DeepAntigen: a novel method for neoantigen prioritization via 3D genome and deep sparse learning
- 27 June 2020
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 36 (19) , 4894-4901
Abstract
The mutations of cancers can encode the seeds of their own destruction, in the form of T cell recognizable immunogenic peptides, also known as neoantigens. It is computationally challenging however, to accurately prioritize the potential neoantigen candidates according to their ability of activating the T cell immuno-response, especially when the somatic mutations are abundant. Although a few neoantigen prioritization methods have been proposed to address this issue, advanced machine learning model that is specifically designed to tackle this problem is still lacking. Moreover, none of the existing methods considers the original DNA loci of the neoantigens in the perspective of 3D genome which may provide key information for inferring neoantigens’ immunogenicity. In this study, we discovered that DNA loci of the immuno-positive and immuno-negative MHC-I neoantigens have distinct spatial distribution patterns across the genome. We therefore employed the 3D genome information along with an ensemble pMHC-I coding strategy, and developed a group feature selection based deep sparse neural network model (DNN-GFS) that is optimized for neoantigen prioritization. DNN-GFS demonstrated increased neoantigen prioritization power comparing to existing sequence-based approaches. We also developed a webserver named deepAntigen (http://yishi.sjtu.edu.cn/deepAntigen) that implements the DNN-GFS as well as other machine learning methods. We believe that this work provides a new perspective towards more accurate neoantigen prediction which eventually contribute to personalized cancer immunotherapy. Data and implementation are available on webserver: http://yishi.sjtu.edu.cn/deepAntigen Supplementary data are available at Bioinformatics online.Keywords
This publication has 55 references indexed in Scilit:
- Topological domains in mammalian genomes identified by analysis of chromatin interactionsNature, 2012
- Dana-Farber repository for machine learning in immunologyJournal of Immunological Methods, 2011
- Prediction of epitopes using neural network based methodsJournal of Immunological Methods, 2011
- The genomic complexity of primary human prostate cancerNature, 2011
- Gene deregulation and spatial genome reorganization near breakpoints prior to formation of translocations in anaplastic large cell lymphomaProceedings of the National Academy of Sciences, 2009
- Systematic and integrative analysis of large gene lists using DAVID bioinformatics resourcesNature Protocols, 2008
- NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8–11Nucleic Acids Research, 2008
- Spatial genome organization in the formation of chromosomal translocationsSeminars in Cancer Biology, 2007
- A consensus epitope prediction approach identifies the breadth of murine TCD8+-cell responses to vaccinia virusNature Biotechnology, 2006
- Imatinib Compared with Interferon and Low-Dose Cytarabine for Newly Diagnosed Chronic-Phase Chronic Myeloid LeukemiaNew England Journal of Medicine, 2003