Machine-Learning Prediction of Tumor Antigen Immunogenicity in the Selection of Therapeutic Epitopes

Cancer Immunology Research - Tập 7 Số 10 - Trang 1591-1604 - 2019
Christof C. Smith1,2, Shengjie Chai2,3, Amber R. Washington2, Samuel Lee2, Elisa Landoni2, Kevin Field2, Jason Garness2, Lisa M. Bixby2, Sara R. Selitsky4,5,6, Joel S. Parker4,5,6, Barbara Savoldo2,7, Jonathan S. Serody1,2,8, Benjamin G. Vincent1,2,3,8,9
11Department of Microbiology and Immunology, UNC School of Medicine, Chapel Hill, North Carolina.
22Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina.
33Curriculum in Bioinformatics and Computational Biology, UNC School of Medicine, Chapel Hill, North Carolina.
44Lineberger Bioinformatics Core, Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina.
55Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina.
6Lineberger Bioinformatics Core, Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina.
76Department of Pediatrics, UNC School of Medicine, Chapel Hill, North Carolina.
87Department of Medicine, Division of Hematology/Oncology, UNC School of Medicine, Chapel Hill, North Carolina.
98Computational Medicine Program, UNC School of Medicine, Chapel Hill, North Carolina.

Tóm tắt

Abstract Current tumor neoantigen calling algorithms primarily rely on epitope/major histocompatibility complex (MHC) binding affinity predictions to rank and select for potential epitope targets. These algorithms do not predict for epitope immunogenicity using approaches modeled from tumor-specific antigen data. Here, we describe peptide-intrinsic biochemical features associated with neoantigen and minor histocompatibility mismatch antigen immunogenicity and present a gradient boosting algorithm for predicting tumor antigen immunogenicity. This algorithm was validated in two murine tumor models and demonstrated the capacity to select for therapeutically active antigens. Immune correlates of neoantigen immunogenicity were studied in a pan-cancer data set from The Cancer Genome Atlas and demonstrated an association between expression of immunogenic neoantigens and immunity in colon and lung adenocarcinomas. Lastly, we present evidence for expression of an out-of-frame neoantigen that was capable of driving antitumor cytotoxic T-cell responses. With the growing clinical importance of tumor vaccine therapies, our approach may allow for better selection of therapeutically relevant tumor-specific antigens, including nonclassic out-of-frame antigens capable of driving antitumor immunity.

Từ khóa


Tài liệu tham khảo

Gubin, 2015, Tumor neoantigens: building a framework for personalized cancer immunotherapy, J Clin Invest, 125, 3413, 10.1172/JCI80008

Castle, 2012, Exploiting the mutanome for tumor vaccination, Cancer Res, 72, 1081, 10.1158/0008-5472.CAN-11-3722

Kreiter, 2015, Mutant MHC class II epitopes drive therapeutic immune responses to cancer, Nature, 520, 692, 10.1038/nature14426

Kranz, 2016, Systemic RNA delivery to dendritic cells exploits antiviral defence for cancer immunotherapy, Nature, 534, 396, 10.1038/nature18300

Sahin, 2017, Personalized RNA mutanome vaccines mobilize poly-specific therapeutic immunity against cancer, Nature, 547, 222, 10.1038/nature23003

Ott, 2017, An immunogenic personal neoantigen vaccine for patients with melanoma, Nature, 547, 217, 10.1038/nature22991

Hoof, 2009, NetMHCpan, a method for MHC class i binding prediction beyond humans, Immunogenetics, 61, 1, 10.1007/s00251-008-0341-z

Nielsen, 2016, NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets, Genome Med, 8, 33, 10.1186/s13073-016-0288-x

Jurtz, 2017, NetMHCpan-4.0: improved peptide–MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data, J Immunol, 199, 3360, 10.4049/jimmunol.1700893

Andreatta, 2015, Accurate pan-specific prediction of peptide-MHC class II binding affinity with improved binding core identification, Immunogenetics, 67, 641, 10.1007/s00251-015-0873-y

Zhang, 2008, Immune epitope database analysis resource (IEDB-AR), Nucleic Acids Res, 36, W513, 10.1093/nar/gkn254

Kim, 2012, Immune epitope database analysis resource, Nucleic Acids Res, 40, W525, 10.1093/nar/gks438

O'Donnell, 2018, MHCflurry: open-source class I MHC binding affinity prediction, Cell Syst, 7, 129, 10.1016/j.cels.2018.05.014

Karosiene, 2012, NetMHCcons: a consensus method for the major histocompatibility complex class I predictions, Immunogenetics, 64, 177, 10.1007/s00251-011-0579-8

Saito, 2018, Molecular subtype-specific immunocompetent models of high-grade urothelial carcinoma reveal differential neoantigen expression and response to immunotherapy, Cancer Res, 78, 3954, 10.1158/0008-5472.CAN-18-0173

Colli, 2016, Burden of nonsynonymous mutations among TCGA cancers and candidate immune checkpoint inhibitor responses, Cancer Res, 76, 3767, 10.1158/0008-5472.CAN-16-0170

Thorsson, 2018, The immune landscape of cancer, Immunity, 48, 812, 10.1016/j.immuni.2018.03.023

Jayasinghe, 2018, Systematic analysis of splice-site-creating mutations in cancer, Cell Rep, 23, 270, 10.1016/j.celrep.2018.03.052

Kahles, 2018, Comprehensive analysis of alternative splicing across tumors from 8,705 patients, Cancer Cell, 34, 211, 10.1016/j.ccell.2018.07.001

Laumont, 2018, Noncoding regions are the main source of targetable tumor-specific antigens, Sci Transl Med, 10, eaau5516, 10.1126/scitranslmed.aau5516

Weiss, 1987, Slippery runs, shifty stops, backward steps, and forward hops: -2, -1, +1, +2, +5, and +6 ribosomal frameshifting, Cold Spring Harb Symp Quant Biol, 52, 687, 10.1101/SQB.1987.052.01.078

Saulquin, 2002, +1 Frameshifting as a novel mechanism to generate a cryptic cytotoxic T lymphocyte epitope derived from human interleukin 10, J Exp Med, 195, 353, 10.1084/jem.20011399

Macejak, 1991, Internal initiation of translation mediated by the 5′ leader of a cellular mRNA, Nature, 353, 90, 10.1038/353090a0

Bullock, 1997, Initiation codon scanthrough versus termination codon readthrough demonstrates strong potential for major histocompatibility complex class I–restricted cryptic epitope expression, J Exp Med, 186, 1051, 10.1084/jem.186.7.1051

Bullock, 1996, Ribosomal scanning past the primary initiation codon as a mechanism for expression of CTL epitopes encoded in alternative reading frames, J Exp Med, 184, 1319, 10.1084/jem.184.4.1319

Malarkannan, 1999, Presentation of out-of-frame peptide/MHC class I complexes by a novel translation initiation mechanism, Immunity, 10, 681, 10.1016/S1074-7613(00)80067-9

Van Den Eynde, 1999, A new antigen recognized by cytolytic T lymphocytes on a human kidney tumor results from reverse strand transcription, J Exp Med, 190, 1793, 10.1084/jem.190.12.1793

Bruce, 1986, tRNA anticodon replacement experiments show that ribosomal frameshifting can be caused by doublet decoding, Proc Natl Acad Sci U S A, 83, 5062, 10.1073/pnas.83.14.5062

Bruce, 2017, Type 2 innate lymphoid cells treat and prevent acute gastrointestinal graft-versus-host disease, J Clin Invest, 127, 1813, 10.1172/JCI91816

Roberts, 2012, Combined PI3K/mTOR and MEK inhibition provides broad antitumor activity in faithful murine cancer models, Clin Cancer Res, 18, 5290, 10.1158/1078-0432.CCR-12-0563

Cooke, 1996, An experimental model of idiopathic pneumonia syndrome after bone marrow transplantation: I. The roles of minor H antigens and endotoxin, Blood, 88, 3230, 10.1182/blood.V88.8.3230.bloodjournal8883230

Wilkerson, 2014, Integrated RNA and DNA sequencing improves mutation detection in low purity tumors, Nucleic Acids Res, 42, e107, 10.1093/nar/gku489

Rajasagi, 2014, Systematic identification of personal tumor-specific neoantigens in chronic lymphocytic leukemia, Blood, 124, 453, 10.1182/blood-2014-04-567933

Pertea, 2015, StringTie enables improved reconstruction of a transcriptome from RNA-seq reads, Nat Biotechnol, 33, 290, 10.1038/nbt.3122

Haas, 2013, De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis, Nat Protoc, 8, 1494, 10.1038/nprot.2013.084

Coghill, 2010, Separation of graft-versus-host disease from graft-versus-leukemia responses by targeting CC-chemokine receptor 7 on donor T cells, Blood, 115, 4914, 10.1182/blood-2009-08-239848

Dolton, 2015, More tricks with tetramers: a practical guide to staining T cells with peptide-MHC multimers, Immunology, 146, 11, 10.1111/imm.12499

Wölfl, 2014, Antigen-specific activation and cytokine-facilitated expansion of naive, human CD8+T cells, Nat Protoc, 9, 950, 10.1038/nprot.2014.064

Quintarelli, 2008, Cytotoxic T lymphocytes directed to the preferentially expressed antigen of melanoma (PRAME) target chronic myeloid leukemia, Blood, 112, 1876, 10.1182/blood-2008-04-150045

Chan, 2009, Identification, molecular characterization, clinical prognosis, and therapeutic targeting of human bladder tumor-initiating cells, Proc Natl Acad Sci U S A, 106, 14016, 10.1073/pnas.0906549106

Prat, 2010, Phenotypic and molecular characterization of the claudin-low intrinsic subtype of breast cancer, Breast Cancer Res, 12, R68, 10.1186/bcr2635

Iglesia, 2014, Prognostic B-cell signatures using mRNA-seq in patients with subtype-specific breast and ovarian cancer, Clin Cancer Res, 20, 3818, 10.1158/1078-0432.CCR-13-3368

Kardos, 2016, Claudin-low bladder tumors are immune infiltrated and actively immune suppressed, JCI Insight, 1, e85902, 10.1172/jci.insight.85902

Bindea, 2013, Spatiotemporal dynamics of intratumoral immune cells reveal the immune landscape in human cancer, Immunity, 39, 782, 10.1016/j.immuni.2013.10.003

Love, 2014, Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2, Genome Biol, 15, 550, 10.1186/s13059-014-0550-8

Subramanian, 2005, Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles, Proc Natl Acad Sci U S A, 102, 15545, 10.1073/pnas.0506580102

Ingenuity Systems, 2013, Ingenuity Pathway Analysis, 5020

Huang, 2007, The DAVID gene functional classification tool: a novel biological module-centric algorithm to functionally analyze large gene lists, Genome Biol, 8, R183, 10.1186/gb-2007-8-9-r183

Bolotin, 2015, MiXCR: software for comprehensive adaptive immunity profiling, Nat Methods, 12, 380, 10.1038/nmeth.3364

Kim, 2018, Neopepsee: accurate genome-level prediction of neoantigens by harnessing sequence and amino acid immunogenicity information, Ann Oncol, 29, 1030, 10.1093/annonc/mdy022

Smith, 2018, Endogenous retroviral signatures predict immunotherapy response in clear cell renal cell carcinoma, J Clin Invest, 128, 4804, 10.1172/JCI121476

Irvine, 2015, Synthetic nanoparticles for vaccines and immunotherapy, Chem Rev, 115, 11109, 10.1021/acs.chemrev.5b00109

Jerby-Arnon, 2018, A cancer cell program promotes T cell exclusion and resistance to checkpoint blockade, Cell, 175, 984, 10.1016/j.cell.2018.09.006