MRC/UVRI and LSHTM Uganda Research Unit, P. O. Box 49, Plot 51-59 Nakiwogo Road, Entebbe, Uganda.
Institute of Human Virology, Abuja, Nigeria.
BMC Infect Dis. 2020 Feb 22;20(1):172. doi: 10.1186/s12879-020-4876-4.
Identifying immunogens that induce HIV-1-specific immune responses is a lengthy process that can benefit from computational methods, which predict T-cell epitopes for various HLA types.
We tested the performance of the NetMHCpan4.0 computational neural network in re-identifying 93 T-cell epitopes that had been previously independently mapped using the whole proteome IFN-γ ELISPOT assays in 6 HLA class I typed Ugandan individuals infected with HIV-1 subtypes A1 and D. To provide a benchmark we compared the predictions for NetMHCpan4.0 to MHCflurry1.2.0 and NetCTL1.2.
NetMHCpan4.0 performed best correctly predicting 88 of the 93 experimentally mapped epitopes for a set length of 9-mer and matched HLA class I alleles. Receiver Operator Characteristic (ROC) analysis gave an area under the curve (AUC) of 0.928. Setting NetMHCpan4.0 to predict 11-14mer length did not improve the prediction (37-79 of 93 peptides) with an inverse correlation between the number of predictions and length set. Late time point peptides were significantly stronger binders than early peptides (Wilcoxon signed rank test: p = 0.0000005). MHCflurry1.2.0 similarly predicted all but 2 of the peptides that NetMHCpan4.0 predicted and NetCTL1.2 predicted only 14 of the 93 experimental peptides.
NetMHCpan4.0 class I epitope predictions covered 95% of the epitope responses identified in six HIV-1 infected individuals, and would have reduced the number of experimental confirmatory tests by > 80%. Algorithmic epitope prediction in conjunction with HLA allele frequency information can cost-effectively assist immunogen design through minimizing the experimental effort.
识别能够诱导 HIV-1 特异性免疫反应的免疫原是一个漫长的过程，可以通过计算方法来加速这一过程，这些方法可以预测各种 HLA 类型的 T 细胞表位。
我们测试了 NetMHCpan4.0 计算神经网络在重新识别 93 个 T 细胞表位方面的性能，这些表位之前已经通过在 6 名感染 HIV-1 亚型 A1 和 D 的乌干达个体中使用全蛋白质 IFN-γ ELISPOT 检测法独立地进行了映射。为了提供一个基准，我们将 NetMHCpan4.0 的预测结果与 MHCflurry1.2.0 和 NetCTL1.2.0 进行了比较。
对于设定的 9 -mer 长度和匹配的 HLA Ⅰ类等位基因，NetMHCpan4.0 正确预测了 93 个实验映射表位中的 88 个，表现最佳。接收者操作特征（ROC）分析得到的曲线下面积（AUC）为 0.928。将 NetMHCpan4.0 设置为预测 11-14mer 长度并没有提高预测准确性（93 个肽中的 37-79 个），而且预测数量和长度设置之间呈反比关系。晚期肽比早期肽具有更强的结合能力（Wilcoxon 符号秩检验：p=0.0000005）。MHCflurry1.2.0 同样预测了 NetMHCpan4.0 预测的所有肽，但除了 2 个之外，NetCTL1.2.0 仅预测了 93 个实验肽中的 14 个。
NetMHCpan4.0 Ⅰ类表位预测涵盖了 6 名 HIV-1 感染者中 95%的表位反应，如果使用 HLA 等位基因频率信息进行算法表位预测，可以通过将实验验证测试的数量减少超过 80%，从而有效地协助免疫原设计。
