Additional file 1 of A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data

Additional file 1: Strategies of domain knowledge integration and explainability methodsLegends: Types of omic data: G - genomics, P - proteomics, T - transcriptomics, E - epigenomics; GO - GeneOntology; PPI - protein-protein interaction; WGCNA - Weighted Correlation Network Analysis; Deep Learningarchitecture: AE - autoencoder, ANN - Artificial Neural Networks, CNN - Convolutional Neural Network, DAE -Denoising Autoencoder, DBN - Deep Belief Network, DNN - Deep Neural Network, GCNN - graph convolutionalneural network, GCNN-MLP - GCNN multilayer perceptron, MMD-VAE - Maximum Mean Discrepancy VariationalAutoencoder, VAE - Variational Autoencoder, VCDN - View Correlation Discovery Network; Interpretability method:LRP - layer-wise relevance propagation; Interpretability group: II - intrinsically interpretable, PH - post-hoc; Interpretability group: PROC - Processing; REPR - Representation; CREATE -Explanation producing; NA - not applicable.