[1]陈耿靖,王晖,郭躬德,等.基于路径类比推理的药物重定位方法[J].计算机技术与发展,2024,34(08):158-165.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0143]
　CHEN Geng-jing,WANG Hui,GUO Gong-de,et al.Path-based Analogical Reasoning for Drug Repurposing[J].,2024,34(08):158-165.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0143]
点击复制

基于路径类比推理的药物重定位方法

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年08期
页码:
158-165
栏目:
人工智能
出版日期:
2024-08-10

文章信息/Info

Title:
Path-based Analogical Reasoning for Drug Repurposing
文章编号:
1673-629X(2024)08-0158-08
作者:
陈耿靖1; 王晖2; 郭躬德1; 林世水3
1. 福建师范大学 计算机与网络空间安全学院,福建 福州 350117; 2. 贝尔法斯特女王大学 电子电气工程和计算机科学学院,贝尔法斯特 BT9 5BN; 3. 福建医科大学 省立临床医学院,福建 福州 350001
Author(s):
CHEN Geng-jing1; WANG Hui2; GUO Gong-de1; LIN Shi-shui3
1. School of Computer and Cyber Security,Fujian Normal University,Fuzhou 350117,China; 2. School of Electronics,Electrical Engineering and Computer Science,Queen's University Belfast,Belfast BT9 5BN,United Kingdom; 3. School of Shengli Clinical Medical,Fu
关键词:
药物重定位; 知识图谱嵌入; 类比推理; 路径排序算法; Adaboost
Keywords:
drug repurposing; knowledge graph embedding; analogical reasoning; path ranking algorithm; Adaboost
分类号:
TP183
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0143
摘要:
传统药物研发模式有着费用昂贵、效率低下、时间周期较长等问题,而药物重定位方法为降低成本、提高效率、缩短时间提供了一种可行的选择。 目前已经提出了许多利用知识图谱进行药物重定位的方法,并取得相对可观的成果,但它们存在涉及限制数据集范围、处理的关系较单一,且不考虑节点间路径信息等局限。 为弥补这些不足,该文提出了一种基于路径类比推理的药物重定位方法。 首先,整合多个生物数据集构建异构信息网络。 其次,对多种知识图谱嵌入模型(TransE、DistMult、ComplEx、RotatE 和 RGCN)进行训练,获得嵌入向量。 再次,采用 Adaboost 决策树集成路径排序算法和多层感知机获取原始推理路径,结合类比推理进行预测。 最后,通过传统性能、嵌入评估及复现率,选定 TransE 模型作为 预测模型。 该方法成功找到 10 种重定位候选药物,并通过相关文献证实它们的治疗效果,充分验证了该方法的有效性。该方法也可为其他从事药物重定位研究的学者提供一种结合路径信息的新思路。
Abstract:
Traditional drug development is costly,inefficient and time-consuming,while drug repurposing methods provide a feasible al-ternative to reduce cost,improve efficiency and shorten time to market. Various knowledge graph-based drug repurposing methods have been proposed with relatively impressive results,but they have limitations such as limiting the scope of the dataset,dealing with simplistic relationships,and neglecting path information between nodes. To compensate for these shortcomings,we propose a drug repurposing approach based on analogical reasoning over the paths between drugs and diseases in knowledge graphs. Initially,multiple biological datasets are integrated to construct a heterogeneous information network. Subsequently, various knowledge graph embedding models (TransE,DistMult,ComplEx,RotatE,and RGCN) are trained to obtain embedding vectors. Then,path ranking algorithm and multilayer perceptron are stacked using AdaBoosted decision stumps to extract original reasoning paths,coupled with analogical reasoning for predictions. Finally,employing traditional performance metrics,embedding evaluations,and reproducibility rates,the TransE model is selected as the prediction model. The proposed approach successfully identifies 10 repurposing candidate drugs and confirms their therapeutic effects through relevant literature,which fully validates its effectiveness. The proposed approach offers a new perspective on drug repurposing by integrating path information,which may benefit other scholars involved in drug repurposing research.

相似文献/References:

[1]陈 鹏,鲍天嘉智,余肖生.基于多相似度融合的药物重定位推荐算法[J].计算机技术与发展,2021,31(01):168.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 030]
　CHEN Peng,BAO Tian-jiazhi,YU Xiao-sheng.Recommendation Algorithm for Drug Repositioning Based onMulti-similarity Fusion[J].,2021,31(08):168.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 030]
[2]高文馨,李贯峰*,王云丽,等.融入逻辑规则的知识图谱推荐模型研究[J].计算机技术与发展,2024,34(09):109.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0180]
　GAO Wen-xin,LI Guan-feng*,WANG Yun-li,et al.Research on Knowledge Graph Recommendation Models Integrated with Logical Rules[J].,2024,34(08):109.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0180]
[3]朱红,胡新雨,高莉莎,等.一种向量索引支持的时态知识图谱高效搜索方法[J].计算机技术与发展,2025,(02):138.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0305]
　ZHU Hong,HU Xin-yu,GAO Li-sha,et al.An Efficient Search Method on Temporal Knowledge Graph Supported by Vector Indexing[J].,2025,(08):138.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0305]

更新日期/Last Update: 2024-08-10