Modal-nexus auto-encoder for multi-modality cellular data integration and imputation

Abstract Heterogeneous feature spaces and technical noise hinder the cellular data integration and imputation. The high cost of obtaining matched data across modalities further restricts analysis. Thus, there’s a critical need for deep learning approaches to effectively integrate and impute unpaired...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhenchao Tang, Guanxing Chen, Shouzhi Chen, Jianhua Yao, Linlin You, Calvin Yu-Chian Chen
Format: Article
Language:English
Published: Nature Portfolio 2024-10-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-024-53355-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181914139295744
author Zhenchao Tang
Guanxing Chen
Shouzhi Chen
Jianhua Yao
Linlin You
Calvin Yu-Chian Chen
author_facet Zhenchao Tang
Guanxing Chen
Shouzhi Chen
Jianhua Yao
Linlin You
Calvin Yu-Chian Chen
author_sort Zhenchao Tang
collection DOAJ
description Abstract Heterogeneous feature spaces and technical noise hinder the cellular data integration and imputation. The high cost of obtaining matched data across modalities further restricts analysis. Thus, there’s a critical need for deep learning approaches to effectively integrate and impute unpaired multi-modality single-cell data, enabling deeper insights into cellular behaviors. To address these issues, we introduce the Modal-Nexus Auto-Encoder (Monae). Leveraging regulatory relationships between modalities and employing contrastive learning within modality-specific auto-encoders, Monae enhances cell representations in the unified space. The integration capability of Monae furnishes it with modality-complementary cellular representations, enabling the generation of precise intra-modal and cross-modal imputation counts for extensive and complex downstream tasks. In addition, we develop Monae-E (Monae-Extension), a variant of Monae that can converge rapidly and support biological discoveries. Evaluations on various datasets have validated Monae and Monae-E’s accuracy and robustness in multi-modality cellular data integration and imputation.
format Article
id doaj-art-b703674671ed48bbaab75d65869ccdd1
institution OA Journals
issn 2041-1723
language English
publishDate 2024-10-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-b703674671ed48bbaab75d65869ccdd12025-08-20T02:17:47ZengNature PortfolioNature Communications2041-17232024-10-0115111510.1038/s41467-024-53355-6Modal-nexus auto-encoder for multi-modality cellular data integration and imputationZhenchao Tang0Guanxing Chen1Shouzhi Chen2Jianhua Yao3Linlin You4Calvin Yu-Chian Chen5Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen UniversityArtificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen UniversityArtificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen UniversityAI Lab, TencentArtificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen UniversityAI for Science (AI4S)-Preferred Program, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate SchoolAbstract Heterogeneous feature spaces and technical noise hinder the cellular data integration and imputation. The high cost of obtaining matched data across modalities further restricts analysis. Thus, there’s a critical need for deep learning approaches to effectively integrate and impute unpaired multi-modality single-cell data, enabling deeper insights into cellular behaviors. To address these issues, we introduce the Modal-Nexus Auto-Encoder (Monae). Leveraging regulatory relationships between modalities and employing contrastive learning within modality-specific auto-encoders, Monae enhances cell representations in the unified space. The integration capability of Monae furnishes it with modality-complementary cellular representations, enabling the generation of precise intra-modal and cross-modal imputation counts for extensive and complex downstream tasks. In addition, we develop Monae-E (Monae-Extension), a variant of Monae that can converge rapidly and support biological discoveries. Evaluations on various datasets have validated Monae and Monae-E’s accuracy and robustness in multi-modality cellular data integration and imputation.https://doi.org/10.1038/s41467-024-53355-6
spellingShingle Zhenchao Tang
Guanxing Chen
Shouzhi Chen
Jianhua Yao
Linlin You
Calvin Yu-Chian Chen
Modal-nexus auto-encoder for multi-modality cellular data integration and imputation
Nature Communications
title Modal-nexus auto-encoder for multi-modality cellular data integration and imputation
title_full Modal-nexus auto-encoder for multi-modality cellular data integration and imputation
title_fullStr Modal-nexus auto-encoder for multi-modality cellular data integration and imputation
title_full_unstemmed Modal-nexus auto-encoder for multi-modality cellular data integration and imputation
title_short Modal-nexus auto-encoder for multi-modality cellular data integration and imputation
title_sort modal nexus auto encoder for multi modality cellular data integration and imputation
url https://doi.org/10.1038/s41467-024-53355-6
work_keys_str_mv AT zhenchaotang modalnexusautoencoderformultimodalitycellulardataintegrationandimputation
AT guanxingchen modalnexusautoencoderformultimodalitycellulardataintegrationandimputation
AT shouzhichen modalnexusautoencoderformultimodalitycellulardataintegrationandimputation
AT jianhuayao modalnexusautoencoderformultimodalitycellulardataintegrationandimputation
AT linlinyou modalnexusautoencoderformultimodalitycellulardataintegrationandimputation
AT calvinyuchianchen modalnexusautoencoderformultimodalitycellulardataintegrationandimputation