药物-靶标相互作用预测平台设计与实现  

Design and implementation of drug-target interaction prediction platform

作　　者：任浩然 邓博韬 李建华[1] 孝大宇[1] Ren Haoran;Deng Botao;Li Jianhua;Xiao Dayu(College of Medicine and Biological Information Engineering,Northeastern University,Shenyang 110169,China)

机构地区：[1]东北大学医学与生物信息工程学院,沈阳110169

出　　处：《现代计算机》2023年第5期104-108,共5页Modern Computer

基　　金：中央高校基本科研业务专项资金资助(N2119007);东北大学大学生创新训练计划项目(211320)。

摘　　要：旧药新用是应对突发疾病的有效手段。利用计算技术筛选潜在的药物-靶标关联,有利于快速发现治疗疾病的候选药物。基于Matlab语言设计了一款药物-靶标预测平台,在标准数据集上运用网络一致性投影方法预测,分析了余弦相似性计算、高斯内核相似性计算及Logistic变换对预测结果的影响,实验结果证实了平台的有效性。New use of old drugs is an effective means to deal with unexpected diseases.Screening potential drug-target asso⁃ciations using computational techniques is beneficial for the rapid discovery of drug candidates to treat diseases.A prediction plat⁃form of drug⁃target interactions was designed based on Matlab language,and the network consistency projection method was ap⁃plied to predict on a standard data set.The effects of cosine similarity calculation,Gaussian kernel similarity calculation and logis⁃tic transformation on the prediction results were analyzed,and the validity of the platform was confirmed by the experimental re⁃sults.

关 键 词：药物重定向 药物-靶标相互作用 预测 平台 

分 类 号：R96[医药卫生—药理学]