Chang Stewart T, Ghosh Debashis, Kirschner Denise E, Linderman Jennifer J
Program in Bioinformatics, University of Michigan Ann Arbor, MI, USA.
Bioinformatics. 2006 Nov 15;22(22):2761-7. doi: 10.1093/bioinformatics/btl479. Epub 2006 Sep 25.
Algorithms for predicting peptide-MHC class II binding are typically similar, if not identical, to methods for predicting peptide-MHC class I binding despite known differences between the two scenarios. We investigate whether representing one of these differences, the greater range of peptide lengths binding MHC class II, improves the performance of these algorithms.
A non-linear relationship between peptide length and peptide-MHC class II binding affinity was identified in the data available for several MHC class II alleles. Peptide length was incorporated into existing prediction algorithms using one of several modifications: using regression to pre-process the data, using peptide length as an additional variable within the algorithm, or representing register shifting in longer peptides. For several datasets and at least two algorithms these modifications consistently improved prediction accuracy.
尽管已知肽与MHC I类结合和肽与MHC II类结合这两种情况存在差异，但预测肽与MHC II类结合的算法通常与预测肽与MHC I类结合的方法相似，甚至相同。我们研究了体现这两种情况差异之一的、与MHC II类结合的肽长度范围更广这一因素，是否能提高这些算法的性能。
在多个MHC II类等位基因的可用数据中，确定了肽长度与肽-MHC II类结合亲和力之间的非线性关系。使用以下几种修改方法之一，将肽长度纳入现有的预测算法中：使用回归对数据进行预处理、将肽长度作为算法中的一个附加变量，或表示较长肽中的寄存器移位。对于多个数据集和至少两种算法，这些修改一致提高了预测准确性。
