AUTHOR=Wu Jingcheng , Wang Wenzhe , Zhang Jiucheng , Zhou Binbin , Zhao Wenyi , Su Zhixi , Gu Xun , Wu Jian , Zhou Zhan , Chen Shuqing 

TITLE=DeepHLApan: A Deep Learning Approach for Neoantigen Prediction Considering Both HLA-Peptide Binding and Immunogenicity

JOURNAL=Frontiers in Immunology

VOLUME=10

YEAR=2019

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2019.02559

DOI=10.3389/fimmu.2019.02559

ISSN=1664-3224

ABSTRACT=<p>Neoantigens play important roles in cancer immunotherapy. Current methods used for neoantigen prediction focus on the binding between human leukocyte antigens (HLAs) and peptides, which is insufficient for high-confidence neoantigen prediction. In this study, we apply deep learning techniques to predict neoantigens considering both the possibility of HLA-peptide binding (binding model) and the potential immunogenicity (immunogenicity model) of the peptide-HLA complex (pHLA). The binding model achieves comparable performance with other well-acknowledged tools on the latest Immune Epitope Database (IEDB) benchmark datasets and an independent mass spectrometry (MS) dataset. The immunogenicity model could significantly improve the prediction precision of neoantigens. The further application of our method to the mutations with pre-existing T-cell responses indicating its feasibility in clinical application. DeepHLApan is freely available at <ext-link ext-link-type="uri" xlink:href="https://github.com/jiujiezz/deephlapan" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/jiujiezz/deephlapan</ext-link> and <ext-link ext-link-type="uri" xlink:href="http://biopharm.zju.edu.cn/deephlapan" xmlns:xlink="http://www.w3.org/1999/xlink">http://biopharm.zju.edu.cn/deephlapan</ext-link>.</p>