TMSEG: Novel prediction of transmembrane helices.
TMSEG: Novel prediction of transmembrane helices.
复制标题
DOI：
10.1002/prot.25155
复制
发表时间：
2016-11
影响因子：
2.9
通讯作者：
Rost, Burkhard
中科院分区：
文献类型：
--
作者：
Bernhofer, Michael;Kloppmann, Edda;Reeb, Jonas;Rost, Burkhard
关键词：
跨膜蛋白（TMPs）是重要的药物靶点，因为它们对信号传导、调节和运输至关重要。尽管取得了重要的突破，但实验结构的确定仍然具有挑战性。各种方法通过预测跨膜螺旋（TMHs）弥补了这一差距，但仍有改进的空间。本文提出了一种新的TMSEG方法，用于识别TMPs并准确预测其TMHs及其拓扑结构。该方法将机器学习与经验过滤器相结合。在41个TMPs和285个可溶性蛋白的非冗余数据集上进行测试，并应用严格的性能测量，TMSEG的性能优于我们手中的最先进的技术。TMSEG正确区分螺旋型TMPs和其他蛋白的灵敏度为98±2%，假阳性率低至3±1%。个体TMHs预测精度为87±3%，召回率为84±3%。此外，在63±6%的螺旋TMPs中，正确预测了所有TMHs的位置及其内外拓扑结构。有两个主要特性将TMSEG与其他方法区分开来。首先，在一个生物体中发现所有螺旋型tmp的错误显著减少。例如，在人类中，与现有的第二和第三最佳方法相比，这导致200和1600个错误分类，比简单的基于疏水性的方法减少4400个错误分类。其次，TMSEG为任何现有方法提供了附加改进。
Transmembrane proteins (TMPs) are important drug targets because they are essential for signaling, regulation, and transport. Despite important breakthroughs, experimental structure determination remains challenging for TMPs. Various methods have bridged the gap by predicting transmembrane helices (TMHs), but room for improvement remains. Here, we present TMSEG, a novel method identifying TMPs and accurately predicting their TMHs and their topology. The method combines machine learning with empirical filters. Testing it on a non-redundant dataset of 41 TMPs and 285 soluble proteins, and applying strict performance measures, TMSEG outperformed the state-of-the-art in our hands. TMSEG correctly distinguished helical TMPs from other proteins with a sensitivity of 98±2% and a false positive rate as low as 3±1%. Individual TMHs were predicted with a precision of 87±3% and recall of 84±3%. Furthermore, in 63±6% of helical TMPs the placement of all TMHs and their inside/outside topology was correctly predicted. There are two main features that distinguish TMSEG from other methods. First, the errors in finding all helical TMPs in an organism are significantly reduced. For example, in human this leads to 200 and 1600 fewer misclassifications compared to the 2nd and 3rd best method available, and 4400 fewer mistakes than by a simple hydrophobicity-based method. Second, TMSEG provides an add-on improvement for any existing method to benefit from.
登录
查看更多内容
影响因子：
5.8
作者：
Granseth, Erik;Viklund, Hakan;Elofsson, Arne
通讯作者：
Elofsson, Arne
影响因子：
3
作者：
Rath EM;Tessier D;Campbell AA;Lee HC;Werner T;Salam NK;Lee LK;Church WB
通讯作者：
Church WB
影响因子：
14.9
作者：
Kozma D;Simon I;Tusnády GE
通讯作者：
Tusnády GE
影响因子：
14.9
作者：
UniProt Consortium
通讯作者：
UniProt Consortium
影响因子：
5.8
作者：
Jones, David T.
通讯作者：
Jones, David T.