Fig. 9: DeepMod2 feature extraction and BiLSTM deep-learning model architecture. | Nature Communications

Fig. 9: DeepMod2 feature extraction and BiLSTM deep-learning model architecture.

From: A signal processing and deep learning framework for methylation detection using Oxford Nanopore sequencing

Fig. 9: DeepMod2 feature extraction and BiLSTM deep-learning model architecture.

For each CpG locus on a read, DeepMod2 extracts 19 features per read base in a 21-bp window centered at the cytosine of interest. The feature matrix is given as an input to a deep learning model, such as BiLSTM (shown in this figure) or Transformer, to predict methylation probability. DeepMod2 uses pruned neural networks by default to improve inference speed.

Back to article page