Enhancing drug-target interaction prediction with graph representation learning and knowledge-based regularization
We validated the practical utility by predicting novel DTIs for FDA-approved drugs and experimentally confirming a high proportion of predictions. Our framework offers a powerful and interpretable solution for DTI prediction with the potential to substantially accelerate the identification of new drug candidates and therapeutic targets.
Authors
- Ye Cao (ORCID: https://orcid.org/0000-0002-7365-7447)
- Qiuyan Yao (ORCID: https://orcid.org/0000-0001-8753-6489)
- Zhen Chen (ORCID: https://orcid.org/0000-0003-2590-0307)
- Huijing Hu
Institutions
- Renji Hospital (CN)
- Pudong Medical Center (CN)
- Shanghai Traditional Chinese Medicine Hospital (CN)
- YangPu Geriatric Hospital (CN)
Publication Details
- Journal
- Frontiers in Bioinformatics
- Published
- 2025-10-21
- DOI
- https://doi.org/10.3389/fbinf.2025.1649337
- Citations
- 3
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 4.51