美国斯坦福大学Ash A. Alizadeh研究组通过整合深度学习方法，预测 II类HLA对抗原的呈递。 该项研究成果在线发表于2019年10月14日的《自然—生物技术》。

研究人员描述了MARIA（具有递归集成架构的主要组织相容性复合体分析），一种多模态递归神经网络，用于在许多感兴趣的基因中预测特定情况下II类白细胞抗原（HLA）呈递抗原的可能性等位基因。除了进行体外结合测试外，还利用质谱对MARIA鉴定的HLA结合肽段进行了序列分析，以及抗原基因的表达水平和蛋白酶切割位点的标记。因为它利用了这些多样化的训练数据和改进的机器学习框架，所以MARIA（曲线下面积= 0.89–0.92）优于现有的验证数据集中的方法。

在独立的癌症新抗原研究中，具有较高MARIA评分的肽更有可能引起强烈的CD4 ⁺ T细胞反应。因此可以利用MARIA鉴定多种癌症和自身免疫性疾病中的免疫原性表位。

据悉，准确预测人II类白细胞抗原（HLA）对抗原呈递对于疫苗研发和癌症免疫治疗具有重要价值。目前，体外结合训练数据的计算方法受到训练数据不足和算法约束的限制。

附：英文原文

Title: Predicting HLA class II antigen presentation through integrated deep learning

Author: Binbin Chen, Michael S. Khodadoust, Niclas Olsson, Lisa E. Wagar, Ethan Fast, Chih Long Liu, Yagmur Muftuoglu, Brian J. Sworder, Maximilian Diehn, Ronald Levy, Mark M. Davis, Joshua E. Elias, Russ B. Altman, Ash A. Alizadeh

Issue&Volume: 2019-10-14

Abstract: 

Accurate prediction of antigen presentation by human leukocyte antigen (HLA) class II molecules would be valuable for vaccine development and cancer immunotherapies. Current computational methods trained on in vitro binding data are limited by insufficient training data and algorithmic constraints. Here we describe MARIA (major histocompatibility complex analysis with recurrent integrated architecture; https://maria.stanford.edu/), a multimodal recurrent neural network for predicting the likelihood of antigen presentation from a gene of interest in the context of specific HLA class II alleles. In addition to in vitro binding measurements, MARIA is trained on peptide HLA ligand sequences identified by mass spectrometry, expression levels of antigen genes and protease cleavage signatures. Because it leverages these diverse training data and our improved machine learning framework, MARIA (area under the curve = 0.89–0.92) outperformed existing methods in validation datasets. Across independent cancer neoantigen studies, peptides with high MARIA scores are more likely to elicit strong CD4+ T cell responses. MARIA allows identification of immunogenic epitopes in diverse cancers and autoimmune disease.

DOI: 10.1038/s41587-019-0280-2

Source: https://www.nature.com/articles/s41587-019-0280-2