郑州大学学报（工学版）2026，Vol.47Issue(1)：66-72,7.DOI:10.13705/j.issn.1671-6833.2026.01.008
融合注意力机制和多尺度信息的蛋白质结合位点预测
Protein Binding Site Prediction by Integrating Attention Mechanism and Multi-scale Information
摘要
Abstract
To effectively address the issues of noise interference and insufficient multi-scale information within 3D U-Net for protein binding site prediction,a novel model named AMPocket was proposed which incorporated both at-tention mechanisms and multi-scale information to improve the accuracy of binding site prediction.AMPocket ini-tially employed squeezed attention mechanism that enabled the model to focus on the most critical channels of pro-tein features while diminishing the impact of irrelevant channels,thereby enhancing segmentation accuracy.Addi-tionally,the multi-scale information was introduced to the encoder component,allowing the model to capture fea-ture representations at various levels and thus obtained more comprehensive and robust spatial information.The ex-perimental results demonstrated that AMPocket achieved superior predictive performance across four widely used test sets,in particular,the DCC success rate and DVO metrics on the SC6K dataset outperformed all other compe-ting methods by 93.04%and 55.01%respectively,with a smaller number of parameters.It indicated that the mo-del had better predictive performance.关键词
蛋白质结合位点预测/3D U-Net/压缩注意力机制/多尺度信息/噪声干扰Key words
protein binding site prediction/3D U-Net/squeezed attention mechanism/multi-scale information/noise interference分类
信息技术与安全科学引用本文复制引用
LU Shuai,YIN Shuailing,YUAN Mengchao,WU Di,ZHOU Qinglei..融合注意力机制和多尺度信息的蛋白质结合位点预测[J].郑州大学学报（工学版）,2026,47(1):66-72,7.基金项目
科技部科技创新2030"新一代人工智能"重大项目(2023ZD020600) （2023ZD020600）
河南省重点研发专项(241111210500) （241111210500）
河南省科技攻关项目(252102211042) （252102211042）
