id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
10_1101-2021_02_08_430070	Zhang, Yao-zhong	On the application of BERT models for nanopore methylation detection	2021	7	.pdf	application/pdf	5183	586	60	On the application of BERT models for nanopore methylation detection with deep learning models, have achieved significant performance improvements on nanopore methylation recurrent patterns of positional-signal-shift in the context window surrounding target 5-methylcytosine that the refined BERT model can achieve competitive or even better results than the state-of-the-art biRNN of datasets from the different research groups, BERT models demonstrate a good generalization Fig. 1: Basic BERT's and refined BERT's model structure used for methylation detection. a refined BERT model to take account of signal-shift patterns in the proposed refined BERT model achieves a competitive or even better result explore applying the BERT model for the nanopore methylation detection 2.2 Applying BERT models for nanopore methylation For the cross-sample evaluation, we train models on one dataset and test a BERT model to pay more attention to center positions. In-sample evaluation of different deep learning models on 5mC datasets.	./cache/10_1101-2021_02_08_430070.pdf	./txt/10_1101-2021_02_08_430070.txt