Improved model quality assessment using ProQ2.
Improved model quality assessment using ProQ2.
复制标题
DOI：
10.1186/1471-2105-13-224
复制
发表时间：
2012-09-10
影响因子：
3
通讯作者：
Wallner B
中科院分区：
文献类型：
--
作者：
Ray A;Lindahl E;Wallner B
采用方法来评估建模的蛋白质结构的质量现在是生物信息学的标准实践。从广义上讲，这些技术可以分为一方面依赖于一致性预测的方法和另一方面依赖于单一模型的方法。共识方法通常在有明确共识的情况下表现得很好，但情况并非总是如此。特别是，在困难的情况下（缺乏共识）或模型非常相似的简单情况下，他们经常无法选择最佳模型。相比之下，单模型方法不受这些缺点的影响，并且可以潜在地应用于任何感兴趣的蛋白质以评估质量或作为基于采样的细化的评分函数。在这里，我们提出了一种新的单模型方法，ProQ 2，基于其前身ProQ的思想。ProQ 2是一种模型质量评估算法，它使用支持向量机来预测蛋白质模型的局部和全局质量。通过将先前使用的特征与更新的结构和预测特征相结合来获得改进的性能。最重要的贡献可以归因于使用残留物特定特征的轮廓加权和在整个模型上平均的使用特征，即使预测仍然是局部的。ProQ 2在检测高质量模型方面明显优于其前辈，与CASP 8和CASP 9中的第二佳单模型方法相比，所选一级模型的Z得分总和分别提高了20%和32%。在局部和全局水平上的模型的绝对质量评估也得到了改善。正确和局部预测分数之间的Pearson相关性在CASP 8上从0.59提高到0.70，在CASP 9上从0.62提高到0.68;与CASP 8和CASP 9中的次佳单一方法相比，全局分数与正确GDT_TS的相关性再次从0.75提高到0.80，从0.77提高到0.80。ProQ 2可在http://proq2.wallnerlab.org上获得。
Employing methods to assess the quality of modeled protein structures is now standard practice in bioinformatics. In a broad sense, the techniques can be divided into methods relying on consensus prediction on the one hand, and single-model methods on the other. Consensus methods frequently perform very well when there is a clear consensus, but this is not always the case. In particular, they frequently fail in selecting the best possible model in the hard cases (lacking consensus) or in the easy cases where models are very similar. In contrast, single-model methods do not suffer from these drawbacks and could potentially be applied on any protein of interest to assess quality or as a scoring function for sampling-based refinement. Here, we present a new single-model method, ProQ2, based on ideas from its predecessor, ProQ. ProQ2 is a model quality assessment algorithm that uses support vector machines to predict local as well as global quality of protein models. Improved performance is obtained by combining previously used features with updated structural and predicted features. The most important contribution can be attributed to the use of profile weighting of the residue specific features and the use features averaged over the whole model even though the prediction is still local. ProQ2 is significantly better than its predecessors at detecting high quality models, improving the sum of Z-scores for the selected first-ranked models by 20% and 32% compared to the second-best single-model method in CASP8 and CASP9, respectively. The absolute quality assessment of the models at both local and global level is also improved. The Pearson’s correlation between the correct and local predicted score is improved from 0.59 to 0.70 on CASP8 and from 0.62 to 0.68 on CASP9; for global score to the correct GDT_TS from 0.75 to 0.80 and from 0.77 to 0.80 again compared to the second-best single methods in CASP8 and CASP9, respectively. ProQ2 is available at http://proq2.wallnerlab.org.
登录
查看更多内容
影响因子：
2.9
作者：
Paluszewski, Martin;Karplus, Kevin
通讯作者：
Karplus, Kevin
影响因子：
14.9
作者：
Cheng, J;Randall, AZ;Sweredoski, MJ;Baldi, P
通讯作者：
Baldi, P
影响因子：
2.9
作者：
Kryshtafovych, Andriy;Fidelis, Krzysztof;Tramontano, Anna
通讯作者：
Tramontano, Anna
影响因子：
2.9
作者：
Benkert, Pascal;Tosatto, Silvio C. E.;Schwede, Torsten
通讯作者：
Schwede, Torsten
DOI：
10.1002/prot.340230412
发表时间：
1995-12-01
期刊：
PROTEINS-STRUCTURE FUNCTION AND GENETICS
影响因子：
--
作者：
Frishman, D;Argos, P
通讯作者：
Argos, P