Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

HGTDP-DTA: Hybrid Graph-Transformer with Dynamic Prompt for Drug-Target Binding Affinity Prediction

Xi Xiao, Wentao Wang, Jiacheng Xie, Lijing Zhu, Gaofei Chen, Zhengji Li, Tianyang Wang, Min Xu

TL;DR

This study proposes a novel DTA prediction method, termed HGTDP-DTA, which utilizes dynamic prompts within a hybrid Graph-Transformer framework, and outperforms state-of-the-art DTA prediction methods in both prediction performance and generalization ability.

Abstract

Drug target binding affinity (DTA) is a key criterion for drug screening. Existing experimental methods are time-consuming and rely on limited structural and domain information. While learning-based methods can model sequence and structural information, they struggle to integrate contextual data and often lack comprehensive modeling of drug-target interactions. In this study, we propose a novel DTA prediction method, termed HGTDP-DTA, which utilizes dynamic prompts within a hybrid Graph-Transformer framework. Our method generates context-specific prompts for each drug-target pair, enhancing the model's ability to capture unique interactions. The introduction of prompt tuning further optimizes the prediction process by filtering out irrelevant noise and emphasizing task-relevant information, dynamically adjusting the input features of the molecular graph. The proposed hybrid Graph-Transformer architecture combines structural information from Graph Convolutional Networks (GCNs) with sequence information captured by Transformers, facilitating the interaction between global and local information. Additionally, we adopted the multi-view feature fusion method to project molecular graph views and affinity subgraph views into a common feature space, effectively combining structural and contextual information. Experiments on two widely used public datasets, Davis and KIBA, show that HGTDP-DTA outperforms state-of-the-art DTA prediction methods in both prediction performance and generalization ability.

HGTDP-DTA: Hybrid Graph-Transformer with Dynamic Prompt for Drug-Target Binding Affinity Prediction

TL;DR

This study proposes a novel DTA prediction method, termed HGTDP-DTA, which utilizes dynamic prompts within a hybrid Graph-Transformer framework, and outperforms state-of-the-art DTA prediction methods in both prediction performance and generalization ability.

Abstract

Drug target binding affinity (DTA) is a key criterion for drug screening. Existing experimental methods are time-consuming and rely on limited structural and domain information. While learning-based methods can model sequence and structural information, they struggle to integrate contextual data and often lack comprehensive modeling of drug-target interactions. In this study, we propose a novel DTA prediction method, termed HGTDP-DTA, which utilizes dynamic prompts within a hybrid Graph-Transformer framework. Our method generates context-specific prompts for each drug-target pair, enhancing the model's ability to capture unique interactions. The introduction of prompt tuning further optimizes the prediction process by filtering out irrelevant noise and emphasizing task-relevant information, dynamically adjusting the input features of the molecular graph. The proposed hybrid Graph-Transformer architecture combines structural information from Graph Convolutional Networks (GCNs) with sequence information captured by Transformers, facilitating the interaction between global and local information. Additionally, we adopted the multi-view feature fusion method to project molecular graph views and affinity subgraph views into a common feature space, effectively combining structural and contextual information. Experiments on two widely used public datasets, Davis and KIBA, show that HGTDP-DTA outperforms state-of-the-art DTA prediction methods in both prediction performance and generalization ability.

Paper Structure

This paper contains 15 sections, 22 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Problem Definition
  3. Methods
  4. Drug Molecule Embedding Generation (Path A)
  5. Affinity Graph Embedding Generation (Path B)
  6. Target Protein Embedding Generation (Path C)
  7. Hybrid Graph-Transformer Architecture with Multi-view Feature Fusion
  8. Drug-target Binding Affinity Prediction
  9. Experiments
  10. Datasets
  11. Implementation Details
  12. Comparison with State-of-the-art Methods
  13. Ablation Study
  14. Visualization Analysis
  15. Conclusion

Figures (3)

  • Figure 1: Overview of the proposed HGTDP-DTA method.
  • Figure 2: Multi-view Feature Fusion with Prompt Integration in HGTDP-DTA. This module combines features from the molecular graph, affinity graph, and protein graph into a unified feature space, integrating context-specific prompts to enhance prediction accuracy.
  • Figure 3: Visualization of affinity representations. Red: weak affinity. Blue: strong affinity.