scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq data
Abstract Background The rapid emergence of single-cell RNA-seq (scRNA-seq) data presents remarkable opportunities for broad investigations through integration analyses. However, most integration models are black boxes that lack interpretability or are hard to train. Results To address the above issu...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-023-05579-4 |
| _version_ | 1797388057088884736 |
|---|---|
| author | Zhen-Hao Guo Yan Wu Siguo Wang Qinhu Zhang Jin-Ming Shi Yan-Bin Wang Zhan-Heng Chen |
| author_facet | Zhen-Hao Guo Yan Wu Siguo Wang Qinhu Zhang Jin-Ming Shi Yan-Bin Wang Zhan-Heng Chen |
| author_sort | Zhen-Hao Guo |
| collection | DOAJ |
| description | Abstract Background The rapid emergence of single-cell RNA-seq (scRNA-seq) data presents remarkable opportunities for broad investigations through integration analyses. However, most integration models are black boxes that lack interpretability or are hard to train. Results To address the above issues, we propose scInterpreter, a deep learning-based interpretable model. scInterpreter substantially outperforms other state-of-the-art (SOTA) models in multiple benchmark datasets. In addition, scInterpreter is extensible and can integrate and annotate atlas scRNA-seq data. We evaluated the robustness of scInterpreter in a variety of situations. Through comparison experiments, we found that with a knowledge prior, the training process can be significantly accelerated. Finally, we conducted interpretability analysis for each dimension (pathway) of cell representation in the embedding space. Conclusions The results showed that the cell representations obtained by scInterpreter are full of biological significance. Through weight sorting, we found several new genes related to pathways in PBMC dataset. In general, scInterpreter is an effective and interpretable integration tool. It is expected that scInterpreter will bring great convenience to the study of single-cell transcriptomics. |
| first_indexed | 2024-03-08T22:34:13Z |
| format | Article |
| id | doaj.art-4b1520acd296408fa75366a0387eae14 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-03-08T22:34:13Z |
| publishDate | 2023-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-4b1520acd296408fa75366a0387eae142023-12-17T12:31:51ZengBMCBMC Bioinformatics1471-21052023-12-0124111410.1186/s12859-023-05579-4scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq dataZhen-Hao Guo0Yan Wu1Siguo Wang2Qinhu Zhang3Jin-Ming Shi4Yan-Bin Wang5Zhan-Heng Chen6College of Electronics and Information Engineering, Tongji UniversityCollege of Electronics and Information Engineering, Tongji UniversityEIT Institute for Advanced StudyEIT Institute for Advanced StudyDepartment of Endocrinology, Aviation General HospitalCollege of Computer Science and Technology, Zhejiang UniversityDepartment of Clinical Anesthesiology, Faculty of Anesthesiology, Second Military Medical University / Naval Medical UniversityAbstract Background The rapid emergence of single-cell RNA-seq (scRNA-seq) data presents remarkable opportunities for broad investigations through integration analyses. However, most integration models are black boxes that lack interpretability or are hard to train. Results To address the above issues, we propose scInterpreter, a deep learning-based interpretable model. scInterpreter substantially outperforms other state-of-the-art (SOTA) models in multiple benchmark datasets. In addition, scInterpreter is extensible and can integrate and annotate atlas scRNA-seq data. We evaluated the robustness of scInterpreter in a variety of situations. Through comparison experiments, we found that with a knowledge prior, the training process can be significantly accelerated. Finally, we conducted interpretability analysis for each dimension (pathway) of cell representation in the embedding space. Conclusions The results showed that the cell representations obtained by scInterpreter are full of biological significance. Through weight sorting, we found several new genes related to pathways in PBMC dataset. In general, scInterpreter is an effective and interpretable integration tool. It is expected that scInterpreter will bring great convenience to the study of single-cell transcriptomics.https://doi.org/10.1186/s12859-023-05579-4Single-cell RNA-seqBatch correctionIntegrationDeep learningKnowledge-regularized |
| spellingShingle | Zhen-Hao Guo Yan Wu Siguo Wang Qinhu Zhang Jin-Ming Shi Yan-Bin Wang Zhan-Heng Chen scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq data BMC Bioinformatics Single-cell RNA-seq Batch correction Integration Deep learning Knowledge-regularized |
| title | scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq data |
| title_full | scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq data |
| title_fullStr | scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq data |
| title_full_unstemmed | scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq data |
| title_short | scInterpreter: a knowledge-regularized generative model for interpretably integrating scRNA-seq data |
| title_sort | scinterpreter a knowledge regularized generative model for interpretably integrating scrna seq data |
| topic | Single-cell RNA-seq Batch correction Integration Deep learning Knowledge-regularized |
| url | https://doi.org/10.1186/s12859-023-05579-4 |
| work_keys_str_mv | AT zhenhaoguo scinterpreteraknowledgeregularizedgenerativemodelforinterpretablyintegratingscrnaseqdata AT yanwu scinterpreteraknowledgeregularizedgenerativemodelforinterpretablyintegratingscrnaseqdata AT siguowang scinterpreteraknowledgeregularizedgenerativemodelforinterpretablyintegratingscrnaseqdata AT qinhuzhang scinterpreteraknowledgeregularizedgenerativemodelforinterpretablyintegratingscrnaseqdata AT jinmingshi scinterpreteraknowledgeregularizedgenerativemodelforinterpretablyintegratingscrnaseqdata AT yanbinwang scinterpreteraknowledgeregularizedgenerativemodelforinterpretablyintegratingscrnaseqdata AT zhanhengchen scinterpreteraknowledgeregularizedgenerativemodelforinterpretablyintegratingscrnaseqdata |