scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings
Single-cell transcriptomics is rapidly advancing our understanding of the composition of complex tissues and biological cells, and single-cell RNA sequencing (scRNA-seq) holds great potential for identifying and characterizing the cell composition of complex tissues. Cell type identification by anal...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/13/4/611 |
| _version_ | 1797606250138042368 |
|---|---|
| author | Linfang Jiao Gan Wang Huanhuan Dai Xue Li Shuang Wang Tao Song |
| author_facet | Linfang Jiao Gan Wang Huanhuan Dai Xue Li Shuang Wang Tao Song |
| author_sort | Linfang Jiao |
| collection | DOAJ |
| description | Single-cell transcriptomics is rapidly advancing our understanding of the composition of complex tissues and biological cells, and single-cell RNA sequencing (scRNA-seq) holds great potential for identifying and characterizing the cell composition of complex tissues. Cell type identification by analyzing scRNA-seq data is mostly limited by time-consuming and irreproducible manual annotation. As scRNA-seq technology scales to thousands of cells per experiment, the exponential increase in the number of cell samples makes manual annotation more difficult. On the other hand, the sparsity of gene transcriptome data remains a major challenge. This paper applied the idea of the transformer to single-cell classification tasks based on scRNA-seq data. We propose scTransSort, a cell-type annotation method pretrained with single-cell transcriptomics data. The scTransSort incorporates a method of representing genes as gene expression embedding blocks to reduce the sparsity of data used for cell type identification and reduce the computational complexity. The feature of scTransSort is that its implementation of intelligent information extraction for unordered data, automatically extracting valid features of cell types without the need for manually labeled features and additional references. In experiments on cells from 35 human and 26 mouse tissues, scTransSort successfully elucidated its high accuracy and high performance for cell type identification, and demonstrated its own high robustness and generalization ability. |
| first_indexed | 2024-03-11T05:12:32Z |
| format | Article |
| id | doaj.art-f0a276857b6042eeb3b10116e31fd4b9 |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-11T05:12:32Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-f0a276857b6042eeb3b10116e31fd4b92023-11-17T18:28:54ZengMDPI AGBiomolecules2218-273X2023-03-0113461110.3390/biom13040611scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene EmbeddingsLinfang Jiao0Gan Wang1Huanhuan Dai2Xue Li3Shuang Wang4Tao Song5College of Computer Science and Technology, China University of Petroleum, Qingdao 266580, ChinaCollege of Computer Science and Technology, China University of Petroleum, Qingdao 266580, ChinaCollege of Computer Science and Technology, China University of Petroleum, Qingdao 266580, ChinaCollege of Computer Science and Technology, China University of Petroleum, Qingdao 266580, ChinaCollege of Computer Science and Technology, China University of Petroleum, Qingdao 266580, ChinaCollege of Computer Science and Technology, China University of Petroleum, Qingdao 266580, ChinaSingle-cell transcriptomics is rapidly advancing our understanding of the composition of complex tissues and biological cells, and single-cell RNA sequencing (scRNA-seq) holds great potential for identifying and characterizing the cell composition of complex tissues. Cell type identification by analyzing scRNA-seq data is mostly limited by time-consuming and irreproducible manual annotation. As scRNA-seq technology scales to thousands of cells per experiment, the exponential increase in the number of cell samples makes manual annotation more difficult. On the other hand, the sparsity of gene transcriptome data remains a major challenge. This paper applied the idea of the transformer to single-cell classification tasks based on scRNA-seq data. We propose scTransSort, a cell-type annotation method pretrained with single-cell transcriptomics data. The scTransSort incorporates a method of representing genes as gene expression embedding blocks to reduce the sparsity of data used for cell type identification and reduce the computational complexity. The feature of scTransSort is that its implementation of intelligent information extraction for unordered data, automatically extracting valid features of cell types without the need for manually labeled features and additional references. In experiments on cells from 35 human and 26 mouse tissues, scTransSort successfully elucidated its high accuracy and high performance for cell type identification, and demonstrated its own high robustness and generalization ability.https://www.mdpi.com/2218-273X/13/4/611scRNA-seqcell typeclassificationannotationidentitytransformer |
| spellingShingle | Linfang Jiao Gan Wang Huanhuan Dai Xue Li Shuang Wang Tao Song scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings Biomolecules scRNA-seq cell type classification annotation identity transformer |
| title | scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings |
| title_full | scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings |
| title_fullStr | scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings |
| title_full_unstemmed | scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings |
| title_short | scTransSort: Transformers for Intelligent Annotation of Cell Types by Gene Embeddings |
| title_sort | sctranssort transformers for intelligent annotation of cell types by gene embeddings |
| topic | scRNA-seq cell type classification annotation identity transformer |
| url | https://www.mdpi.com/2218-273X/13/4/611 |
| work_keys_str_mv | AT linfangjiao sctranssorttransformersforintelligentannotationofcelltypesbygeneembeddings AT ganwang sctranssorttransformersforintelligentannotationofcelltypesbygeneembeddings AT huanhuandai sctranssorttransformersforintelligentannotationofcelltypesbygeneembeddings AT xueli sctranssorttransformersforintelligentannotationofcelltypesbygeneembeddings AT shuangwang sctranssorttransformersforintelligentannotationofcelltypesbygeneembeddings AT taosong sctranssorttransformersforintelligentannotationofcelltypesbygeneembeddings |