Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ViDTA: Enhanced Drug-Target Affinity Prediction via Virtual Graph Nodes and Attention-based Feature Fusion

Minghui Li, Zikang Guo, Yang Wu, Peijin Guo, Yao Shi, Shengshan Hu, Wei Wan, Shengqing Hu

TL;DR

ViDTA tackles drug-target affinity prediction by integrating global drug topology through virtual nodes in a Graph Transformer and by using an attention-based linear fusion to combine drug and protein features. The model jointly encodes drug molecular graphs and protein sequences, producing a fused representation for affinity prediction. ViDTA demonstrates state-of-the-art performance on Davis, Metz, and KIBA benchmarks, with ablation studies confirming the value of virtual nodes and the fusion module. The work advances DTA modeling by bridging local molecular structure with global context and nuanced interaction modeling, supporting more reliable in silico screening.

Abstract

Drug-target interaction is fundamental in understanding how drugs affect biological systems, and accurately predicting drug-target affinity (DTA) is vital for drug discovery. Recently, deep learning methods have emerged as a significant approach for estimating the binding strength between drugs and target proteins. However, existing methods simply utilize the drug's local information from molecular topology rather than global information. Additionally, the features of drugs and proteins are usually fused with a simple concatenation operation, limiting their effectiveness. To address these challenges, we proposed ViDTA, an enhanced DTA prediction framework. We introduce virtual nodes into the Graph Neural Network (GNN)-based drug feature extraction network, which acts as a global memory to exchange messages more efficiently. By incorporating virtual graph nodes, we seamlessly integrate local and global features of drug molecular structures, expanding the GNN's receptive field. Additionally, we propose an attention-based linear feature fusion network for better capturing the interaction information between drugs and proteins. Experimental results evaluated on various benchmarks including Davis, Metz, and KIBA demonstrate that our proposed ViDTA outperforms the state-of-the-art baselines.

ViDTA: Enhanced Drug-Target Affinity Prediction via Virtual Graph Nodes and Attention-based Feature Fusion

TL;DR

ViDTA tackles drug-target affinity prediction by integrating global drug topology through virtual nodes in a Graph Transformer and by using an attention-based linear fusion to combine drug and protein features. The model jointly encodes drug molecular graphs and protein sequences, producing a fused representation for affinity prediction. ViDTA demonstrates state-of-the-art performance on Davis, Metz, and KIBA benchmarks, with ablation studies confirming the value of virtual nodes and the fusion module. The work advances DTA modeling by bridging local molecular structure with global context and nuanced interaction modeling, supporting more reliable in silico screening.

Abstract

Drug-target interaction is fundamental in understanding how drugs affect biological systems, and accurately predicting drug-target affinity (DTA) is vital for drug discovery. Recently, deep learning methods have emerged as a significant approach for estimating the binding strength between drugs and target proteins. However, existing methods simply utilize the drug's local information from molecular topology rather than global information. Additionally, the features of drugs and proteins are usually fused with a simple concatenation operation, limiting their effectiveness. To address these challenges, we proposed ViDTA, an enhanced DTA prediction framework. We introduce virtual nodes into the Graph Neural Network (GNN)-based drug feature extraction network, which acts as a global memory to exchange messages more efficiently. By incorporating virtual graph nodes, we seamlessly integrate local and global features of drug molecular structures, expanding the GNN's receptive field. Additionally, we propose an attention-based linear feature fusion network for better capturing the interaction information between drugs and proteins. Experimental results evaluated on various benchmarks including Davis, Metz, and KIBA demonstrate that our proposed ViDTA outperforms the state-of-the-art baselines.
Paper Structure (18 sections, 16 equations, 3 figures, 7 tables)

This paper contains 18 sections, 16 equations, 3 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Materials and Methodology
  3. Datasets
  4. Overview
  5. Drug Feature Extraction
  6. Drug Molecular Graph Representation
  7. Graph-Transformer-bsed Drug Encoder
  8. Protein Feature Extraction
  9. Protein Sequence Representation
  10. 1D-CNNs-based Protein Encoder
  11. Attention-based Linear Feature Fusion
  12. Affinity Prediction Network
  13. Experiment and Result
  14. Experiment setting
  15. Evaluation Metrics
  16. ...and 3 more sections

Figures (3)

  • Figure 1: Overview of the proposed ViDTA
  • Figure 2: Flowchart of drug encoder based on Graph Transformer
  • Figure 3: Flowchart of the attention-based linear feature fusion network