JASMINE: A powerful representation learning method for enhanced analysis of incomplete multi-omics data

Integrative analysis of multi-omics data provides a more comprehensive and nuanced view of a subject's biological state. However, high-dimensionality and ubiquitous modality missingness present significant analytical challenges. Existing methods for incomplete multi-omics data are scarce, do no...

Full description

Saved in:
Bibliographic Details
Published inbioRxiv
Main Authors Ballard, Jenna L, Dai, Zongyu, Shen, Li, Long, Qi
Format Journal Article
LanguageEnglish
Published United States Cold Spring Harbor Laboratory 22.06.2025
Subjects
multimodal integration
representation learning
variational autoencoder
missing data
Online AccessGet full text

Cover

More Information
Summary:Integrative analysis of multi-omics data provides a more comprehensive and nuanced view of a subject's biological state. However, high-dimensionality and ubiquitous modality missingness present significant analytical challenges. Existing methods for incomplete multi-omics data are scarce, do not fully leverage both modality-specific and shared information, and produce task-biased representations. We propose JASMINE, a self-supervised representation learning method for incomplete multi-omics data that preserves both modality-specific and joint information and enhances sample similarity structure. JASMINE produces embeddings that achieve superior performance across multiple tasks for two different incomplete multi-omics datasets while requiring only a single round of training per dataset.
Bibliography:ObjectType-Working Paper/Pre-Print-3
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2692-8205
2692-8205
DOI:10.1101/2025.06.16.659949