首页> 外文期刊>Molecular BioSystems >Identifying the common genetic networks of ADR (adverse drug reaction) clusters and developing an ADR classification model
【24h】

Identifying the common genetic networks of ADR (adverse drug reaction) clusters and developing an ADR classification model

机译:识别ADR(药物不良反应)群的常见遗传网络并建立ADR分类模型

获取原文
获取原文并翻译 | 示例
       

摘要

Adverse drug reactions (ADRs) are one of the major concerns threatening public health and havernresulted in failures in drug development. Thus, predicting ADRs and discovering the mechanismsrnunderlying ADRs have become important tasks in pharmacovigilance. Identification of potential ADRs byrncomputational approaches in the early stages would be advantageous in drug development. Here wernpropose a computational method that elucidates the action mechanisms of ADRs and predicts potentialrnADRs by utilizing ADR genes, drug features, and protein–protein interaction (PPI) networks. If some ADRsrnshare similar features, there is a high possibility that they may appear together in a drug and share analogousrnmechanisms. Proceeding from this assumption, we clustered ADRs according to interactions ofrnADR genes in the PPI networks and the frequency of co-occurrence of ADRs in drugs. ADR clustersrnwere verified based on a side effect database and literature data regarding whether ADRs have relevancernto other ADRs in the same cluster. Gene networks shared by ADRs in each cluster were constructed byrncumulating the shortest paths between drug target genes and ADR genes in the PPI network. Werndeveloped a classification model to predict potential ADRs using these gene networks shared by ADRsrnand calculated cross-validation AUC (area under the curve) values for each ADR cluster. In addition,rnin order to demonstrate correlations between gene networks shared by ADRs and ADRs in a cluster, wernapplied the Wilcoxon rank sum statistical test to the literature data and results of a Google query search.rnWe attained statistically meaningful p-values (<0.05) for every ADR cluster. The results suggest that ourrnapproach provides insights into discovering the action mechanisms of ADRs and is a novel attempt tornpredict ADRs in a biological aspect.
机译:药物不良反应(ADR)是威胁公众健康并导致药物开发失败的主要问题之一。因此,预测ADR并发现其基础机制已成为药物警戒的重要任务。在早期阶段通过计算机方法识别潜在的ADR将有利于药物开发。在这里,我们提出了一种计算方法,该方法通过利用ADR基因,药物特征和蛋白质-蛋白质相互作用(PPI)网络来阐明ADR的作用机制并预测潜在的ADR。如果某些ADR具有相似的功能,则它们很可能会一起出现在药物中并具有相似的机理。从这个假设出发,我们根据PPI网络中rnADR基因的相互作用和药物中ADR的共现频率对ADR进行聚类。基于副作用数据库和有关ADR是否与同一群集中其他ADR相关的文献资料,对ADR群集进行了验证。通过聚类PPI网络中药物靶基因和ADR基因之间的最短路径,构建每个簇中ADR共有的基因网络。 Wern开发了一种分类模型,以使用由ADRsrn共享的这些基因网络预测潜在的ADR,并为每个ADR簇计算交叉验证AUC(曲线下面积)值。此外,为了证明ADR和ADR共享的基因网络之间的相关性,我们将Wilcoxon秩和统计检验应用于文献数据和Google查询搜索结果。我们获得了具有统计学意义的p值(<0.05)每个ADR群集。结果表明,我们的方法为发现ADR的作用机制提供了见识,并且是从生物学角度预测ADR的新尝试。

著录项

  • 来源
    《Molecular BioSystems》 |2017年第9期|1788-1796|共9页
  • 作者单位

    Dept. of Computer Science, University of Southern California, USA;

    Dept. of Computer Science, Virginia Tech, USA;

    Dept. of IT Convergence Engineering, Gachon University, Korea;

    Dept. of Computer Engineering, Gachon University, Korea;

    Biomedical HPC Technology Research Center, Korean Institute of Science andTechnology Information, Korea;

    Dept. of Computer Science & Engineering, Incheon National University, Korea;

    Dept. of Computer Engineering, Gachon University, Korea;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

  • 入库时间 2022-08-18 01:07:40

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号