Cargando…
Adversarial dense graph convolutional networks for single-cell classification
MOTIVATION: In single-cell transcriptomics applications, effective identification of cell types in multicellular organisms and in-depth study of the relationships between genes has become one of the main goals of bioinformatics research. However, data heterogeneity and random noise pose significant...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9919433/ https://www.ncbi.nlm.nih.gov/pubmed/36661313 http://dx.doi.org/10.1093/bioinformatics/btad043 |
_version_ | 1784886823921647616 |
---|---|
author | Wang, Kangwei Li, Zhengwei You, Zhu-Hong Han, Pengyong Nie, Ru |
author_facet | Wang, Kangwei Li, Zhengwei You, Zhu-Hong Han, Pengyong Nie, Ru |
author_sort | Wang, Kangwei |
collection | PubMed |
description | MOTIVATION: In single-cell transcriptomics applications, effective identification of cell types in multicellular organisms and in-depth study of the relationships between genes has become one of the main goals of bioinformatics research. However, data heterogeneity and random noise pose significant difficulties for scRNA-seq data analysis. RESULTS: We have proposed an adversarial dense graph convolutional network architecture for single-cell classification. Specifically, to enhance the representation of higher-order features and the organic combination between features, dense connectivity mechanism and attention-based feature aggregation are introduced for feature learning in convolutional neural networks. To preserve the features of the original data, we use a feature reconstruction module to assist the goal of single-cell classification. In addition, HNNVAT uses virtual adversarial training to improve the generalization and robustness. Experimental results show that our model outperforms the existing classical methods in terms of classification accuracy on benchmark datasets. AVAILABILITY AND IMPLEMENTATION: The source code of HNNVAT is available at https://github.com/DisscLab/HNNVAT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. |
format | Online Article Text |
id | pubmed-9919433 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-99194332023-02-13 Adversarial dense graph convolutional networks for single-cell classification Wang, Kangwei Li, Zhengwei You, Zhu-Hong Han, Pengyong Nie, Ru Bioinformatics Original Paper MOTIVATION: In single-cell transcriptomics applications, effective identification of cell types in multicellular organisms and in-depth study of the relationships between genes has become one of the main goals of bioinformatics research. However, data heterogeneity and random noise pose significant difficulties for scRNA-seq data analysis. RESULTS: We have proposed an adversarial dense graph convolutional network architecture for single-cell classification. Specifically, to enhance the representation of higher-order features and the organic combination between features, dense connectivity mechanism and attention-based feature aggregation are introduced for feature learning in convolutional neural networks. To preserve the features of the original data, we use a feature reconstruction module to assist the goal of single-cell classification. In addition, HNNVAT uses virtual adversarial training to improve the generalization and robustness. Experimental results show that our model outperforms the existing classical methods in terms of classification accuracy on benchmark datasets. AVAILABILITY AND IMPLEMENTATION: The source code of HNNVAT is available at https://github.com/DisscLab/HNNVAT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. Oxford University Press 2023-01-20 /pmc/articles/PMC9919433/ /pubmed/36661313 http://dx.doi.org/10.1093/bioinformatics/btad043 Text en © The Author(s) 2023. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Original Paper Wang, Kangwei Li, Zhengwei You, Zhu-Hong Han, Pengyong Nie, Ru Adversarial dense graph convolutional networks for single-cell classification |
title | Adversarial dense graph convolutional networks for single-cell classification |
title_full | Adversarial dense graph convolutional networks for single-cell classification |
title_fullStr | Adversarial dense graph convolutional networks for single-cell classification |
title_full_unstemmed | Adversarial dense graph convolutional networks for single-cell classification |
title_short | Adversarial dense graph convolutional networks for single-cell classification |
title_sort | adversarial dense graph convolutional networks for single-cell classification |
topic | Original Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9919433/ https://www.ncbi.nlm.nih.gov/pubmed/36661313 http://dx.doi.org/10.1093/bioinformatics/btad043 |
work_keys_str_mv | AT wangkangwei adversarialdensegraphconvolutionalnetworksforsinglecellclassification AT lizhengwei adversarialdensegraphconvolutionalnetworksforsinglecellclassification AT youzhuhong adversarialdensegraphconvolutionalnetworksforsinglecellclassification AT hanpengyong adversarialdensegraphconvolutionalnetworksforsinglecellclassification AT nieru adversarialdensegraphconvolutionalnetworksforsinglecellclassification |