...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Molecular BioSystems >Applying random forest and subtractive fuzzy c-means clustering techniques for the development of a novel G protein-coupled receptor discrimination method using pseudo amino acid compositions
【24h】

Applying random forest and subtractive fuzzy c-means clustering techniques for the development of a novel G protein-coupled receptor discrimination method using pseudo amino acid compositions

机译：应用随机森林和减法模糊c均值聚类技术开发使用伪氨基酸成分的新型G蛋白偶联受体识别方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

G protein-coupled receptors (GPCRs) constitute the largest superfamily of integral membrane proteins (IMPs) and they tremendously contribute in the flow of information into cells. In this study, the random forest (RF) and the subtractive fuzzy c-means clustering (SBC) methods have been used to determine the importance of input variables and discriminate GPCRs from non-GPCRs using twenty amino acid and fifty pseudo amino acid compositions derived from GPCR sequences. The studied dataset was retrieved from the UniProt/SWISSPROT database and consists of 1000 GPCR and 1000 non-GPCR reviewed sequences. The top ranked RF-SBC-based model discriminates GPCRs and non-GPCRs successfully with the accuracy, sensitivity, specificity and Matthew's coefficient correlation (MCC) rates of 99.15%, 99.60%, 98.70% and 0.983%, respectively. These rates were obtained from averaged values of 5-fold cross validation using only twenty four out of fifty pseudo amino acid composition features. The results show that the proposed RF-SBC-based model outperforms other existing algorithms in terms of the evaluated performance criteria.
机译：G蛋白偶联受体（GPCR）构成了完整的膜蛋白（IMP）的最大超家族，它们极大地促进了信息进入细胞的流动。在这项研究中，随机森林（RF）和减法模糊c均值聚类（SBC）方法已用于确定输入变量的重要性，并使用衍生的二十种氨基酸和五十种伪氨基酸成分来区分GPCR与非GPCR从GPCR序列。从UniProt / SWISSPROT数据库检索研究的数据集，该数据集由1000个GPCR和1000个非GPCR审查序列组成。排名靠前的基于RF-SBC的模型成功地区分了GPCR和非GPCR，其准确性，敏感性，特异性和马修系数相关（MCC）率分别为99.15％，99.60％，98.70％和0.983％。这些比率是使用50个伪氨基酸组成特征中的24个从5倍交叉验证的平均值获得的。结果表明，在评估的性能标准方面，所提出的基于RF-SBC的模型优于其他现有算法。

著录项

  • 来源
    《Molecular BioSystems》 |2015年第8期|2364-2372|共9页
  • 作者

    Babak Sokouti; Farshad Rezvan; Siavoush Dastmalchi;

  • 作者单位

    Biotechnology Research Center, Tabriz University of Medical Sciences, Tabriz, 5165665813, Iran;

    Biotechnology Research Center, Tabriz University of Medical Sciences, Tabriz, 5165665813, Iran;

    Biotechnology Research Center and School of Pharmacy, Tabriz University of Medical Sciences, Tabriz, 5165665813, Iran;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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