- Author
- Gaetan De Waele (UGent) , Jim Clauwaert (UGent) , Gerben Menschaert (UGent) and Willem Waegeman (UGent)
- Organization
- Project
- Abstract
- Motivation: The adoption of current single-cell DNA methylation sequencing protocols is hindered by incomplete coverage, outlining the need for effective imputation techniques. The task of imputing single-cell (methylation) data requires models to build an understanding of underlying biological processes. Results: We adapt the transformer neural network architecture to operate on methylation matrices through combining axial attention with sliding window self-attention. The obtained CpG Transformer displays state-of-the-art performances on a wide range of scBS-seq and scRRBS-seq datasets. Furthermore, we demonstrate the interpretability of CpG Transformer and illustrate its rapid transfer learning properties, allowing practitioners to train models on new datasets with a limited computational and time budget.
- Keywords
- DNA METHYLATION, LANDSCAPES
Downloads
-
CpG Transformer for.pdf
- full text (Published version)
- |
- open access
- |
- |
- 870.89 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8738803
- MLA
- De Waele, Gaetan, et al. “CpG Transformer for Imputation of Single-Cell Methylomes.” BIOINFORMATICS, vol. 38, no. 3, 2022, pp. 597–603, doi:10.1093/bioinformatics/btab746.
- APA
- De Waele, G., Clauwaert, J., Menschaert, G., & Waegeman, W. (2022). CpG transformer for imputation of single-cell methylomes. BIOINFORMATICS, 38(3), 597–603. https://doi.org/10.1093/bioinformatics/btab746
- Chicago author-date
- De Waele, Gaetan, Jim Clauwaert, Gerben Menschaert, and Willem Waegeman. 2022. “CpG Transformer for Imputation of Single-Cell Methylomes.” BIOINFORMATICS 38 (3): 597–603. https://doi.org/10.1093/bioinformatics/btab746.
- Chicago author-date (all authors)
- De Waele, Gaetan, Jim Clauwaert, Gerben Menschaert, and Willem Waegeman. 2022. “CpG Transformer for Imputation of Single-Cell Methylomes.” BIOINFORMATICS 38 (3): 597–603. doi:10.1093/bioinformatics/btab746.
- Vancouver
- 1.De Waele G, Clauwaert J, Menschaert G, Waegeman W. CpG transformer for imputation of single-cell methylomes. BIOINFORMATICS. 2022;38(3):597–603.
- IEEE
- [1]G. De Waele, J. Clauwaert, G. Menschaert, and W. Waegeman, “CpG transformer for imputation of single-cell methylomes,” BIOINFORMATICS, vol. 38, no. 3, pp. 597–603, 2022.
@article{8738803,
abstract = {{Motivation: The adoption of current single-cell DNA methylation sequencing protocols is hindered by incomplete coverage, outlining the need for effective imputation techniques. The task of imputing single-cell (methylation) data requires models to build an understanding of underlying biological processes.
Results: We adapt the transformer neural network architecture to operate on methylation matrices through combining axial attention with sliding window self-attention. The obtained CpG Transformer displays state-of-the-art performances on a wide range of scBS-seq and scRRBS-seq datasets. Furthermore, we demonstrate the interpretability of CpG Transformer and illustrate its rapid transfer learning properties, allowing practitioners to train models on new datasets with a limited computational and time budget.}},
author = {{De Waele, Gaetan and Clauwaert, Jim and Menschaert, Gerben and Waegeman, Willem}},
issn = {{1367-4803}},
journal = {{BIOINFORMATICS}},
keywords = {{DNA METHYLATION,LANDSCAPES}},
language = {{eng}},
number = {{3}},
pages = {{597--603}},
title = {{CpG transformer for imputation of single-cell methylomes}},
url = {{http://doi.org/10.1093/bioinformatics/btab746}},
volume = {{38}},
year = {{2022}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: