首页> 外国专利> METHOD FOR PREDICTING PROTEIN-BINDING SITES IN A DNA SEQUENCE WITH CONSIDERATION OF BINDING PARTNERS

METHOD FOR PREDICTING PROTEIN-BINDING SITES IN A DNA SEQUENCE WITH CONSIDERATION OF BINDING PARTNERS

机译:考虑结合伙伴的DNA序列中蛋白质结合位点的预测方法

摘要

The present invention relates to a method for predicting a base binding to protein in a DNA sequence, and has developed a method for predicting protein-binding sites in a DNA sequence with consideration for DNA binding partners. The present invention has developed a support vector machine (SVM) model for predicting a DNA base which binds with protein using both DNA and protein sequences and a SVM model for predicting a base which binds with protein only using a DNA sequence for the comparison, and thus it was confirmed that predicting using both the DNA and protein sequences was excellent in most of the performance measurement as compared to predicting only using the DNA sequence, and that the new model can predict different binding sites for a given DNA sequence when the partner changes. Therefore, the present invention can be useful for biochemical experiments since the base of protein binding DNA can be predicted only with sequence data even if the structure is unknown.
机译:本发明涉及预测与DNA序列中的蛋白质的碱基结合的方法,并且已经开发了一种考虑到DNA结合伴侣而预测DNA序列中的蛋白质结合位点的方法。本发明已经开发了用于使用DNA和蛋白质序列预测与蛋白质结合的DNA碱基的支持向量机(SVM)模型和用于仅使用DNA序列进行比较来预测与蛋白质结合的碱基的SVM模型,以及因此,可以肯定的是,与仅使用DNA序列进行预测相比,使用DNA和蛋白质序列进行预测在大多数性能测量中均表现出色,并且当伴侣改变时,新模型可以预测给定DNA序列的不同结合位点。因此,本发明可用于生化实验,因为即使结构未知,也只能用序列数据预测蛋白质结合DNA的碱基。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号