DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Network

TL;DR

DRExplainer is a novel directed graph convolutional network model that predicts drug responses in cancer cell lines and provides quantifiable interpretability by identifying relevant biological subgraphs, outperforming existing methods.

Contribution

It introduces a directed bipartite network framework with a mask learning approach for interpretability and quantifiable explanations in drug response prediction.

Findings

Outperforms state-of-the-art predictive methods.

Provides quantifiable interpretability with biological validation.

Effective in case studies for novel drug response prediction.

Abstract

Predicting the response of a cancer cell line to a therapeutic drug is pivotal for personalized medicine. Despite numerous deep learning methods that have been developed for drug response prediction, integrating diverse information about biological entities and predicting the directional response remain major challenges. Here, we propose a novel interpretable predictive model, DRExplainer, which leverages a directed graph convolutional network to enhance the prediction in a directed bipartite network framework. DRExplainer constructs a directed bipartite network integrating multi-omics profiles of cell lines, the chemical structure of drugs and known drug response to achieve directed prediction. Then, DRExplainer identifies the most relevant subgraph to each prediction in this directed bipartite network by learning a mask, facilitating critical medical decision-making. Additionally, we introduce a quantifiable method for model interpretability that leverages a ground truth benchmark dataset curated from biological features. In computational experiments, DRExplainer outperforms state-of-the-art predictive methods and another graph-based explanation method under the same experimental setting. Finally, the case studies further validate the interpretability and the effectiveness of DRExplainer in predictive novel drug response. Our code is available at: https://github.com/vshy-dream/DRExplainer.