HopWD-DTA: a novel framework for drug-target affinity prediction fusing multi-hop neighborhoods and deep features

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: State-of-the-art performance (specific metrics not provided)

• Primary Outcome: Drug-target affinity prediction accuracy

• Nnt Or Sensitivity: Significantly improved accuracy over existing solutions (quantitative measures not specified)

• Confidence Interval: Not reported

Clinical Application

Requires computational infrastructure and expertise in machine learning implementation Could support Australian pharmaceutical research initiatives and TGA drug evaluation processes, potentially accelerating local drug discovery efforts Drug discovery researchers and pharmaceutical companies developing new therapeutics

Abstract

CONTEXT: Accurate prediction of drug-target affinity (DTA) is crucial for accelerating drug discovery, but it remains a significant challenge. While deep learning methods have shown promise, many existing models struggle with representing long-range protein relationships within protein-protein interaction (PPI) networks, often suffering from performance degradation as graph neural network layers deepen. To overcome this limitation, we developed HopWD-DTA, a novel framework designed to effectively capture both local and global protein features. The core innovation lies in integrating multi-hop neighborhood information from PPI networks with deep structural features of proteins and drugs. Comprehensive evaluations on the Davis, KIBA, and Human benchmark datasets demonstrate that HopWD-DTA achieves state-of-the-art performance, significantly improving DTA prediction accuracy over existing cutting-edge solutions. METHODS: The HopWD-DTA framework consists of separate branches for protein and drug feature extraction. For proteins, structural features from residue contact maps are first encoded using a Graph Convolutional Network (GCN). These features, along with InterPro annotations, are then embedded into a PPI network. We introduce a multi-hop neighborhood serialization technique, which generates a sequence of feature matrices representing different neighborhood scopes. This sequence is processed by a Variational Autoencoder (VAE) to learn a robust protein representation. For drugs, molecules are represented as graphs from SMILES strings and encoded via a GCN, followed by a novel Wide-and-Deep Path (WDPATH) module to capture both macroscopic and microscopic features. The final protein and drug features are concatenated and fed into a multilayer perceptron for affinity prediction. The model was implemented using PyTorch and RDKit.

References

1. 1.Liu, X., Zhou, M., Huang, X., Zhang, J., Li, J., Wang, Z., Lei, L., Han, K., Moghadam, N., Ganjidoust, H., & Guo, Q. (2026). HopWD-DTA: a novel framework for drug-target affinity prediction fusing multi-hop neighborhoods and deep features. Journal of Molecular Modeling. https://doi.org/10.1002/advs.202512453