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

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

TSProm: deep learning framework to predict tissue-specific regulatory logic.

NAR genomics and bioinformatics·2026

Same author

Solid Tumors Pan Cancer Transcriptome: Tissue/Cancer specific expression groups at the Isoform-Level.

bioRxiv : the preprint server for biology·2026

Same author

HViLM: A Foundation Model for Viral Genomics Enables Multi-Task Prediction of Pathogenicity, Transmissibility, and Host Tropism.

bioRxiv : the preprint server for biology·2026

Same author

A DNABERT based deep learning framework for predicting transcription factor binding sites.

Scientific reports·2026

Same author

TSProm: Deciphering the Genomic Context of Tissue Specificity.

bioRxiv : the preprint server for biology·2025

Same author

DNABERT-S: pioneering species differentiation with species-aware DNA embeddings.

Bioinformatics (Oxford, England)·2025

Search research articles

Related Experiment Video

Updated: Jul 24, 2025

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Published on: May 17, 2019

Deep multi-omics integration by learning correlation-maximizing representation identifies prognostically stratified

Yanrong Ji¹, Pratik Dutta², Ramana Davuluri²

¹Division of Health and Biomedical Informatics, Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL 60611, USA.

Bioinformatics Advances

|July 10, 2023

Summary

We developed Deep Multi-Omics Integrative Subtyping by Maximizing Correlation (DeepMOIS-MC), a novel framework for molecular subtyping. This method improves patient stratification by integrating multi-omics data, outperforming traditional approaches in cancer studies.

More Related Videos

Author Spotlight: Unveiling Transmembrane Protein Family-Related Markers in Gastric Cancer and Implications for Targeted Therapies

Author Spotlight: Unveiling Transmembrane Protein Family-Related Markers in Gastric Cancer and Implications for Targeted Therapies

Published on: September 15, 2023

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Published on: November 15, 2017

Related Experiment Videos

Last Updated: Jul 24, 2025

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Published on: May 17, 2019

Author Spotlight: Unveiling Transmembrane Protein Family-Related Markers in Gastric Cancer and Implications for Targeted Therapies

Author Spotlight: Unveiling Transmembrane Protein Family-Related Markers in Gastric Cancer and Implications for Targeted Therapies

Published on: September 15, 2023

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Published on: November 15, 2017

Area of Science:

Computational biology and bioinformatics
Genomics and multi-omics data integration
Precision medicine and cancer research

Background:

Molecular subtyping is crucial for precision medicine, enabling the identification of clinically actionable disease subgroups.
Integrating multi-omics data offers a comprehensive view for robust disease stratification.
Existing methods may not fully leverage the correlations within and across diverse omics datasets.

Purpose of the Study:

To develop a novel outcome-guided molecular subgrouping framework, Deep Multi-Omics Integrative Subtyping by Maximizing Correlation (DeepMOIS-MC).
To enhance integrative learning from multi-omics data by maximizing correlation between all input omics views.
To improve patient stratification for precision medicine applications in cancer.

Main Methods:

DeepMOIS-MC employs a two-part framework: clustering and classification.
Clustering utilizes two-layer neural networks and Generalized Canonical Correlation Analysis loss for shared representation learning, followed by outcome-guided feature selection and clustering.
Classification involves feature selection (RandomForest) and predictive modeling (XGBoost) on discretized omics data to predict identified molecular subgroups.

Main Results:

DeepMOIS-MC was applied to lung and liver cancer TCGA datasets, demonstrating superior patient stratification compared to traditional methods.
Comparative analysis confirmed the effectiveness of DeepMOIS-MC in identifying robust molecular subgroups.
Classification models showed robustness and generalizability on independent datasets.

Conclusions:

DeepMOIS-MC provides a powerful and adaptable framework for multi-omics integrative analysis.
The method facilitates the discovery of clinically relevant molecular subgroups, advancing precision oncology.
DeepMOIS-MC holds potential for broad adoption in various multi-omics integrative tasks.