瑞士洛桑大学David Gfeller和Michal Bassani-Sternberg等研究人员，合作开发出可用于准确预测II型人类白细胞抗原分子（HLA-II）表位的新技术。该项研究成果在线发表在2019年10月14日的《自然—生物技术》杂志上。

研究人员将无偏倚质谱技术与模体逆卷积算法相结合，来描绘和分析从HLA-II分子洗脱的总共99265种独特的肽。然后，研究人员用这些数据训练了抗原决定簇预测算法，并改进了对病原体和与肿瘤相关的II类新表位的预测。

据介绍，HLA-II所呈现的表位的预测准确性有限，这限制了疫苗和治疗设计。

附：英文原文

Title: Robust prediction of HLA class II epitopes by deep motif deconvolution of immunopeptidomes

Author: Julien Racle, Justine Michaux, Georg Alexander Rockinger, Marion Arnaud, Sara Bobisse, Chloe Chong, Philippe Guillaume, George Coukos, Alexandre Harari, Camilla Jandus, Michal Bassani-Sternberg, David Gfeller

Issue&Volume: 2019-10-14

Abstract: 

Predictions of epitopes presented by class II human leukocyte antigen molecules (HLA-II) have limited accuracy, restricting vaccine and therapy design. Here we combined unbiased mass spectrometry with a motif deconvolution algorithm to profile and analyze a total of 99,265 unique peptides eluted from HLA-II molecules. We then trained an epitope prediction algorithm with these data and improved prediction of pathogen and tumor-associated class II neoepitopes.

DOI: 10.1038/s41587-019-0289-6

Source: https://www.nature.com/articles/s41587-019-0289-6