A joint analysis of single cell transcriptomics and proteomics using transformer
Abstract CITE-seq provides a powerful method for simultaneously measuring RNA and protein expression at the single-cell level. The integrated analysis of RNA and protein expression in identical cells is crucial for revealing cellular heterogeneity. However, the high experimental costs associated wit...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Systems Biology and Applications |
| Online Access: | https://doi.org/10.1038/s41540-024-00484-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559334555746304 |
|---|---|
| author | Yuanyuan Chen Xiaodan Fan Chaowen Shi Zhiyan Shi Chaojie Wang |
| author_facet | Yuanyuan Chen Xiaodan Fan Chaowen Shi Zhiyan Shi Chaojie Wang |
| author_sort | Yuanyuan Chen |
| collection | DOAJ |
| description | Abstract CITE-seq provides a powerful method for simultaneously measuring RNA and protein expression at the single-cell level. The integrated analysis of RNA and protein expression in identical cells is crucial for revealing cellular heterogeneity. However, the high experimental costs associated with CITE-seq limit its widespread application. In this paper, we propose scTEL, a deep learning framework based on Transformer encoder layers, to establish a mapping from sequenced RNA expression to unobserved protein expression in the same cells. This computation-based approach significantly reduces the experimental costs of protein expression sequencing. We are now able to predict protein expression using single-cell RNA sequencing (scRNA-seq) data, which is well-established and available at a lower cost. Moreover, our scTEL model offers a unified framework for integrating multiple CITE-seq datasets, addressing the challenge posed by the partial overlap of protein panels across different datasets. Empirical validation on public CITE-seq datasets demonstrates scTEL significantly outperforms existing methods. |
| format | Article |
| id | doaj-art-06303b071e4b4dd88c758a0a868b63fd |
| institution | Kabale University |
| issn | 2056-7189 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Systems Biology and Applications |
| spelling | doaj-art-06303b071e4b4dd88c758a0a868b63fd2025-01-05T12:34:16ZengNature Portfolionpj Systems Biology and Applications2056-71892025-01-0111111110.1038/s41540-024-00484-9A joint analysis of single cell transcriptomics and proteomics using transformerYuanyuan Chen0Xiaodan Fan1Chaowen Shi2Zhiyan Shi3Chaojie Wang4School of Mathematical Science, Jiangsu UniversityDepartment of Statistics, The Chinese University of Hong KongSchool of Life Sciences, Jiangsu UniversitySchool of Mathematical Science, Jiangsu UniversitySchool of Mathematical Science, Jiangsu UniversityAbstract CITE-seq provides a powerful method for simultaneously measuring RNA and protein expression at the single-cell level. The integrated analysis of RNA and protein expression in identical cells is crucial for revealing cellular heterogeneity. However, the high experimental costs associated with CITE-seq limit its widespread application. In this paper, we propose scTEL, a deep learning framework based on Transformer encoder layers, to establish a mapping from sequenced RNA expression to unobserved protein expression in the same cells. This computation-based approach significantly reduces the experimental costs of protein expression sequencing. We are now able to predict protein expression using single-cell RNA sequencing (scRNA-seq) data, which is well-established and available at a lower cost. Moreover, our scTEL model offers a unified framework for integrating multiple CITE-seq datasets, addressing the challenge posed by the partial overlap of protein panels across different datasets. Empirical validation on public CITE-seq datasets demonstrates scTEL significantly outperforms existing methods.https://doi.org/10.1038/s41540-024-00484-9 |
| spellingShingle | Yuanyuan Chen Xiaodan Fan Chaowen Shi Zhiyan Shi Chaojie Wang A joint analysis of single cell transcriptomics and proteomics using transformer npj Systems Biology and Applications |
| title | A joint analysis of single cell transcriptomics and proteomics using transformer |
| title_full | A joint analysis of single cell transcriptomics and proteomics using transformer |
| title_fullStr | A joint analysis of single cell transcriptomics and proteomics using transformer |
| title_full_unstemmed | A joint analysis of single cell transcriptomics and proteomics using transformer |
| title_short | A joint analysis of single cell transcriptomics and proteomics using transformer |
| title_sort | joint analysis of single cell transcriptomics and proteomics using transformer |
| url | https://doi.org/10.1038/s41540-024-00484-9 |
| work_keys_str_mv | AT yuanyuanchen ajointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT xiaodanfan ajointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT chaowenshi ajointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT zhiyanshi ajointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT chaojiewang ajointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT yuanyuanchen jointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT xiaodanfan jointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT chaowenshi jointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT zhiyanshi jointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer AT chaojiewang jointanalysisofsinglecelltranscriptomicsandproteomicsusingtransformer |