Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasets

Abstract As single-cell sequencing technology became widely used, scientists found that single-modality data alone could not fully meet the research needs of complex biological systems. To address this issue, researchers began simultaneously collect multi-modal single-cell omics data. But different...

Full description

Saved in:
Bibliographic Details
Main Authors: Zihao Wang, Zeyu Wu, Minghua Deng
Format: Article
Language:English
Published: BMC 2025-08-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-025-06239-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332259516055552
author Zihao Wang
Zeyu Wu
Minghua Deng
author_facet Zihao Wang
Zeyu Wu
Minghua Deng
author_sort Zihao Wang
collection DOAJ
description Abstract As single-cell sequencing technology became widely used, scientists found that single-modality data alone could not fully meet the research needs of complex biological systems. To address this issue, researchers began simultaneously collect multi-modal single-cell omics data. But different sequencing technologies often result in datasets where one or more data modalities are missing. Therefore, mosaic datasets are more common when we analyze. However, the high dimensionality and sparsity of the data increase the difficulty, and the presence of batch effects poses an additional challenge. To address these challenges, we proposes a flexible integration framework based on Variational Autoencoder called scGCM. The main task of scGCM is to integrate single-cell multimodal mosaic data and eliminate batch effects. This method was conducted on multiple datasets, encompassing different modalities of single-cell data. The results demonstrate that, compared to state-of-the-art multimodal data integration methods, scGCM offers significant advantages in clustering accuracy and data consistency. The source code of scGCM can be accessed at https://github.com/closmouz/scCGM .
format Article
id doaj-art-9eed07cdc94c4fa59f1c4d923d16f811
institution Kabale University
issn 1471-2105
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-9eed07cdc94c4fa59f1c4d923d16f8112025-08-20T03:46:15ZengBMCBMC Bioinformatics1471-21052025-08-0126111310.1186/s12859-025-06239-5Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasetsZihao Wang0Zeyu Wu1Minghua Deng2Biomedical Interdisciplinary Research Center, Peking UniversitySchool of Mathematical Sciences, Peking UniversityBiomedical Interdisciplinary Research Center, Peking UniversityAbstract As single-cell sequencing technology became widely used, scientists found that single-modality data alone could not fully meet the research needs of complex biological systems. To address this issue, researchers began simultaneously collect multi-modal single-cell omics data. But different sequencing technologies often result in datasets where one or more data modalities are missing. Therefore, mosaic datasets are more common when we analyze. However, the high dimensionality and sparsity of the data increase the difficulty, and the presence of batch effects poses an additional challenge. To address these challenges, we proposes a flexible integration framework based on Variational Autoencoder called scGCM. The main task of scGCM is to integrate single-cell multimodal mosaic data and eliminate batch effects. This method was conducted on multiple datasets, encompassing different modalities of single-cell data. The results demonstrate that, compared to state-of-the-art multimodal data integration methods, scGCM offers significant advantages in clustering accuracy and data consistency. The source code of scGCM can be accessed at https://github.com/closmouz/scCGM .https://doi.org/10.1186/s12859-025-06239-5Mosaic intergrateSingle-cell multimodalBatch effect
spellingShingle Zihao Wang
Zeyu Wu
Minghua Deng
Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasets
BMC Bioinformatics
Mosaic intergrate
Single-cell multimodal
Batch effect
title Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasets
title_full Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasets
title_fullStr Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasets
title_full_unstemmed Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasets
title_short Semi-supervised contrastive learning variational autoencoder Integrating single-cell multimodal mosaic datasets
title_sort semi supervised contrastive learning variational autoencoder integrating single cell multimodal mosaic datasets
topic Mosaic intergrate
Single-cell multimodal
Batch effect
url https://doi.org/10.1186/s12859-025-06239-5
work_keys_str_mv AT zihaowang semisupervisedcontrastivelearningvariationalautoencoderintegratingsinglecellmultimodalmosaicdatasets
AT zeyuwu semisupervisedcontrastivelearningvariationalautoencoderintegratingsinglecellmultimodalmosaicdatasets
AT minghuadeng semisupervisedcontrastivelearningvariationalautoencoderintegratingsinglecellmultimodalmosaicdatasets