scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration
Abstract Single-cell multi-omics data integration aims to reduce the omics difference while keeping the cell type difference. However, it is daunting to model and distinguish the two differences due to cell heterogeneity. Namely, even cells of the same omics and type would have various features, mak...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-09-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-41795-5 |
| _version_ | 1797557951410470912 |
|---|---|
| author | Yunfan Li Dan Zhang Mouxing Yang Dezhong Peng Jun Yu Yu Liu Jiancheng Lv Lu Chen Xi Peng |
| author_facet | Yunfan Li Dan Zhang Mouxing Yang Dezhong Peng Jun Yu Yu Liu Jiancheng Lv Lu Chen Xi Peng |
| author_sort | Yunfan Li |
| collection | DOAJ |
| description | Abstract Single-cell multi-omics data integration aims to reduce the omics difference while keeping the cell type difference. However, it is daunting to model and distinguish the two differences due to cell heterogeneity. Namely, even cells of the same omics and type would have various features, making the two differences less significant. In this work, we reveal that instead of being an interference, cell heterogeneity could be exploited to improve data integration. Specifically, we observe that the omics difference varies in cells, and cells with smaller omics differences are easier to be integrated. Hence, unlike most existing works that homogeneously treat and integrate all cells, we propose a multi-omics data integration method (dubbed scBridge) that integrates cells in a heterogeneous manner. In brief, scBridge iterates between i) identifying reliable scATAC-seq cells that have smaller omics differences, and ii) integrating reliable scATAC-seq cells with scRNA-seq data to narrow the omics gap, thus benefiting the integration for the rest cells. Extensive experiments on seven multi-omics datasets demonstrate the superiority of scBridge compared with six representative baselines. |
| first_indexed | 2024-03-10T17:23:29Z |
| format | Article |
| id | doaj.art-8616f457e0ec45bba056cbde4b580553 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-10T17:23:29Z |
| publishDate | 2023-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-8616f457e0ec45bba056cbde4b5805532023-11-20T10:15:58ZengNature PortfolioNature Communications2041-17232023-09-0114111410.1038/s41467-023-41795-5scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integrationYunfan Li0Dan Zhang1Mouxing Yang2Dezhong Peng3Jun Yu4Yu Liu5Jiancheng Lv6Lu Chen7Xi Peng8School of Computer Science, Sichuan UniversityKey Laboratory of Birth Defects and Related Diseases of Women and Children of MOE, Department of Laboratory Medicine, State Key Laboratory of Biotherapy, West China Second University Hospital, Sichuan UniversitySchool of Computer Science, Sichuan UniversitySchool of Computer Science, Sichuan UniversitySchool of Computer Science, Hangzhou Dianzi UniversitySchool of Electronic and Information Engineering, Naval Aviation UniversitySchool of Computer Science, Sichuan UniversityKey Laboratory of Birth Defects and Related Diseases of Women and Children of MOE, Department of Laboratory Medicine, State Key Laboratory of Biotherapy, West China Second University Hospital, Sichuan UniversitySchool of Computer Science, Sichuan UniversityAbstract Single-cell multi-omics data integration aims to reduce the omics difference while keeping the cell type difference. However, it is daunting to model and distinguish the two differences due to cell heterogeneity. Namely, even cells of the same omics and type would have various features, making the two differences less significant. In this work, we reveal that instead of being an interference, cell heterogeneity could be exploited to improve data integration. Specifically, we observe that the omics difference varies in cells, and cells with smaller omics differences are easier to be integrated. Hence, unlike most existing works that homogeneously treat and integrate all cells, we propose a multi-omics data integration method (dubbed scBridge) that integrates cells in a heterogeneous manner. In brief, scBridge iterates between i) identifying reliable scATAC-seq cells that have smaller omics differences, and ii) integrating reliable scATAC-seq cells with scRNA-seq data to narrow the omics gap, thus benefiting the integration for the rest cells. Extensive experiments on seven multi-omics datasets demonstrate the superiority of scBridge compared with six representative baselines.https://doi.org/10.1038/s41467-023-41795-5 |
| spellingShingle | Yunfan Li Dan Zhang Mouxing Yang Dezhong Peng Jun Yu Yu Liu Jiancheng Lv Lu Chen Xi Peng scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration Nature Communications |
| title | scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration |
| title_full | scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration |
| title_fullStr | scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration |
| title_full_unstemmed | scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration |
| title_short | scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration |
| title_sort | scbridge embraces cell heterogeneity in single cell rna seq and atac seq data integration |
| url | https://doi.org/10.1038/s41467-023-41795-5 |
| work_keys_str_mv | AT yunfanli scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT danzhang scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT mouxingyang scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT dezhongpeng scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT junyu scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT yuliu scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT jianchenglv scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT luchen scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration AT xipeng scbridgeembracescellheterogeneityinsinglecellrnaseqandatacseqdataintegration |