GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction

doi:10.1007/s12539-024-00609-y

LZUFE-KMS

	GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction
	Ma, Jun 1,1,2; Zhao, Zhili 1; Li, Tongfeng 1,3; Liu, Yunwu 1; Zhang, Ruisheng 1
	2024-03-08
在线发表日期	2024-03
发表期刊	INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
卷号	16 期号:2 页码:361-377
摘要	Accurately predicting compound-protein interactions (CPI) is a critical task in computer-aided drug design. In recent years, the exponential growth of compound activity and biomedical data has highlighted the need for efficient and interpretable prediction approaches. In this study, we propose GraphsformerCPI, an end-to-end deep learning framework that improves prediction performance and interpretability. GraphsformerCPI treats compounds and proteins as sequences of nodes with spatial structures, and leverages novel structure-enhanced self-attention mechanisms to integrate semantic and graph structural features within molecules for deep molecule representations. To capture the vital association between compound atoms and protein residues, we devise a dual-attention mechanism to effectively extract relational features through .cross-mapping. By extending the powerful learning capabilities of Transformers to spatial structures and extensively utilizing attention mechanisms, our model offers strong interpretability, a significant advantage over most black-box deep learning methods. To evaluate GraphsformerCPI, extensive experiments were conducted on benchmark datasets including human, C. elegans, Davis and KIBA datasets. We explored the impact of model depth and dropout rate on performance and compared our model against state-of-the-art baseline models. Our results demonstrate that GraphsformerCPI outperforms baseline models in classification datasets and achieves competitive performance in regression datasets. Specifically, on the human dataset, GraphsformerCPI achieves an average improvement of 1.6% in AUC, 0.5% in precision, and 5.3% in recall. On the KIBA dataset, the average improvement in Concordance index (CI) and mean squared error (MSE) is 3.3% and 7.2%, respectively. Molecular docking shows that our model provides novel insights into the intrinsic interactions and binding mechanisms. Our research holds practical significance in effectively predicting CPIs and binding affinities, identifying key atoms and residues, enhancing model interpretability.
关键词	CPI prediction Deep learning Molecular graph Attention mechanism
DOI	10.1007/s12539-024-00609-y
收录类别	SCIE
ISSN	1913-2751
语种	英语
WOS研究方向	Mathematical & Computational Biology
WOS类目	Mathematical & Computational Biology
WOS记录号	WOS:001177413900001
出版者	SPRINGER HEIDELBERG
原始文献类型	Article ; Early Access
EISSN	1867-1462
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/35774
专题	兰州财经大学
通讯作者	Zhang, Ruisheng
作者单位	1.Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou 730000, Peoples R China; 2.Lanzhou Univ Finance & Econ, Sch Informat Engn, Lanzhou 730020, Peoples R China; 3.Qinghai Normal Univ, Comp Coll, Xining 810016, Peoples R China
第一作者单位	兰州财经大学
推荐引用方式 GB/T 7714	Ma, Jun,Zhao, Zhili,Li, Tongfeng,et al. GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction[J]. INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES,2024,16(2):361-377.
APA	Ma, Jun,Zhao, Zhili,Li, Tongfeng,Liu, Yunwu,&Zhang, Ruisheng.(2024).GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction.INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES,16(2),361-377.
MLA	Ma, Jun,et al."GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction".INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES 16.2(2024):361-377.