Modeling anti-Trypanosoma cruzi Activity of N-Oxide Containing Heterocycles
详细信息 查看全文
- 作者：Mariana Boiani ; Hugo Cerecetto ; Mercedes Gonzá ; lez ; Johann Gasteiger
- 刊名：Journal of Chemical Information and Modeling
- 出版年：2008
- 出版时间：January 2008
- 年：2008
- 卷：48
- 期：1
- 页码：213 - 219
- 全文大小：219K
- 年卷期：v.48,no.1(January 2008)
- ISSN：1549-960X
文摘
In the present study a systematic approach was used to model the anti-T. cruzi activity of a series of N-oxidecontaining heterocycles belonging to four chemical families with a wide structural diversity. The proposedmode of action implies the reduction of the N-oxide moiety; however, the biochemical mechanism underlyingthe anti-T. cruzi activity is still unkown. For structural representation two types of descriptors wereanalyzed: quantum chemical (AM1) global descriptors and properties coded by radial distribution function(RDF). Both types of descriptors point to the relevance of electronic properties. The local-RDF (LRDF)identified an electrophilic center at 4.1-4.9 Å from the oxygen atom of the N-oxide moiety, although otherproperties are required to explain the biological activity. While the mode of action of N-oxide containingheterocycles is still unknown, the results obtained here strengthen the importance of the electrophilic characterof the molecule and the possible participation of the heterocycle in a reduction process. The ability of thesedescriptors to distinguish among activity classes was assessed using Kohonen neural networks, and the bestclustering descriptors were later used for model building. Different learning algorithms were used for modeldevelopment, and stratified 10-fold cross-validation was used to evaluate the performance of each classifier.The best results were obtained using k-nearest neighbors (k-NN) and decision tree (J48) methods combinedwith global descriptors. Since tree-based methods are easily translated into classification rules, the J48 modelis a useful tool in the de novo construction of new N-oxide containing heterocycle lead structures.