Kauffman Chris, Rangwala Huzefa, Karypis George
Department of Computer Science, University of Minnesota, 117 Pleasant St SE, Room 464, Minneapolis, MN 55455, USA.
Comput Syst Bioinformatics Conf. 2008;7:211-22.
In order to improve the prediction of protein-ligand binding sites through homology modeling, we incorporate knowledge of the binding residues into the modeling framework. Residues are identified as binding or nonbinding based on their true labels as well as labels predicted from structure and sequence. The sequence predictions were made using a support vector machine framework which employs a sophisticated window-based kernel. Binding labels are used with a very sensitive sequence alignment method to align the target and template. Relevant parameters governing the alignment process are searched for optimal values. Based on our results, homology models of the binding site can be improved if a priori knowledge of the binding residues is available. For target-template pairs with low sequence identity and high structural diversity our sequence-based prediction method provided sufficient information to realize this improvement.
为了通过同源建模改进蛋白质-配体结合位点的预测，我们将结合残基的知识纳入建模框架。根据残基的真实标签以及从结构和序列预测的标签，将残基识别为结合或非结合。序列预测使用支持向量机框架进行，该框架采用复杂的基于窗口的核。结合标签与一种非常灵敏的序列比对方法一起用于比对目标和模板。搜索控制比对过程的相关参数以获取最佳值。根据我们的结果，如果有结合残基的先验知识，结合位点的同源模型可以得到改进。对于具有低序列同一性和高结构多样性的目标-模板对，我们基于序列的预测方法提供了足够的信息来实现这种改进。
