An interpretable geometric graph neural network for enhancing the generalizability of drug–target interaction prediction
Comprehensive benchmarking across in-domain and cross-domain DTI prediction tasks demonstrates that GPS-DTI outperforms existing methods, underscoring its strong generalization capability. Notably, the model achieves state-of-the-art performance on drug-target affinity (DTA) tasks and shows robust adaptability when evaluated on an independent Coronavirus Disease 2019 (COVID-19)-related test set. Furthermore, visualization of cross-attention maps offers interpretable insights into key molecular interactions, highlighting the potential of GPS-DTI in real-world drug discovery applications.
Authors
- Quan Zou (ORCID: https://orcid.org/0000-0001-6406-1142)
- Zhenjie Luo
- Ying Xia (ORCID: https://orcid.org/0000-0002-0126-6594)
- Leyi Wei (ORCID: https://orcid.org/0000-0003-1444-190X)
- Feifei Cui (ORCID: https://orcid.org/0000-0001-7055-3813)
- An Xiong
- Zilong Zhang (ORCID: https://orcid.org/0000-0002-4934-1258)
- Tao Wang (ORCID: https://orcid.org/0009-0002-6079-4781)
- Lesong Wei (ORCID: https://orcid.org/0000-0002-5074-9955)
Institutions
- University of Electronic Science and Technology of China (CN)
- Hainan University (CN)
- Quzhou University (CN)
- Hainan Agricultural School (CN)
- Macao Polytechnic University (MO)
- Qiqihar Medical University (CN)
Publication Details
- Journal
- BMC Biology
- Published
- 2025-11-26
- DOI
- https://doi.org/10.1186/s12915-025-02456-9
- Citations
- 3
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 4.51
Funders
- National Natural Science Foundation of China