Artificial intelligence applied in neoantigen identification facilitates personalized cancer immunotherapy

被引:30
作者
Cai, Yu [1 ]
Chen, Rui [1 ]
Gao, Shenghan [1 ]
Li, Wenqing [1 ]
Liu, Yuru [1 ]
Su, Guodong [1 ]
Song, Mingming [1 ]
Jiang, Mengju [1 ]
Jiang, Chao [2 ]
Zhang, Xi [1 ]
机构
[1] Northwest Univ, Sch Med, Xian, Shaanxi, Peoples R China
[2] Xian Med Univ, Affiliated Hosp 2, Dept Neurol, Xian, Shaanxi, Peoples R China
基金
中国国家自然科学基金;
关键词
neoantigen prediction; cancer neoantigen; cancer immunotherapy; artificial intelligence; next generation sequencing; MHC CLASS-I; REACTIVE T-CELLS; PEPTIDE BINDING; PREDICTION; TUMOR; IMMUNOGENICITY; POTENTIALS; PIPELINE;
D O I
10.3389/fonc.2022.1054231
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
The field of cancer neoantigen investigation has developed swiftly in the past decade. Predicting novel and true neoantigens derived from large multi-omics data became difficult but critical challenges. The rise of Artificial Intelligence (AI) or Machine Learning (ML) in biomedicine application has brought benefits to strengthen the current computational pipeline for neoantigen prediction. ML algorithms offer powerful tools to recognize the multidimensional nature of the omics data and therefore extract the key neoantigen features enabling a successful discovery of new neoantigens. The present review aims to outline the significant technology progress of machine learning approaches, especially the newly deep learning tools and pipelines, that were recently applied in neoantigen prediction. In this review article, we summarize the current state-of-the-art tools developed to predict neoantigens. The standard workflow includes calling genetic variants in paired tumor and blood samples, and rating the binding affinity between mutated peptide, MHC (I and II) and T cell receptor (TCR), followed by characterizing the immunogenicity of tumor epitopes. More specifically, we highlight the outstanding feature extraction tools and multi-layer neural network architectures in typical ML models. It is noted that more integrated neoantigen-predicting pipelines are constructed with hybrid or combined ML algorithms instead of conventional machine learning models. In addition, the trends and challenges in further optimizing and integrating the existing pipelines are discussed.
引用
收藏
页数:22
相关论文
共 137 条
[1]   Defining HLA-II Ligand Processing and Binding Rules with Mass Spectrometry Enhances Cancer Epitope Prediction [J].
Abelin, Jennifer G. ;
Harjanto, Dewi ;
Malloy, Matthew ;
Suri, Prerna ;
Colson, Tyler ;
Goulding, Scott P. ;
Creech, Amanda L. ;
Serrano, Lia R. ;
Nasir, Gibran ;
Nasrullah, Yusuf ;
McGann, Christopher D. ;
Velez, Diana ;
Ting, Ying S. ;
Poran, Asaf ;
Rothenberg, Daniel A. ;
Chhangawala, Sagar ;
Rubinsteyn, Alex ;
Hammerbacher, Jeff ;
Gaynor, Richard B. ;
Fritsch, Edward F. ;
Greshock, Joel ;
Oslund, Rob C. ;
Barthelme, Dominik ;
Addona, Terri A. ;
Arleta, Christina M. ;
Rooney, Michael S. .
IMMUNITY, 2019, 51 (04) :766-+
[2]   Mass Spectrometry Profiling of HLA-Associated Peptidomes in Mono-allelic Cells Enables More Accurate Epitope Prediction [J].
Abelin, Jennifer G. ;
Keskin, Derin B. ;
Sarkizova, Siranush ;
Hartigan, Christina R. ;
Zhang, Wandi ;
Sidney, John ;
Stevens, Jonathan ;
Lane, William ;
Zhang, Guang Lan ;
Eisenhaure, Thomas M. ;
Clauser, Karl R. ;
Hacohen, Nir ;
Rooney, Michael S. ;
Carr, Steven A. ;
Wu, Catherine J. .
IMMUNITY, 2017, 46 (02) :315-326
[3]   Gapped sequence alignment using artificial neural networks: application to the MHC class I system [J].
Andreatta, Massimo ;
Nielsen, Morten .
BIOINFORMATICS, 2016, 32 (04) :511-517
[4]   Accurate pan-specific prediction of peptide-MHC class II binding affinity with improved binding core identification [J].
Andreatta, Massimo ;
Karosiene, Edita ;
Rasmussen, Michael ;
Stryhn, Anette ;
Buus, Soren ;
Nielsen, Morten .
IMMUNOGENETICS, 2015, 67 (11-12) :641-650
[5]   CloudNeo: a cloud pipeline for identifying patient-specific tumor neoantigens [J].
Bais, Preeti ;
Namburi, Sandeep ;
Gatti, Daniel M. ;
Zhang, Xinyu ;
Chuang, Jeffrey H. .
BIOINFORMATICS, 2017, 33 (19) :3110-3112
[6]   Evaluation of computational programs to predict HLA genotypes from genomic sequencing data [J].
Bauer, Denis C. ;
Zadoorian, Armella ;
Wilson, Laurence O. W. ;
Thorne, Natalie P. .
BRIEFINGS IN BIOINFORMATICS, 2018, 19 (02) :179-187
[7]   Principles and Practice of Explainable Machine Learning [J].
Belle, Vaishak ;
Papantonis, Ioannis .
FRONTIERS IN BIG DATA, 2021, 4
[8]   Artificial Intelligence in Cancer Research and Precision Medicine [J].
Bhinder, Bhavneet ;
Gilvary, Coryandar ;
Madhukar, Neel S. ;
Elemento, Olivier .
CANCER DISCOVERY, 2021, 11 (04) :900-915
[9]   An Analysis of Natural T Cell Responses to Predicted Tumor Neoepitopes [J].
Bjerregaard, Anne-Mette ;
Nielsen, Morten ;
Jurtz, Vanessa ;
Barra, Carolina M. ;
Hadrup, Sine Reker ;
Szallasi, Zoltan ;
Eklund, Aron Charles .
FRONTIERS IN IMMUNOLOGY, 2017, 8
[10]   MuPeXI: prediction of neo-epitopes from tumor sequencing data [J].
Bjerregaard, Anne-Mette ;
Nielsen, Morten ;
Hadrup, Sine Reker ;
Szallasi, Zoltan ;
Eklund, Aron Charles .
CANCER IMMUNOLOGY IMMUNOTHERAPY, 2017, 66 (09) :1123-1130