Ensemble approaches for improving HLA Class I-peptide binding prediction
Ensemble approaches for improving HLA Class I-peptide binding prediction
复制标题
用于改进 HLA I 类肽结合预测的集成方法
DOI：
10.1016/j.jim.2010.09.007
复制
发表时间：
2011-11-30
影响因子：
2.2
通讯作者：
Zhu, Shanfeng
中科院分区：
文献类型：
--
作者：
Hu, Xihao;Mamitsuka, Hiroshi;Zhu, Shanfeng
准确预测与主要组织相容性复合体（MHC）I分子结合的多肽对于阐明免疫识别的机制和促进肽疫苗的设计具有重要意义。各种计算方法已被开发用于MHC I-肽结合预测，并且据报道，其中一些方法在最近的基准数据集上的评估中实现了高精度。为了参加免疫学竞赛中的机器学习（MLIC）预测人类白细胞抗原（HLA）结合肽，我们（复旦CS）利用集成方法，通过集成几个领先的预测器的输出，进一步提高预测性能。两种整体方法。PM和AvgTanh已用于参加MLIC。AvgTanh和PM在MLIC的所有20份提交材料中的平均AUC分别排名第四和第七。此外，AvgTanh还获得了9聚体HLA-A*0101类别的赢家。总体而言，竞赛结果验证了集成方法的有效性。(C)2010 Elsevier B. V.保留所有权利。
Accurately predicting peptides binding to major histocompatibility complex (MHC) I molecules is of great importance to immunologists for elucidating the underlying mechanism of immune recognition and facilitating the design of peptide-based vaccine. Various computational methods have been developed for MHC I-peptide binding prediction, and several of them are reported to achieve high accuracy in recent evaluation on benchmark datasets. For attending the machine learning in immunology competition (MLIC) in prediction of human leukocyte antigen (HLA)-binding peptides, we (FudanCS) have made use of ensemble approaches to further improve the prediction performance by integrating the outputs of several leading predictors. Two ensemble approaches. PM and AvgTanh, have been implemented for attending MLIC. AvgTanh and PM achieved the fourth and the seventh out of all 20 submissions in MLIC in terms of the average AUC. In addition, AvgTanh was awarded the winner in the category of HLA-A*0101 of 9-mer. Overall, the competition results validate the effectiveness of ensemble approaches. (C) 2010 Elsevier B.V. All rights reserved.