Efficient substructure feature encoding based on graph neural network blocks for drug-target interaction prediction
Experimental results on three benchmark datasets demonstrated that GNNBlockDTI is highly competitive compared to the state-of-the-art models. Moreover, the case study of drug candidates ranking against different targets affirms the practical effectiveness of GNNBlockDTI. The source code for this study is available at https://github.com/Ptexys/GNNBlockDTI.
Authors
- Changsheng Shi
- Feiwei Qin (ORCID: https://orcid.org/0000-0001-5036-9365)
- Ruiquan Ge (ORCID: https://orcid.org/0000-0001-5713-5588)
- H. X. Mao (ORCID: https://orcid.org/0009-0001-9937-5368)
- Changmiao Wang (ORCID: https://orcid.org/0000-0003-2466-5990)
- Guojian Deng
- Qing Yang (ORCID: https://orcid.org/0000-0001-8623-7532)
- Cheng Pan (ORCID: https://orcid.org/0000-0003-4612-8889)
- Riqian Hu
Institutions
- Shenzhen Polytechnic University (CN)
- Wenzhou Medical University (CN)
- University of California System (US)
- Sanda University (CN)
- University of California San Diego (US)
- Ruian People's Hospital (CN)
- Shenzhen Research Institute of Big Data (CN)
- Hangzhou Institute of Applied Acoustics (CN)
- Hangzhou Dianzi University (CN)
Publication Details
- Journal
- Frontiers in Pharmacology
- Published
- 2025-03-05
- DOI
- https://doi.org/10.3389/fphar.2025.1553743
- Citations
- 1
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 1.50