首页> 外文期刊>Journal of Bioinformatics and Computational Biology >TOPTMH: TOPOLOGY PREDICTOR FOR TRANSMEMBRANE α-HELICES
【24h】

TOPTMH: TOPOLOGY PREDICTOR FOR TRANSMEMBRANE α-HELICES

机译:TOPTMH:跨膜α-头盔的拓扑预测器

获取原文
获取原文并翻译 | 示例
           

摘要

Alpha-helical transmembrane proteins mediate many key biological processes and representn20%–30% of all genes in many organisms. Due to the difficulties in experimentallyndetermining their high-resolution 3D structure, computational methods to predict thenlocation and orientation of transmembrane helix segments using sequence informationnare essential. We present TOPTMH, a new transmembrane helix topology predictionnmethod that combines support vector machines, hidden Markov models, and a widelynused rule-based scheme. The contribution of this work is the development of a predictionnapproach that first uses a binary SVM classifier to predict the helix residues and then itnemploys a pair of HMM models that incorporate the SVM predictions and hydropathybasednfeatures to identify the entire transmembrane helix segments by capturing thenstructural characteristics of these proteins. TOPTMH outperforms state-of-the-art predictionnmethods and achieves the best performance on an independent static benchmark.
机译:α-螺旋跨膜蛋白介导许多关键的生物学过程,占许多生物中所有基因的20%–30%。由于难以通过实验确定其高分辨率3D结构,因此使用序列信息预测跨膜螺旋片段的位置和方向的计算方法是必不可少的。我们提出TOPTMH,这是一种新的跨膜螺旋拓扑预测方法,它结合了支持向量机,隐马尔可夫模型和广泛使用的基于规则的方案。这项工作的贡献在于开发了一种预测方法,该方法首先使用二元SVM分类器预测螺旋残基,然后使用一对结合了SVM预测和亲水性特征的HMM模型,通过捕获膜的结构特征来识别整个跨膜螺旋段。这些蛋白质。 TOPTMH胜过最新的预测方法,并在独立的静态基准上达到最佳性能。

著录项

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