Interpretable Drug Synergy Prediction with Graph Neural Networks for Human-AI Collaboration in Healthcare

TL;DR

This paper introduces IDSP, a graph neural network model that predicts drug synergy in cancer treatment by leveraging molecular signaling pathways, providing interpretable insights into the mechanisms of drug interactions.

Contribution

The paper presents a novel interpretable deep learning model, IDSP, that incorporates gene and drug signaling relationships for predicting drug synergy without relying on chemical data.

Findings

IDSP achieves comparable performance to state-of-the-art methods.

IDSP demonstrates strong generality in both transductive and inductive settings.

IDSP provides interpretable signaling patterns related to drug synergy.

Abstract

We investigate molecular mechanisms of resistant or sensitive response of cancer drug combination therapies in an inductive and interpretable manner. Though deep learning algorithms are widely used in the drug synergy prediction problem, it is still an open problem to formulate the prediction model with biological meaning to investigate the mysterious mechanisms of synergy (MoS) for the human-AI collaboration in healthcare systems. To address the challenges, we propose a deep graph neural network, IDSP (Interpretable Deep Signaling Pathways), to incorporate the gene-gene as well as gene-drug regulatory relationships in synergic drug combination predictions. IDSP automatically learns weights of edges based on the gene and drug node relations, i.e., signaling interactions, by a multi-layer perceptron (MLP) and aggregates information in an inductive manner. The proposed architecture generates interpretable drug synergy prediction by detecting important signaling interactions, and can be implemented when the underlying molecular mechanism encounters unseen genes or signaling pathways. We test IDWSP on signaling networks formulated by genes from 46 core cancer signaling pathways and drug combinations from NCI ALMANAC drug combination screening data. The experimental results demonstrated that 1) IDSP can learn from the underlying molecular mechanism to make prediction without additional drug chemical information while achieving highly comparable performance with current state-of-art methods; 2) IDSP show superior generality and flexibility to implement the synergy prediction task on both transductive tasks and inductive tasks. 3) IDSP can generate interpretable results by detecting different salient signaling patterns (i.e. MoS) for different cell lines.