基于模体PageRank算法识别穴位-疾病网络的关键节点  

Identification of Key Nodes of Acupoint-Disease Network Based on Motif PageRank Algorithm

作　　者：赵海 缪九男 刘晓 尉雪龙 ZHAO Hai;MIAO Jiu-nan;LIU Xiao;YU Xue-long(School of Computer Science&Engineering,Northeastern University,Shenyang 110169,China;Qi An Xin Technology Group Inc,Beijing 100096,China)

机构地区：[1]东北大学计算机科学与工程学院,辽宁沈阳110169 [2]奇安信网神信息技术(北京)股份有限公司,北京100096

出　　处：《东北大学学报（自然科学版）》2024年第5期628-635,共8页Journal of Northeastern University(Natural Science)

基　　金：中央高校基本科研业务费专项资金资助项目(N2020GFZD014);北京市博士后科研基金资助项目(2021-ZZ-092)。

摘　　要：针对现有针灸关键穴位挖掘算法存在精度不佳、适用性较窄的问题,在“穴位-疾病”网络中引入多穴位间的高阶相互作用,提出一种基于3节点模体的高特异性关键穴位挖掘算法.将此算法从分辨率、网络损失和准确性方面分别与其他5种穴位重要性评估算法进行比较.结果表明,该算法识别的关键穴位对网络的连通性有明显的破坏作用,说明关键穴位处于穴位疾病网络拓扑结构的核心位置,并与其他穴位有较高的协同合作;该算法的稳定性保证了关键穴位的可靠性;从网络拓扑结构和穴位间的高协同性角度来看,该算法寻找的关键穴位可以作为穴位网络中的核心穴位,帮助研究人员探索有针对性的、高影响力的穴位组合.Aiming at the problems of poor accuracy and narrow applicability of the existing key acupoint mining algorithms,a high specificity acupoint mining algorithm based on a 3‐node motif is proposed by introducing higher‐order interactions between multiple acupoints in the acupoint‐disease network.Comparing this algorithm with five other acupoint importance assessment algorithms in terms of resolution,network loss,and accuracy,the results show that the key acupoints identified by this algorithm have obvious destructive effects on the connectivity of the network,which indicates that the key acupoints are the core of the topology of acupoint‐disease network and have high synergistic co‑operation with other acupoints.The stability of this algorithm ensures the reliability of the key acupoints.From the perspective of the network topology and the high synergy between acupoints,the key acupoints found by the algorithm can be used as the core acupoints in the acupoint network,helping researchers to explore targeted and highly effective combinations of acupoints.

关 键 词：穴位 疾病 模体 网络 网页排名算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]