DynamicDTA: Drug-Target Binding Affinity Prediction Using Dynamic Descriptors and Graph Representation

2025-05-13

AI Summary

Most existing drug–target binding affinity (DTA) prediction models rely on static protein structures, neglecting the critical role of conformational dynamics in molecular recognition and binding. To address this limitation, this work introduces dynamic protein descriptors—derived from molecular dynamics simulations (e.g., root-mean-square fluctuation, RMSF)—into DTA prediction for the first time. We propose a cross-modal collaborative modeling framework that jointly encodes drug molecular graphs, protein sequences, and dynamic structural features. Specifically, we design a drug encoder integrating graph convolutional networks, dilated convolutions, and MLPs, and a multi-source feature interaction module combining cross-attention mechanisms with tensor fusion networks. Evaluated on three benchmark datasets, our model achieves an average ≥3.4% reduction in RMSE over state-of-the-art methods. Furthermore, it successfully predicts novel HIV-1 inhibitors, validated via molecular docking, demonstrating both high predictive accuracy and strong biological interpretability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Predicting drug-target binding affinity (DTA) is essential for identifying potential therapeutic candidates in drug discovery. However, most existing models rely heavily on static protein structures, often overlooking the dynamic nature of proteins, which is crucial for capturing conformational flexibility that will be beneficial for protein binding interactions. We introduce DynamicDTA, an innovative deep learning framework that incorporates static and dynamic protein features to enhance DTA prediction. The proposed DynamicDTA takes three types of inputs, including drug sequence, protein sequence, and dynamic descriptors. A molecular graph representation of the drug sequence is generated and subsequently processed through graph convolutional network, while the protein sequence is encoded using dilated convolutions. Dynamic descriptors, such as root mean square fluctuation, are processed through a multi-layer perceptron. These embedding features are fused with static protein features using cross-attention, and a tensor fusion network integrates all three modalities for DTA prediction. Extensive experiments on three datasets demonstrate that DynamicDTA achieves by at least 3.4% improvement in RMSE score with comparison to seven state-of-the-art baseline methods. Additionally, predicting novel drugs for Human Immunodeficiency Virus Type 1 and visualizing the docking complexes further demonstrates the reliability and biological relevance of DynamicDTA.

Problem

• Predict drug-target binding affinity accurately
• Incorporate dynamic protein features for flexibility
• Improve DTA prediction over static models

Innovation

• Uses dynamic and static protein features
• Combines graph CNN and dilated convolutions
• Integrates modalities via tensor fusion