AGMI: Attention-Guided Multi-omics Integration for Drug Response Prediction with Graph Neural Networks

TL;DR

This paper introduces AGMI, a novel graph neural network-based method that integrates multi-omics data with gene constraints for improved drug response prediction, significantly outperforming existing methods on benchmark datasets.

Contribution

The paper presents the first gene constraint-based multi-omics integration approach for drug response prediction using GNNs, introducing the AGMI framework and GeNet structure.

Findings

AGMI outperforms state-of-the-art methods by 8.3%-34.2% on four metrics.

First to explore whole-genome multi-omics integration with GNNs for DRP.

Empirical validation on CCLE and GDSC datasets confirms effectiveness.

Abstract

Accurate drug response prediction (DRP) is a crucial yet challenging task in precision medicine. This paper presents a novel Attention-Guided Multi-omics Integration (AGMI) approach for DRP, which first constructs a Multi-edge Graph (MeG) for each cell line, and then aggregates multi-omics features to predict drug response using a novel structure, called Graph edge-aware Network (GeNet). For the first time, our AGMI approach explores gene constraint based multi-omics integration for DRP with the whole-genome using GNNs. Empirical experiments on the CCLE and GDSC datasets show that our AGMI largely outperforms state-of-the-art DRP methods by 8.3%--34.2% on four metrics. Our data and code are available at https://github.com/yivan-WYYGDSG/AGMI.