SOC-DGL: Social Interaction Behavior Inspired Dual Graph Learning Framework for Drug-Target Interaction Identification

TL;DR

SOC-DGL introduces a dual graph learning framework inspired by social behaviors to improve drug-target interaction prediction by capturing multi-scale similarities in heterogeneous graphs.

Contribution

The paper proposes SOC-DGL, a novel dual graph learning framework with affinity and equilibrium modules, addressing dataset imbalance and outperforming existing methods in DTI prediction.

Findings

Outperforms state-of-the-art methods on four benchmark datasets.

Successfully predicts top drugs binding to ABL1.

Provides potential new drug-target interactions with supporting evidence.

Abstract

The identification of drug-target interactions (DTI) is critical for drug discovery and repositioning, as it reveals potential therapeutic uses of existing drugs, accelerating development and reducing costs. However, most existing models focus only on direct similarity in homogeneous graphs, failing to exploit the rich similarity in heterogeneous graphs. To address this gap, inspired by real-world social interaction behaviors, we propose SOC-DGL, which comprises two specialized modules: the Affinity-Driven Graph Learning (ADGL) module, learning global similarity through an affinity-enhanced drug-target graph, and the Equilibrium-Driven Graph Learning (EDGL) module, capturing higher-order similarity by amplifying the influence of even-hop neighbors using an even-polynomial graph filter based on balance theory. This dual approach enables SOC-DGL to effectively capture similarity information across multiple interaction scales within affinity and association matrices. To address the issue of imbalance in DTI datasets, we propose an adjustable imbalance loss function that adjusts the weight of negative samples by the parameter. Extensive experiments on four benchmark datasets demonstrate that SOC-DGL consistently outperforms existing state-of-the-art methods across both balanced and imbalanced scenarios. Moreover, SOC-DGL successfully predicts the top 9 drugs known to bind ABL1, and further analyzed the 10th drug, which has not been experimentally confirmed to interact with ABL1, providing supporting evidence for its potential binding.