Comparing the chemical spaces of metabolites and available chemicals: models of metabolite-likeness
Comparing the chemical spaces of metabolites and available chemicals: models of metabolite-likeness
复制标题
DOI：
10.1007/s11030-006-9054-0
复制
发表时间：
2007-02-01
影响因子：
3.8
通讯作者：
Aires-de-Sousa, Joao
中科院分区：
文献类型：
--
作者：
Gupta, Sunil;Aires-de-Sousa, Joao
利用化学信息学技术，将参与代谢反应的化合物所覆盖的化学空间与购买化合物的随机数据集进行了比较。比较是基于3D结构，2D结构，或描述符的全局属性，通过自组织映射，随机森林，和分类树。观察到代谢物和非代谢物之间的重叠在由全局描述符定义的空间中最少，最具区别性的特征是OH基团的数量、芳族系统的存在和分子量。两个数据集之间的歧视，实现了高达97%的准确度。建立模型以产生代谢物相似性参数。观察到类似代谢物和快速生物降解性之间的关系。
The chemical space covered by compounds involved in metabolic reactions was compared with that of a random dataset of purchasable compounds by chemoinformatics techniques. The comparison was based on 3D structure, 2D structure, or descriptors of global properties, by means of self-organizing maps, random forests, and classification trees. The overlap between metabolites and non-metabolites was observed to be the least in the space defined by the global descriptors, the most discriminatory features being the number of OH groups, presence of aromatic systems, and molecular weight. Discrimination between the two datasets was achieved with accuracy up to 97%. Models were built to produce a metabolite-likeness parameter. A relationship between metabolite-likeness and ready biodegradability was observed.