AUTHOR=Wang Zihao , Zhou Yun , Zhang Yu , Mo Yu K. , Wang Yijie 

TITLE=XMR: an explainable multimodal neural network for drug response prediction

JOURNAL=Frontiers in Bioinformatics

VOLUME=Volume 3 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2023.1164482

DOI=10.3389/fbinf.2023.1164482

ISSN=2673-7647

ABSTRACT=Existing large-scale preclinical cancer drug-response databases provide us a great opportunity to identify and predict potentially effective drugs to combat cancers. Deep learning models built on these databases have been developed and applied to tackle the cancer drug-response prediction task. Their prediction has been demonstrated to significantly outperform traditional machine learning methods. However,  due to the “black-box” characteristic, biologically faithful explanations are hardly derived from these deep learning models. Interpretable deep learning models that rely on visible neural networks (VNNs) have been proposed to provide biological justification for the predicted outcomes. However, their performance does not meet the expectation to be applied in clinical practice. In this paper, we develop XMR model, an eXplainable Multimodal neural network for drug Response prediction. XMR is a new compact multimodal neural network consisting of two sub-networks: a visible neural network (VNN) for learning genomic features and a graph neural network (GNN) for learning drugs’ structural features. Both sub-networks are integrated in a multimodal fusion layer to model the drug response for given gene mutations and drug’s molecular structures. Furthermore, a pruning approach is applied to provide better interpretations of the XMR model. We use 5 pathway hierarchies (cell cycle, DNA repair, disease, signal transduction, and metabolism), which are obtained  from the Reactome Pathway Database, as the architecture of VNN for our XMR model to predict drug responses of triple-negative breast cancer. We find that our model outperforms other state-of-the-art interpretable deep learning models in terms of predictive performance. In addition, our model can provide biological insights for explaining drug responses for triple-negative breast cancer.