 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

Integrin αvβ3-Targeted SLNs for Co-Delivery of Paclitaxel and Quercetin in Triple-Negative Breast Cancer.

ACS applied materials & interfaces·2026

Same author

Molecular diagnosis of non-syndromic hearing loss in seven Iranian families using whole-exome sequencing.

BMC medical genomics·2026

Same author

Microbiome-microRNA interactions in inflammatory bowel disease: insights from metagenomic and transcriptomic data analysis.

Gastroenterology and hepatology from bed to bench·2026

Same author

Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction.

PloS one·2026

Same author

Effects of acetylation on human insulin structure, and dynamics at different temperatures: A molecular dynamics simulation study.

Journal of biosciences·2026

Same author

Modeling optimal timing of immunotherapy and chemotherapy to prevent resistance and recurrence in triple-negative breast cancer.

Scientific reports·2026

Same journal

Mental health of healthcare workers in England during the first three years of the COVID-19 pandemic: The NHS CHECK study cohort.

PloS one·2026

Same journal

Research on trajectory tracking control of tracked vehicles based on hydraulic motor system identification and Laguerre-MPC.

PloS one·2026

Same journal

A collaborative cervical precancer screening strategy with concurrent HPV genotyping and visual inspection using alumni of a training centre across Ghana: The Rotary 'Protect Your Pearl' initiative.

PloS one·2026

Same journal

Removal efficiency of pesticide residues on pesticide-spiked Perilla Leaf and Broccoli surfaces using microplasma-treated water.

PloS one·2026

Same journal

Cross-domain zero-shot semantic segmentation for unstructured environments via EVA-CLIP model, ensemble prompt engineering, and optimized text-image matching.

PloS one·2026

Same journal

Adaptive robust sparse representation for face recognition based on weighted and fusion dictionary.

PloS one·2026

See all related articles

This summary is machine-generated.

Integrating multiple omics data, like metabolomics, aids cancer research. Deep Transfer Learning and Multiple Kernel Learning significantly improved cancer detection and biomarker discovery compared to single methods.

Area of Science:

Oncology
Bioinformatics
Metabolomics

Background:

Multi-omics integration is vital for cancer research, especially metabolomics.
Early cancer detection and biomarker discovery rely on advanced analytical strategies.

Purpose of the Study:

To evaluate five strategies for integrating metabolomics data from LC-MS, GC-MS, and NMR.
To identify superior methods for multi-omics data integration in cancer research.

Main Methods:

Compared five metabolomics data integration strategies.
Utilized Deep Transfer Learning (DTL) with autoencoders and artificial neural networks.
Employed Multiple Kernel Learning (MKL) for cross-modality kernel optimization.

Main Results:

Related Experiment Videos

Last Updated: Jun 17, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

DTL and MKL significantly outperformed single-modality analyses in classification accuracy, sensitivity, and robustness.
DTL identified specific elevated monounsaturated phospholipids (e.g., phosphatidylcholine 30:1) and metabolites (e.g., β-alanine) in HER2-positive cancers.
DTL also identified decreased metabolites like 5'-deoxy-5'-methylthioadenosine.

Conclusions:

DTL and MKL offer robust and adaptable strategies for multi-omics integration.
These methods enhance cancer detection, biomarker discovery, and the development of diagnostic tools.
The findings advance precise diagnostics and therapeutics in oncology.