Department of Computer Science, University of Bristol, Woodland Road, Bristol BS8 1UB, UK.
Bioinformatics. 2010 Mar 1;26(5):596-602. doi: 10.1093/bioinformatics/btq020. Epub 2010 Feb 3.
Some first order methods for protein sequence analysis inherently treat each position as independent. We develop a general framework for introducing longer range interactions. We then demonstrate the power of our approach by applying it to secondary structure prediction; under the independence assumption, sequences produced by existing methods can produce features that are not protein like, an extreme example being a helix of length 1. Our goal was to make the predictions from state of the art methods more realistic, without loss of performance by other measures.
Our framework for longer range interactions is described as a k-mer order model. We succeeded in applying our model to the specific problem of secondary structure prediction, to be used as an additional layer on top of existing methods. We achieved our goal of making the predictions more realistic and protein like, and remarkably this also improved the overall performance. We improve the Segment OVerlap (SOV) score by 1.8%, but more importantly we radically improve the probability of the real sequence given a prediction from an average of 0.271 per residue to 0.385. Crucially, this improvement is obtained using no additional information.
一些用于蛋白质序列分析的一阶方法本质上将每个位置视为独立的。我们开发了一个引入长程相互作用的通用框架。然后，我们通过将其应用于二级结构预测来展示我们方法的强大功能；在独立性假设下，现有方法生成的序列可能会产生不具有蛋白质特征的特征，一个极端的例子是长度为 1 的螺旋。我们的目标是使最先进方法的预测更加真实，而不会因其他指标而降低性能。
我们的长程相互作用框架描述为 k-mer 阶模型。我们成功地将我们的模型应用于二级结构预测这一具体问题，用作现有方法之上的附加层。我们实现了使预测更加真实和具有蛋白质特征的目标，值得注意的是，这也提高了整体性能。我们将段重叠（SOV）得分提高了 1.8%，但更重要的是，我们将给定预测的真实序列的概率从平均每残基 0.271 显著提高到 0.385。至关重要的是，这一改进是在不使用任何额外信息的情况下实现的。
