BiMA-DTI: a bidirectional Mamba-Attention hybrid framework for enhanced drug-target interaction prediction.

Youyuan Shui, Xuewen Ge, Chen Cao, Junjie Wang, Jie Hu, Yun Liu

Journal: BMC biology 2025;23(1):309

PMID: 41094478

Abstract

BACKGROUND

Predicting drug-target interactions (DTIs) is essential for accelerating drug discovery, yet traditional experimental methods are time-consuming and costly. Computational approaches, especially those using machine learning and deep learning, offer a more efficient alternative.

RESULTS

This paper presents the BiMA-DTI framework, which integrates Mamba's State Space Model (SSM) with multi-head attention mechanisms. This combination maximizes Mamba's ability to process long sequences while taking advantage of the attention mechanism's strength in handling short sequences. We designed a hybrid Mamba-Attention Network (MAN) and a Graph Mamba Network (GMN) for processing multimodal inputs, including protein amino acid sequences, Simplified Molecular Input Line Entry System (SMILES) strings, and molecular graphs of drugs, enabling comprehensive feature extraction and fusion. To enhance the complementarity between features extracted from sequences and graphs, BiMA-DTI performs a two-step weighted fusion of sequence features of drugs and proteins with molecular graph features of drugs. Finally, these fused features are concatenated and passed through a fully connected network to predict DTIs.

CONCLUSIONS

BiMA-DTI demonstrates its potential to discover new drugs, offering a powerful tool for drug discovery. Experimental results show that BiMA-DTI outperforms state-of-the-art competing methods on benchmark datasets. Additionally, ablation experiments validate the rationality of BiMA-DTI's architecture and its generalization ability. Visualization studies provide interpretability of biological mechanisms. Finally, case studies further confirm that BiMA-DTI is a reliable drug-target interaction prediction tool.

Address: Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China.; Key Laboratory for Bio-Electromagnetic Environment and Advanced Medical Theranostics, School of Biomedical Engineering and Informatics, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China.; Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China. [email protected].; Institute of Medical Informatics and Management, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China. [email protected].; Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China. [email protected].; Institute of Medical Informatics and Management, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China. [email protected].; Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China. [email protected].; Institute of Medical Informatics and Management, Nanjing Medical University, 101 Longmian Avenue, Nanjing, 211166, Jiangsu, China. [email protected].; Department of Information, The First Affiliated Hospital, Nanjing Medical University, No. 300 Guang Zhou Road, Nanjing, 210029, Jiangsu, China. [email protected].

DOI: 10.1186/s12915-025-02407-4

MeSH Terms: Drug Discovery, Computational Biology, Deep Learning, Machine Learning