Bocheng Xie
Bocheng Xie has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Chao Yang
Faculty of Pharmaceutical Sciences, Shenzhen University of Advanced Technology, Shenzhen 518107, China
2 shared publications - Pengwei Xiao
Faculty of Pharmaceutical Sciences, Shenzhen University of Advanced Technology, Shenzhen 518107, China
2 shared publications - Xiaokang Guo
Institute of Intelligent Innovation,Henan Academy of Sciences,Zhengzhou,China, China
2 shared publications
Latest Publications
- Open Access
- 16 May 2026
- Published by MDPI AG in AI Chemistry
- Vol. 1 (2) , 9
Does DrugCLIP Find the Right Pocket? A Systematic Evaluation of Binding-Site Identification Across 42 Drug Targets
Contrastive learning-based models such as DrugCLIP have recently emerged as scalable tools for structure-based virtual screening by embedding protein structures and small molecules into a shared representation space. While these approaches demonstrate high throughput and competitive screening performance in ligand retrieval tasks, their ability to correctly identify biologically relevant ligand-binding pockets has not been systematically evaluated. Here, we construct a benchmarking dataset comprising 42 pharmacologically diverse human protein targets with experimentally validated drug-bound structures spanning multiple target families. Using this dataset, we evaluate the pocket recognition capability of DrugCLIP and compare its performance with a traditional structure-based workflow (Fpocket combined with ESSA) and a machine learning-based method (P2Rank). DrugCLIP shows robust performance for well-characterized target classes, including kinases (10/10) and nuclear receptors (5/5), but exhibits markedly reduced accuracy for ion channels (1/4), GPCRs (3/5), and transporters (3/5). Notably, pocket prediction accuracy does not strongly correlate with structural data availability, suggesting that intrinsic pocket characteristics rather than training data abundance primarily affect model performance. Across the benchmark, DrugCLIP achieves an overall success rate of 71% (95% CI: 56–83%), compared with 79% (95% CI: 64–88%) for Fpocket+ESSA, and 93% (95% CI: 81–98%) for P2Rank. McNemar’s test showed no significant difference between DrugCLIP and Fpocket+ESSA (p = 0.508), whereas P2Rank significantly outperformed DrugCLIP (p = 0.012). Together, these results provide a quantitative evaluation of pocket recognition by contrastive learning-based models and highlight key limitations of embedding-based approaches for pocket localization.
- 16 May 2026
- Published by MDPI AG in AI Chemistry
- Vol. 1 (2) , 9
Open AccessDoes DrugCLIP Find the Right Pocket? A Systematic Evaluation of Binding-Site Identification Across 42 Drug Targets
Contrastive learning-based models such as DrugCLIP have recently emerged as scalable tools for structure-based virtual screening by embedding protein structures and small molecules into a shared representation space. While these approaches demonstrate high throughput and competitive screening performance in ligand retrieval tasks, their ability to correctly identify biologically relevant ligand-binding pockets has not been systematically evaluated. Here, we construct a benchmarking dataset comprising 42 pharmacologically diverse human protein targets with experimentally validated drug-bound structures spanning multiple target families. Using this dataset, we evaluate the pocket recognition capability of DrugCLIP and compare its performance with a traditional structure-based workflow (Fpocket combined with ESSA) and a machine learning-based method (P2Rank). DrugCLIP shows robust performance for well-characterized target classes, including kinases (10/10) and nuclear receptors (5/5), but exhibits markedly reduced accuracy for ion channels (1/4), GPCRs (3/5), and transporters (3/5). Notably, pocket prediction accuracy does not strongly correlate with structural data availability, suggesting that intrinsic pocket characteristics rather than training data abundance primarily affect model performance. Across the benchmark, DrugCLIP achieves an overall success rate of 71% (95% CI: 56–83%), compared with 79% (95% CI: 64–88%) for Fpocket+ESSA, and 93% (95% CI: 81–98%) for P2Rank. McNemar’s test showed no significant difference between DrugCLIP and Fpocket+ESSA (p = 0.508), whereas P2Rank significantly outperformed DrugCLIP (p = 0.012). Together, these results provide a quantitative evaluation of pocket recognition by contrastive learning-based models and highlight key limitations of embedding-based approaches for pocket localization.
- Open Access
- 13 May 2026
- Published by MDPI AG in Preprints.org
Does DrugCLIP Find the Right Pocket? A Systematic Evaluation of Binding-Site Identification Across 42 Drug Targets
This preprint is being retracted at the author's request due to serious scientific errors that cannot be corrected by updating the paper.
- 13 May 2026
- Published by MDPI AG in Preprints.org
Open AccessDoes DrugCLIP Find the Right Pocket? A Systematic Evaluation of Binding-Site Identification Across 42 Drug Targets
This preprint is being retracted at the author's request due to serious scientific errors that cannot be corrected by updating the paper.