3pHLA-score improves structure-based peptide-HLA binding affinity prediction.

3pHLA-score improves structure-based peptide-HLA binding affinity prediction.
复制标题

DOI:
10.1038/s41598-022-14526-x
复制
发表时间:
2022-06-24
期刊:
影响因子:
4.6
通讯作者:
Kavraki, Lydia E.
Kavraki, Lydia E.
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Conev, Anja;Devaurs, Didier;Rigo, Mauricio Menegatti;Antunes, Dinler Amaral;Kavraki, Lydia E.

文献摘要

参考文献

相似文献

多肽与人类白细胞抗原(人类白细胞抗原)受体的结合是触发免疫反应的先决条件。估计多肽-人类白细胞抗原(Phla)的结合是多肽疫苗靶标识别和表位发现管道的关键。结合亲和力预测的计算方法可以加速这些管道。目前,这些计算方法大多完全依赖于基于序列的数据,这导致了固有的局限性。最近的研究表明,基于结构的数据可以解决其中一些限制。在这项工作中,我们提出了一种新的基于机器学习(ML)结构的协议来预测多肽与人类白细胞抗原受体的结合亲和力。为此,我们通过解耦多肽中不同残基位置的能量贡献来设计ML模型的输入特征,这导致了我们新的每肽位置协议。以Rosetta的ref2015评分功能为基线,利用该协议开发了3PHLA-SCORE。我们的每肽位置方案的性能优于标准的训练方案,并导致精度召回曲线下的面积从0.82增加到0.99。3PHLA-SCORE在结构性虚拟筛选任务中优于广泛使用的评分功能(AutoDock4、Vina、Dope、Vinardo、FoldX、GradDock)。总体而言,这项工作使基于结构的方法离表位发现管道更近了一步,并可能有助于推进癌症和病毒疫苗的开发。
Binding of peptides to Human Leukocyte Antigen (HLA) receptors is a prerequisite for triggering immune response. Estimating peptide-HLA (pHLA) binding is crucial for peptide vaccine target identification and epitope discovery pipelines. Computational methods for binding affinity prediction can accelerate these pipelines. Currently, most of those computational methods rely exclusively on sequence-based data, which leads to inherent limitations. Recent studies have shown that structure-based data can address some of these limitations. In this work we propose a novel machine learning (ML) structure-based protocol to predict binding affinity of peptides to HLA receptors. For that, we engineer the input features for ML models by decoupling energy contributions at different residue positions in peptides, which leads to our novel per-peptide-position protocol. Using Rosetta’s ref2015 scoring function as a baseline we use this protocol to develop 3pHLA-score. Our per-peptide-position protocol outperforms the standard training protocol and leads to an increase from 0.82 to 0.99 of the area under the precision-recall curve. 3pHLA-score outperforms widely used scoring functions (AutoDock4, Vina, Dope, Vinardo, FoldX, GradDock) in a structural virtual screening task. Overall, this work brings structure-based methods one step closer to epitope discovery pipelines and could help advance the development of cancer and viral vaccines.
DOI: 10.1002/jlb.1mr1217-496r
发表时间: 2018-08
影响因子: 5.5
作者:
James KD;Jenkinson WE;Anderson G
通讯作者: Anderson G
DOI: 10.1002/jcc.21256
发表时间: 2009-12
影响因子: 3
作者:
Morris, Garrett M.;Huey, Ruth;Lindstrom, William;Sanner, Michel F.;Belew, Richard K.;Goodsell, David S.;Olson, Arthur J.
通讯作者: Olson, Arthur J.
DOI: 10.1021/acs.jctc.7b00125
发表时间: 2017-06-01
影响因子: 5.5
作者:
Alford, Rebecca F.;Leaver-Fay, Andrew;Gray, Jeffrey J.
通讯作者: Gray, Jeffrey J.
DOI: 10.1074/mcp.m116.063800
发表时间: 2017-02-01
影响因子: 7
作者:
Alpizar, Adab;Marino, Fabio;Marcilla, Miguel
通讯作者: Marcilla, Miguel
DOI: 10.1093/bioinformatics/btv639
发表时间: 2016-02-15
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Andreatta, Massimo;Nielsen, Morten
通讯作者: Nielsen, Morten