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

Survival Genie 2: a next-generation web server for targeted and single-cell-based survival analyses.

Genome medicine·2026

Same author

Spatial multi-omics of multiple myeloma uncovers niche-dependent pro-myeloma and immunosuppressive signaling in the bone marrow and extramedullary lesions.

bioRxiv : the preprint server for biology·2026

Same author

Association between adipokines and glycemia in children under age 8: the PROGRESS cohort of Mexico.

medRxiv : the preprint server for health sciences·2026

Same author

A single-cell atlas characterizes dysregulation of the bone marrow immune microenvironment associated with outcomes in multiple myeloma.

Nature cancer·2026

Same author

Longitudinal Profiling of Tumor and Immune Compartments Uncovers Patterns of Dysregulation and Associations with Response in Multiple Myeloma.

Blood cancer discovery·2025

Same author

Biomarkers of immune dysregulation and posttreatment inflammation in spinal muscular atrophy.

Proceedings of the National Academy of Sciences of the United States of America·2025

Search research articles

Related Experiment Video

Updated: Jul 12, 2026

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

Deep learning-based classifier for malignant plasma cell identification in myeloma.

Sarthak Satpathy^1,2, Marina E Michaud¹, William C Pilcher^1,3

¹Department of Pediatrics, Emory University, Atlanta, GA, USA.

NPJ Precision Oncology

|July 9, 2026

Summary

A new deep learning model accurately identifies malignant multiple myeloma (MM) cells in single-cell data, even in precursor stages. This breakthrough aids in understanding disease progression and treatment response.

More Related Videos

Detection of Anti-MDA5 Autoantibodies Using HeLa Cells and Immunocytochemistry with Light Microscopy

Detection of Anti-MDA5 Autoantibodies Using HeLa Cells and Immunocytochemistry with Light Microscopy

Published on: October 31, 2025

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier (MSC) for Lung Cancer Screening

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier (MSC) for Lung Cancer Screening

Published on: October 26, 2017

Related Experiment Videos

Last Updated: Jul 12, 2026

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

Detection of Anti-MDA5 Autoantibodies Using HeLa Cells and Immunocytochemistry with Light Microscopy

Detection of Anti-MDA5 Autoantibodies Using HeLa Cells and Immunocytochemistry with Light Microscopy

Published on: October 31, 2025

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier (MSC) for Lung Cancer Screening

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier (MSC) for Lung Cancer Screening

Published on: October 26, 2017

Area of Science:

Hematology
Computational Biology
Genomics

Background:

Multiple myeloma (MM) exhibits genetic heterogeneity, complicating single-cell data analysis.
Current methods for distinguishing malignant from non-malignant plasma cells are often manual or computationally intensive.

Purpose of the Study:

To develop and validate a supervised deep learning autoencoder for classifying malignant plasma cells in MM and its precursor stages.
To assess the model's performance, biological relevance, and clinical applicability.

Main Methods:

Developed a supervised deep learning autoencoder model.
Trained and validated the model on internal and external single-cell datasets across MM and precursor stages (MGUS, SMM).
Performed differential expression analysis to identify a malignant plasma cell signature.

Main Results:

The model achieved high accuracy (mean AUCs of 0.86 internal, 0.80 external, 0.92 on unseen samples).
Successfully distinguished malignant cells in precursor stages, with predicted malignant cell proportions increasing from MGUS to SMM and MM.
Identified a 12-gene malignant plasma signature associated with poor survival.

Conclusions:

The developed deep learning model enables accurate identification of malignant cells in multiple myeloma.
The model provides biologically and clinically relevant insights into MM progression and treatment response.
This approach offers a scalable and automated solution for analyzing single-cell data in MM research.