Transformer‐based DNA methylation detection on ionic signals from Oxford Nanopore sequencing data
Published in Quantitative Biology, 2023
We apply Transformer architecture, a self-attention-based deep learning model, to detect DNA methylation from ionic signals generated by Oxford Nanopore sequencing. Using real E. coli and human genome datasets, we demonstrate that Transformers offer advantages over traditional CNN and RNN models in capturing long-range dependencies and contextual methylation signals.
Recommended citation: Xiuquan Wang, Mian Umair Ahsan, Yunyun Zhou, Kai Wang. Transformer-based DNA methylation detection on ionic signals from Oxford Nanopore sequencing data. Quant. Biol., 2023, 11(3): 287‒296. https://doi.org/10.15302/J-QB-022-0323