Ridder Lars, Wagener Markus
Molecular Design and Informatics, Organon, part of Schering-Plough Corporation, P.O. Box 20, 5340 BH Oss, The Netherlands.
ChemMedChem. 2008 May;3(5):821-32. doi: 10.1002/cmdc.200700312.
Predictions of potential metabolites based on chemical structure are becoming increasingly important in drug discovery to guide medicinal chemistry efforts that address metabolic issues and to support experimental metabolite screening and identification. Herein we present a novel rule-based method, SyGMa (Systematic Generation of potential Metabolites), to predict the potential metabolites of a given parent structure. A set of reaction rules covering a broad range of phase 1 and phase 2 metabolism has been derived from metabolic reactions reported in the Metabolite Database to occur in humans. An empirical probability score is assigned to each rule representing the fraction of correctly predicted metabolites in the training database. This score is used to refine the rules and to rank predicted metabolites. The current rule set of SyGMa covers approximately 70 % of biotransformation reactions observed in humans. Evaluation of the rule-based predictions demonstrated a significant enrichment of true metabolites in the top of the ranking list: while in total, 68 % of all observed metabolites in an independent test set were reproduced by SyGMa, a large part, 30 % of the observed metabolites, were identified among the top three predictions. From a subset of cytochrome P450 specific metabolites, 84 % were reproduced overall, with 66 % in the top three predicted phase 1 metabolites. A similarity analysis of the reactions present in the database was performed to obtain an overview of the metabolic reactions predicted by SyGMa and to support ongoing efforts to extend the rules. Specific examples demonstrate the use of SyGMa in experimental metabolite identification and the application of SyGMa to suggest chemical modifications that improve the metabolic stability of compounds.
在药物研发中，基于化学结构预测潜在代谢物对于指导解决代谢问题的药物化学研究以及支持实验性代谢物筛选和鉴定变得越来越重要。在此，我们提出一种新颖的基于规则的方法——SyGMa（潜在代谢物系统生成法），用于预测给定母体结构的潜在代谢物。我们从代谢物数据库中报道的发生在人体的代谢反应中推导得出了一组涵盖广泛的I相和II相代谢反应规则。为每个规则赋予一个经验概率分数，该分数代表训练数据库中正确预测的代谢物比例。此分数用于完善规则并对预测的代谢物进行排名。SyGMa当前的规则集涵盖了约70%在人体中观察到的生物转化反应。基于规则预测的评估表明，排名靠前的列表中真实代谢物有显著富集：在一个独立测试集中，SyGMa总共重现了所有观察到的代谢物的68%，其中很大一部分，即30%的观察到的代谢物，在前三的预测结果中被鉴定出来。对于细胞色素P450特异性代谢物的一个子集，总体上84%被重现，其中66%在前三个预测的I相代谢物中。对数据库中存在的反应进行了相似性分析，以概述SyGMa预测的代谢反应，并支持正在进行的扩展规则的努力。具体实例展示了SyGMa在实验性代谢物鉴定中的应用以及SyGMa在建议化学修饰以提高化合物代谢稳定性方面的应用。
