GraphSynergy: a network-inspired deep learning model for anticancer drug combination prediction.

Zhongzhi Xu,Qian Chu,Qingpeng Zhang,William Ka Kei Wu,Jiannan Yang

doi:10.1093/jamia/ocab162

Abstract

To develop an end-to-end deep learning framework based on a protein-protein interaction (PPI) network to make synergistic anticancer drug combination predictions. We propose a deep learning framework named Graph Convolutional Network for Drug Synergy (GraphSynergy). GraphSynergy adapts a spatial-based Graph Convolutional Network component to encode the high-order topological relationships in the PPI network of protein modules targeted by a pair of drugs, as well as the protein modules associated with a specific cancer cell line. The pharmacological effects of drug combinations are explicitly evaluated by their therapy and toxicity scores. An attention component is also introduced in GraphSynergy, which aims to capture the pivotal proteins that play a part in both PPI network and biomolecular interactions between drug combinations and cancer cell lines. GraphSynergy outperforms the classic and state-of-the-art models in predicting synergistic drug combinations on the 2 latest drug combination datasets. Specifically, GraphSynergy achieves accuracy values of 0.7553 (11.94% improvement compared to DeepSynergy, the latest published drug combination prediction algorithm) and 0.7557 (10.95% improvement compared to DeepSynergy) on DrugCombDB and Oncology-Screen datasets, respectively. Furthermore, the proteins allocated with high contribution weights during the training of GraphSynergy are proved to play a role in view of molecular functions and biological processes, such as transcription and transcription regulation. The introduction of topological relations between drug combination and cell line within the PPI network can significantly improve the capability of synergistic drug combination identification.

Highlights

Drug combination therapy has shown great promises to improve the efficacy and extend the duration of response in the treatment of complex diseases[1], such as cancers[2], human immunodeficiency virus (HIV)[3], and cardiovascular diseases[4]
GraphSynergy takes a combination of drug i and drug j with a cell line k as input and outputs the predicted probability that the drug combination is synergistic to the corresponding cell line
For each entity e in the input (i, j, k), its directed connected proteins Se0 are extracted from the drug(cell line)-protein associations A as target field, and extended along edges in the Protein-Protein Interaction (PPI) network G to form a radiant field Sek(k = 1, 2, ..., H), which contains the proteins that are within k hops away from entity e

Summary

Introduction

Drug combination therapy has shown great promises to improve the efficacy and extend the duration of response in the treatment of complex diseases[1], such as cancers[2], human immunodeficiency virus (HIV)[3], and cardiovascular diseases[4]. Machine learning methods offer the opportunity to efficiently explore the large combinatorial space Existing models, such as random forest and support vector machine, mainly focus on the drug’s chemical features or biological targets[7,8,9] of a specific cancer. A latest model, namely AuDNNsynergy[11], integrates multiomics data by introducing three auto-encoders These methods are all based on the assumption that drugs with similar chemical structures have similar treatment effects. This assumption does not take into consideration the complex biological interactions among the proteins related to drugs and diseases, and lacks the ability to explicitly capture the toxic effects resulted by combining drugs

Objectives

Methods

Results

Conclusion