Graph-augmented Convolutional Networks on Drug-Drug Interactions Prediction

2019/12/08 by Yi Zhong, Zhong, Yi, Xueyu Chen +8 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Bioinformatics and Genomic Networks #Computational Drug Discovery Methods #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.1912.03702

openalex publication_date 2019/12/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose an end-to-end model to predict drug-drug interactions (DDIs) by employing graph-augmented convolutional networks. And this is implemented by combining graph CNN with an attentive pooling network to extract structural relations between drug pairs and make DDI predictions. The experiment results suggest a desirable performance achieving ROC at 0.988, F1-score at 0.956, and AUPR at 0.986. Besides, the model can tell how the two DDI drugs interact structurally by varying colored atoms. And this may be helpful for drug design during drug discovery.

Cited by

• ModuLM: Enabling Modular and Multimodal Molecular Relational Learning with Large Language Models

Related

• A Graph-in-Graph Learning Framework for Drug-Target Interaction Prediction
• Graph Distance Neural Networks for Predicting Multiple Drug Interactions
• Towards Interpretable Drug-Drug Interaction Prediction: A Graph-Based Approach with Molecular and Network-Level Explanations
• DDI Prediction via Heterogeneous Graph Attention Networks
• Heterogeneous networks in drug-target interaction prediction