利用子结构分析预测化合物库的中枢神经系统活性

Prediction of CNS activity of compound libraries using substructure analysis.

作者信息

Engkvist Ola, Wrede Paul, Rester Ulrich

机构信息

CallistoGen AG, Neuendorfstrasse 24b, D-16761 Hennigsdorf, Germany.

出版信息

J Chem Inf Comput Sci. 2003 Jan-Feb;43(1):155-60. doi: 10.1021/ci0102721.

DOI:10.1021/ci0102721

PMID:12546548

Abstract

An in silico ADME/Tox prediction tool based on substructural analysis has been developed. The tool called SUBSTRUCT has been used to predict CNS activity. Data sets with CNS active and nonactive drugs were extracted from the World Drug Index (WDI). The SUBSTRUCT program predicts CNS activity as good as a much more complicated artificial neural network model. SUBSTRUCT separates the data sets with approximately 80% accuracy. Substructural analysis also shows surprisingly large differences in substructure profiles between CNS active and nonactive drugs.

摘要

基于亚结构分析的计算机辅助药物代谢动力学/毒性预测工具已经开发出来。名为SUBSTRUCT的该工具已被用于预测中枢神经系统活性。从世界药物索引（WDI）中提取了具有中枢神经系统活性和无活性药物的数据集。SUBSTRUCT程序预测中枢神经系统活性的效果与一个复杂得多的人工神经网络模型相当。SUBSTRUCT对数据集的区分准确率约为80%。亚结构分析还显示，中枢神经系统活性药物和无活性药物之间的亚结构谱存在惊人的巨大差异。