Additional file 1: of NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets

Predictive performance on different alleles and peptide lengths for the allmer and 9mer predictive methods. The two methods were trained as described in the text. The predictive performance was measured in terms of Pearsonâ s correlation coefficient (PCC) and area under the ROC curve (AUC), the latter using a binding threshold of 500 nM. (XLSX 70 kb)

针对allmer与9mer两种预测方法，评估其在不同等位基因及肽段长度下的预测性能。两种预测方法均按照本文所述流程完成训练。本研究以皮尔逊相关系数（Pearson Correlation Coefficient，PCC）与受试者工作特征曲线下面积（AUC）作为预测性能的评估指标，其中AUC的计算采用500 nM的结合阈值。（XLSX格式，70 KB）