scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder
Abstract Background Single-cell RNA sequencing (scRNA-seq) has transformed biological research by offering new insights into cellular heterogeneity, developmental processes, and disease mechanisms. As scRNA-seq technology advances, its role in modern biology has become increasingly vital. This study...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-025-06047-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571237559173120 |
|---|---|
| author | Xiaoxu Cui Renkai Wu Yinghao Liu Peizhan Chen Qing Chang Pengchen Liang Changyu He |
| author_facet | Xiaoxu Cui Renkai Wu Yinghao Liu Peizhan Chen Qing Chang Pengchen Liang Changyu He |
| author_sort | Xiaoxu Cui |
| collection | DOAJ |
| description | Abstract Background Single-cell RNA sequencing (scRNA-seq) has transformed biological research by offering new insights into cellular heterogeneity, developmental processes, and disease mechanisms. As scRNA-seq technology advances, its role in modern biology has become increasingly vital. This study explores the application of deep learning to single-cell data clustering, with a particular focus on managing sparse, high-dimensional data. Results We propose the SMD deep learning model, which integrates nonlinear dimensionality reduction techniques with a porous dilated attention gate component. Built upon a convolutional autoencoder and informed by the negative binomial distribution, the SMD model efficiently captures essential cell clustering features and dynamically adjusts feature weights. Comprehensive evaluation on both public datasets and proprietary osteosarcoma data highlights the SMD model’s efficacy in achieving precise classifications for single-cell data clustering, showcasing its potential for advanced transcriptomic analysis. Conclusion This study underscores the potential of deep learning-specifically the SMD model-in advancing single-cell RNA sequencing data analysis. By integrating innovative computational techniques, the SMD model provides a powerful framework for unraveling cellular complexities, enhancing our understanding of biological processes, and elucidating disease mechanisms. The code is available from https://github.com/xiaoxuc/scSMD . |
| format | Article |
| id | doaj-art-605df7442c734dc5bad9d12cd5da77e4 |
| institution | Kabale University |
| issn | 1471-2105 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj-art-605df7442c734dc5bad9d12cd5da77e42025-02-02T12:44:57ZengBMCBMC Bioinformatics1471-21052025-01-0126111710.1186/s12859-025-06047-xscSMD: a deep learning method for accurate clustering of single cells based on auto-encoderXiaoxu Cui0Renkai Wu1Yinghao Liu2Peizhan Chen3Qing Chang4Pengchen Liang5Changyu He6School of Health Science and Engineering, University of Shanghai for Science and TechnologySchool of Microelectronics, Shanghai UniversitySchool of Health Science and Engineering, University of Shanghai for Science and TechnologyClinical Research Center, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Surgery, Shanghai Key Laboratory of Gastric Neoplasms, Shanghai Institute of Digestive Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineSchool of Microelectronics, Shanghai UniversityDepartment of Surgery, Shanghai Key Laboratory of Gastric Neoplasms, Shanghai Institute of Digestive Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineAbstract Background Single-cell RNA sequencing (scRNA-seq) has transformed biological research by offering new insights into cellular heterogeneity, developmental processes, and disease mechanisms. As scRNA-seq technology advances, its role in modern biology has become increasingly vital. This study explores the application of deep learning to single-cell data clustering, with a particular focus on managing sparse, high-dimensional data. Results We propose the SMD deep learning model, which integrates nonlinear dimensionality reduction techniques with a porous dilated attention gate component. Built upon a convolutional autoencoder and informed by the negative binomial distribution, the SMD model efficiently captures essential cell clustering features and dynamically adjusts feature weights. Comprehensive evaluation on both public datasets and proprietary osteosarcoma data highlights the SMD model’s efficacy in achieving precise classifications for single-cell data clustering, showcasing its potential for advanced transcriptomic analysis. Conclusion This study underscores the potential of deep learning-specifically the SMD model-in advancing single-cell RNA sequencing data analysis. By integrating innovative computational techniques, the SMD model provides a powerful framework for unraveling cellular complexities, enhancing our understanding of biological processes, and elucidating disease mechanisms. The code is available from https://github.com/xiaoxuc/scSMD .https://doi.org/10.1186/s12859-025-06047-xScRNA-seqDeep clusteringDeep learningMulti-dilated attention gate |
| spellingShingle | Xiaoxu Cui Renkai Wu Yinghao Liu Peizhan Chen Qing Chang Pengchen Liang Changyu He scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder BMC Bioinformatics ScRNA-seq Deep clustering Deep learning Multi-dilated attention gate |
| title | scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder |
| title_full | scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder |
| title_fullStr | scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder |
| title_full_unstemmed | scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder |
| title_short | scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder |
| title_sort | scsmd a deep learning method for accurate clustering of single cells based on auto encoder |
| topic | ScRNA-seq Deep clustering Deep learning Multi-dilated attention gate |
| url | https://doi.org/10.1186/s12859-025-06047-x |
| work_keys_str_mv | AT xiaoxucui scsmdadeeplearningmethodforaccurateclusteringofsinglecellsbasedonautoencoder AT renkaiwu scsmdadeeplearningmethodforaccurateclusteringofsinglecellsbasedonautoencoder AT yinghaoliu scsmdadeeplearningmethodforaccurateclusteringofsinglecellsbasedonautoencoder AT peizhanchen scsmdadeeplearningmethodforaccurateclusteringofsinglecellsbasedonautoencoder AT qingchang scsmdadeeplearningmethodforaccurateclusteringofsinglecellsbasedonautoencoder AT pengchenliang scsmdadeeplearningmethodforaccurateclusteringofsinglecellsbasedonautoencoder AT changyuhe scsmdadeeplearningmethodforaccurateclusteringofsinglecellsbasedonautoencoder |