RBM-MHC: A Semi-Supervised Machine-Learning Method for Sample-Specific Prediction of Antigen Presentation by HLA-I Alleles.
RBM-MHC: A Semi-Supervised Machine-Learning Method for Sample-Specific Prediction of Antigen Presentation by HLA-I Alleles.
复制标题
DOI：
10.1016/j.cels.2020.11.005
复制
发表时间：
2021-02-17
期刊：
影响因子：
9.3
通讯作者：
Walczak AM
中科院分区：
文献类型：
--
作者：
Bravi B;Tubiana J;Cocco S;Monasson R;Mora T;Walczak AM
最近，通过质谱仪或结合分析获得的免疫表型数据的增加，为研究高度多态的人类白细胞抗原I类(HL A-I)蛋白的内源性抗原提呈打开了可能性。最先进的方法可以高精度地预测在发布时在数据库中得到很好代表的人类白细胞抗原等位基因，但对于较罕见和特征较少的等位基因来说，性能较差。在这里，我们介绍了一种基于受限Boltzmann机器(RBMS)的方法来预测由人类白细胞抗原基因编码的主要组织相容性复合体(MHC)上的抗原-RBM-MHC。RBM-MHC可以在没有或少量HLA注释的自定义和新可用的样本上进行训练。RBM-MHC确保改进对稀有等位基因的预测，并匹配表征良好的等位基因的最新性能，同时对数据的要求较低。RBM-MHC是一种灵活且易于解释的方法，可以作为癌症新抗原和病毒表位的预测因子，作为特征发现的工具，并重建呈现在特定HLA分子上的多肽基序。用于定制和新产生的数据集的灵活的HLA呈现抗原预测对于表现不佳的HLA等位基因的预测比最先进的工具改进当只有几个可用的HLA注释时准确的HLA类型预测低维数据表示使特征发现Bravi等人得以实现。开发了一种灵活的机器学习方法，以预测通过组织相容性白细胞抗原(HLA)I类蛋白呈递给杀伤T细胞的病毒和癌症抗原。该方法的设计是为了在新获得的样本中提供准确的预测，对于这些样本，现有数据库中几乎无法检索到关于呈现的人类白细胞抗原蛋白的信息。
The recent increase of immunopeptidomics data, obtained by mass spectrometry or binding assays, opens up possibilities for investigating endogenous antigen presentation by the highly polymorphic human leukocyte antigen class I (HLA-I) protein. State-of-the-art methods predict with high accuracy presentation by HLA alleles that are well represented in databases at the time of release but have a poorer performance for rarer and less characterized alleles. Here, we introduce a method based on Restricted Boltzmann Machines (RBMs) for prediction of antigens presented on the Major Histocompatibility Complex (MHC) encoded by HLA genes—RBM-MHC. RBM-MHC can be trained on custom and newly available samples with no or a small amount of HLA annotations. RBM-MHC ensures improved predictions for rare alleles and matches state-of-the-art performance for well-characterized alleles while being less data demanding. RBM-MHC is shown to be a flexible and easily interpretable method that can be used as a predictor of cancer neoantigens and viral epitopes, as a tool for feature discovery, and to reconstruct peptide motifs presented on specific HLA molecules. Flexible predictor of HLA-presented antigens for custom and newly produced datasets Prediction for poorly represented HLA alleles is improved over state-of-the-art tools Accurate HLA type prediction when only a few HLA annotations are available Lower-dimensional data representation enables feature discovery Bravi et al. developed a flexible machine-learning method to predict viral and cancer antigens presented to killer T cells by histocompatibility leukocyte antigen (HLA) class I proteins. The method is designed to deliver accurate predictions in newly available samples for which little information on the presenting HLA proteins can be retrieved in existing databases.
登录
查看更多内容
DOI：
10.4049/jimmunol.1700893
发表时间：
2017-11-01
期刊：
Journal of immunology (Baltimore, Md. : 1950)
影响因子：
--
作者：
Jurtz V;Paul S;Andreatta M;Marcatili P;Peters B;Nielsen M
通讯作者：
Nielsen M
DOI：
10.4049/jimmunol.1302101
发表时间：
2013-12-15
期刊：
Journal of immunology (Baltimore, Md. : 1950)
影响因子：
--
作者：
Paul S;Weiskopf D;Angelo MA;Sidney J;Peters B;Sette A
通讯作者：
Sette A
影响因子：
32.4
作者：
Abelin JG;Keskin DB;Sarkizova S;Hartigan CR;Zhang W;Sidney J;Stevens J;Lane W;Zhang GL;Eisenhaure TM;Clauser KR;Hacohen N;Rooney MS;Carr SA;Wu CJ
通讯作者：
Wu CJ
影响因子：
3.7
作者：
Nielsen M;Lundegaard C;Blicher T;Lamberth K;Harndahl M;Justesen S;Røder G;Peters B;Sette A;Lund O;Buus S
通讯作者：
Buus S
影响因子：
--
作者：
Forbes, S A;Beare, D;Campbell, P J
通讯作者：
Campbell, P J