arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.02138cs.LGq-bio.QM
收藏

面向边缘的基于GAT的蛋白质结合位点预测

Edge-aware GAT-based protein binding site prediction

Jingdezhen Ceramic University(景德镇陶瓷大学);Jiangxi Art & Ceramics Technology Institute(江西艺术陶瓷职业技术学院)

Weisen Yang, Hanqing Zhang, Wangren Qiu, Xuan Xiao, Weizhong Lin

AI总结:

本文提出了一种面向边缘的基于GAT的蛋白质结合位点预测模型,通过整合多维结构特征提升预测准确性与效率。

摘要:

准确识别蛋白质结合位点对于理解生物分子相互作用机制以及理性设计药物靶点至关重要。传统预测方法在捕捉复杂空间构象时往往难以在预测准确性与计算效率之间取得平衡。为解决这一挑战,我们提出了一种面向边缘的图注意力网络(Edge-aware GAT)模型,用于在各种生物分子中进行细粒度的结合位点预测,包括蛋白质、DNA/RNA、离子、配体和脂质。我们的方法构建了原子级图,并整合了多维结构特征,包括几何描述符、DSSP衍生的二级结构以及相对溶剂可及性(RSA),以生成空间感知的嵌入向量。通过在注意力机制中结合原子间距离和方向向量作为边特征,模型显著增强了其表示能力。在基准数据集上,我们的模型在蛋白质-蛋白质结合位点预测中实现了0.93的ROC-AUC,优于几种最先进的方法。使用方向张量传播和残差级注意力池化进一步提高了结合位点定位和局部结构细节的捕捉能力。使用PyMOL进行的可视化确认了模型的实际效用和可解释性。为了方便社区访问和应用,我们已部署了一个公开可访问的Web服务器,网址为http://119.45.201.89:5000/。总之,我们的方法提供了一种新颖且高效的解决方案,在预测准确性、泛化能力和可解释性之间取得了平衡,用于识别蛋白质中的功能位点。

英文摘要:

Accurate identification of protein binding sites is crucial for understanding biomolecular interaction mechanisms and for the rational design of drug targets. Traditional predictive methods often struggle to balance prediction accuracy with computational efficiency when capturing complex spatial conformations. To address this challenge, we propose an Edge-aware Graph Attention Network (Edge-aware GAT) model for the fine-grained prediction of binding sites across various biomolecules, including proteins, DNA/RNA, ions, ligands, and lipids. Our method constructs atom-level graphs and integrates multidimensional structural features, including geometric descriptors, DSSP-derived secondary structure, and relative solvent accessibility (RSA), to generate spatially aware embedding vectors. By incorporating interatomic distances and directional vectors as edge features within the attention mechanism, the model significantly enhances its representation capacity. On benchmark datasets, our model achieves an ROC-AUC of 0.93 for protein-protein binding site prediction, outperforming several state-of-the-art methods. The use of directional tensor propagation and residue-level attention pooling further improves both binding site localization and the capture of local structural details. Visualizations using PyMOL confirm the model's practical utility and interpretability. To facilitate community access and application, we have deployed a publicly accessible web server at http://119.45.201.89:5000/. In summary, our approach offers a novel and efficient solution that balances prediction accuracy, generalization, and interpretability for identifying functional sites in proteins.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑