CoChat
Sign Up
Cited by 14vaccines and immunoinformatics approachesCancer Immunotherapy and BiomarkersComputational Drug Discovery Methods

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

GraphMHC: Neoantigen prediction model applying the graph neural network to molecular structure

Open access
Jeong, Hoyeon, Cho, Young-Rae, Gim, Jungsoo, Cha, Seung-Kuy, Kim, Maengsup, Kang, Dae Ryong·2024·PLOS ONE
DOI 10.1371/journal.pone.0291223PMC PMC10971776

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Neoantigens are tumor-derived peptides and are biomarkers that can predict prognosis related to immune checkpoint inhibition by estimating their binding to major histocompatibility complex (MHC) proteins. Although deep neural networks have been primarily used for these prediction models, it is difficult to interpret the models reported thus far as accurately representing the interactions between biomolecules. In this study, we propose the GraphMHC model, which utilizes a graph neural network model applied to molecular structure to simulate the binding between MHC proteins and peptide sequences. Amino acid sequences sourced from the immune epitope database (IEDB) undergo conversion into molecular structures. Subsequently, atomic intrinsic informations and inter-atomic connections are extracted and structured as a graph representation. Stacked graph attention and convolution layers comprise the GraphMHC network which classifies bindings. The prediction results from the test set using the GraphMHC model showed a high performance with an area under the receiver operating characteristic curve of 92.2% (91.9-92.5%), surpassing a baseline model. Moreover, by applying the GraphMHC model to melanoma patient data from The Cancer Genome Atlas project, we found a borderline difference (0.061) in overall survival and a significant difference in stromal score between the high and low neoantigen load groups. This distinction was not present in the baseline model. This study presents the first feature-intrinsic method based on biochemical molecular structure for modeling the binding between MHC protein sequences and neoantigen candidate peptide sequences. This model can provide highly accurate responsibility information that can predict the prognosis of immune checkpoint inhibitors to cancer patients who want to apply it.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0291223

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 84

  1. H Sung, 2021, Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA: a cancer journal for clinicians, 71, 209
  2. KW Jung, 2020, Prediction of cancer incidence and mortality in Korea, 2020, Cancer Research and Treatment: Official Journal of Korean Cancer Association, 52, 351, 10.4143/crt.2020.203 · DOI
  3. P Anand, 2008, Cancer is a preventable disease that requires major lifestyle changes, Pharmaceutical research, 25, 2097, 10.1007/s11095-008-9661-9 · DOI · Paper page
  4. P Sharma, 2015, Immune checkpoint targeting in cancer therapy: toward combination strategies with curative potential, Cell, 161, 205, 10.1016/j.cell.2015.03.030 · DOI · Paper page
  5. J Nam, 2019, Cancer nanomedicine for combination cancer immunotherapy, Nature Reviews Materials, 4, 398, 10.1038/s41578-019-0108-1 · DOI
  6. CL Ventola, 2017, Cancer immunotherapy, part 3: challenges and future trends, Pharmacy and Therapeutics, 42, 514
  7. T Jiang, 2019, Tumor neoantigens: from basic research to clinical applications, Journal of hematology & oncology, 12, 1, 10.1186/s13045-019-0787-5 · DOI
  8. M Yi, 2018, The role of neoantigen in immune checkpoint blockade therapy, Experimental Hematology & Oncology, 7, 1
  9. A Sette, 1994, Peptide binding to the most frequent HLA-A class I alleles measured by quantitative molecular binding assays, Molecular immunology, 31, 813, 10.1016/0161-5890(94)90019-1 · DOI
  10. R Vita, 2015, The immune epitope database (IEDB) 3.0, Nucleic acids research, 43, D405, 10.1093/nar/gku938 · DOI
  11. V Jurtz, 2017, NetMHCpan-4.0: improved peptide–MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data, The Journal of Immunology, 199, 3360, 10.4049/jimmunol.1700893 · DOI
  12. B Reynisson, 2020, NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data, Nucleic acids research, 48, W449, 10.1093/nar/gkaa379 · DOI · Paper page
  13. M Nielsen, 2007, NetMHCpan, a method for quantitative predictions of peptide binding to any HLA-A and-B locus protein of known sequence, PloS one, 2, e796, 10.1371/journal.pone.0000796 · DOI
  14. G Venkatesh, 2020, MHCAttnNet: predicting MHC-peptide bindings for MHC alleles classes I and II using an attention-based deep neural model, Bioinformatics, 36, i399, 10.1093/bioinformatics/btaa479 · DOI
  15. K Kim, 2020, Predicting clinical benefit of immunotherapy by antigenic or functional mutations affecting tumour immunogenicity, Nature communications, 11, 1
  16. G Li, 2021, DeepImmuno: deep learning-empowered prediction and generation of immunogenic peptides for T-cell immunity, Briefings in bioinformatics, 22, bbab160, 10.1093/bib/bbab160 · DOI · Paper page
  17. F Scarselli, 2008, The graph neural network model, IEEE transactions on neural networks, 20, 61, 10.1109/TNN.2008.2005605 · DOI · Paper page
  18. Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:160902907. 2016;.
  19. P Velickovic, 2017, Graph attention networks, stat, 1050, 20
  20. HC Yi, 2022, Graph representation learning in bioinformatics: trends, methods and applications, Briefings in Bioinformatics, 23, bbab340, 10.1093/bib/bbab340 · DOI
  21. W Ju, 2023, Few-shot molecular property prediction via Hierarchically Structured Learning on Relation Graphs, Neural Networks, 163, 122, 10.1016/j.neunet.2023.03.034 · DOI
  22. D Weininger, 1988, SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules, Journal of chemical information and computer sciences, 28, 31, 10.1021/ci00057a005 · DOI · Paper page
  23. Lin X. Deepgs: Deep representation learning of graphs and sequences for drug-target binding affinity prediction. arXiv preprint arXiv:200313902. 2020;.
  24. Z Yang, 2022, MGraphDTA: deep multiscale graph neural network for explainable drug–target binding affinity prediction, Chemical science, 13, 816, 10.1039/D1SC05180F · DOI
  25. T Nguyen, 2021, GraphDTA: Predicting drug–target binding affinity with graph neural networks, Bioinformatics, 37, 1140, 10.1093/bioinformatics/btaa921 · DOI
  26. H Öztürk, 2018, DeepDTA: deep drug–target binding affinity prediction, Bioinformatics, 34, i821, 10.1093/bioinformatics/bty593 · DOI
  27. T Nikolaienko, 2022, Complex machine learning model needs complex testing: Examining predictability of molecular binding affinity by a graph neural network, Journal of Computational Chemistry
  28. JF Joung, 2021, Deep Learning Optical Spectroscopy Based on Experimental Database: Potential Applications to Molecular Design, JACS Au, 1, 427, 10.1021/jacsau.1c00035 · DOI
  29. AK Nyamabo, 2021, SSI–DDI: substructure–substructure interactions for drug–drug interaction prediction, Briefings in Bioinformatics, 22, bbab133, 10.1093/bib/bbab133 · DOI
  30. Deac A, Huang YH, Veličković P, Liò P, Tang J. Drug-drug adverse effect prediction with graph co-attention. arXiv preprint arXiv:190500534. 2019;.
  31. M Łuksza, 2017, A neoantigen fitness model predicts tumour response to checkpoint blockade immunotherapy, Nature, 551, 517, 10.1038/nature24473 · DOI
  32. A Vitiello, 2017, Neoantigen prediction and the need for validation, Nature biotechnology, 35, 815, 10.1038/nbt.3932 · DOI
  33. LP Richman, 2019, Neoantigen dissimilarity to the self-proteome predicts immunogenicity and response to immune checkpoint blockade, Cell systems, 9, 375, 10.1016/j.cels.2019.08.009 · DOI
  34. T Kamada, 1989, An algorithm for drawing general undirected graphs, Information processing letters, 31, 7, 10.1016/0020-0190(89)90102-6 · DOI
  35. Fey M, Lenssen JE. Fast Graph Representation Learning with PyTorch Geometric. In: ICLR Workshop on Representation Learning on Graphs and Manifolds; 2019.
  36. Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:14090473. 2014;.
  37. Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y. Graph attention networks. arXiv preprint arXiv:171010903. 2017;.
  38. A Paszke, 2019, Pytorch: An imperative style, high-performance deep learning library, Advances in neural information processing systems, 32
  39. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014;.
  40. F Pedregosa, 2011, Scikit-learn: Machine learning in Python, the Journal of machine Learning research, 12, 2825
  41. ER DeLong, 1988, Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach, Biometrics, 837, 10.2307/2531595 · DOI · Paper page
  42. F Schoonjans, 1995, MedCalc: a new computer program for medical statistics, Computer methods and programs in biomedicine, 48, 257, 10.1016/0169-2607(95)01703-8 · DOI
  43. JN Weinstein, 2013, The cancer genome atlas pan-cancer analysis project, Nature genetics, 45, 1113, 10.1038/ng.2764 · DOI · Paper page
  44. AM Eggermont, 2014, Cutaneous melanoma, The Lancet, 383, 816, 10.1016/S0140-6736(13)60802-8 · DOI
  45. ACM Coelho, 2020, neoANT-HILL: an integrated tool for identification of potential neoantigens, BMC Medical Genomics, 13, 1
  46. A Szolek, 2014, OptiType: precision HLA typing from next-generation sequencing data, Bioinformatics, 30, 3310, 10.1093/bioinformatics/btu548 · DOI
  47. Park S, Won D, Kim DJ, Park SY, Lee ST. Genetic Alterations of Esophageal Squamous Cell Carcinoma in Korean Patients. 2021;. · DOI
  48. W McLaren, 2016, The ensembl variant effect predictor, Genome biology, 17, 1, 10.1186/s13059-016-0974-4 · DOI · Paper page
  49. X Wang, 2013, customProDB: an R package to generate customized protein databases from RNA-Seq data for proteomics search, Bioinformatics, 29, 3235, 10.1093/bioinformatics/btt543 · DOI · Paper page
  50. JH Kim, 2020, Genome data analysis 2: NGS edition, cancer and disease genome. V. 2
  51. K Yoshihara, 2013, Inferring tumour purity and stromal and immune cell admixture from expression data, Nature communications, 4, 1, 10.1038/ncomms3612 · DOI · Paper page
  52. D Hanahan, 2011, Hallmarks of cancer: the next generation, cell, 144, 646, 10.1016/j.cell.2011.02.013 · DOI · Paper page
  53. R Kalluri, 2006, Fibroblasts in cancer, Nature reviews cancer, 6, 392, 10.1038/nrc1877 · DOI · Paper page
  54. Galon J, Marincola FM, Thurin M, Trinchieri G, Fox BA, Gajewski TF, et al.. The immune score as a new possible approach for the classification of cancer; 2012. · DOI
  55. RM Pyke, 2018, Evolutionary pressure against MHC class II binding cancer mutations, Cell, 175, 416, 10.1016/j.cell.2018.08.048 · DOI
  56. Z Sun, 2017, MHC class II restricted neoantigen: a promising target in tumor immunotherapy, Cancer letters, 392, 17, 10.1016/j.canlet.2016.12.039 · DOI
  57. XM Shao, 2020, High-Throughput Prediction of MHC Class I and II Neoantigens with MHCnuggetsHigh-Throughput Prediction of Neoantigens with MHCnuggets, Cancer immunology research, 8, 396, 10.1158/2326-6066.CIR-19-0464 · DOI
  58. H Zhang, 2009, The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding, Bioinformatics, 25, 1293, 10.1093/bioinformatics/btp137 · DOI
  59. M Andreatta, 2016, Gapped sequence alignment using artificial neural networks: application to the MHC class I system, Bioinformatics, 32, 511, 10.1093/bioinformatics/btv639 · DOI
  60. N McGranahan, 2016, Clonal neoantigens elicit T cell immunoreactivity and sensitivity to immune checkpoint blockade, Science, 351, 1463, 10.1126/science.aaf1490 · DOI · Paper page
  61. S Kim, 2018, Neopepsee: accurate genome-level prediction of neoantigens by harnessing sequence and amino acid immunogenicity information, Annals of Oncology, 29, 1030, 10.1093/annonc/mdy022 · DOI
  62. E Ghorani, 2018, Differential binding affinity of mutated peptides for MHC class I is a predictor of survival in advanced lung cancer and melanoma, Annals of oncology, 29, 271, 10.1093/annonc/mdx687 · DOI
  63. AP Delaunay, 2022, Peptide-MHC Structure Prediction With Mixed Residue and Atom Graph Neural Network, bioRxiv
  64. A Khan, 2022, Characterization of HLA-A* 33: 03 epitopes via immunoprecipitation and LC-MS/MS, Proteomics, 22, 2100171, 10.1002/pmic.202100171 · DOI
  65. A Duarte, 2015, Prediction of CD8+ epitopes in Leishmania braziliensis proteins using EPIBOT: in silico search and in vivo validation, PLoS One, 10, e0124786, 10.1371/journal.pone.0124786 · DOI
  66. CW Abbott, 2021, Prediction of immunotherapy response in melanoma through combined modeling of neoantigen burden and immune-related resistance mechanisms, Clinical Cancer Research, 27, 4265, 10.1158/1078-0432.CCR-20-4314 · DOI
  67. U Sahin, 2017, Personalized RNA mutanome vaccines mobilize poly-specific therapeutic immunity against cancer, Nature, 547, 222, 10.1038/nature23003 · DOI · Paper page
  68. PA Ott, 2017, An immunogenic personal neoantigen vaccine for patients with melanoma, Nature, 547, 217, 10.1038/nature22991 · DOI · Paper page
  69. CD Zahm, 2017, Vaccination with high-affinity epitopes impairs antitumor efficacy by increasing PD-1 expression on CD8+ T cells, Cancer immunology research, 5, 630, 10.1158/2326-6066.CIR-16-0374 · DOI
  70. M Prachar, 2020, Identification and validation of 174 COVID-19 vaccine candidate epitopes reveals low performance of common epitope prediction tools, Scientific reports, 10, 1, 10.1038/s41598-020-77466-4 · DOI
  71. EF Fritsch, 2014, HLA-Binding Properties of Tumor Neoepitopes in HumansTumor Neoepitopes in Humans, Cancer immunology research, 2, 522, 10.1158/2326-6066.CIR-13-0227 · DOI
  72. CW Tung, 2007, POPI: predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties, Bioinformatics, 23, 942, 10.1093/bioinformatics/btm061 · DOI
  73. CW Tung, 2011, POPISK: T-cell reactivity prediction using support vector machines and string kernels, BMC bioinformatics, 12, 1
  74. T Lu, 2021, Deep learning-based prediction of the T cell receptor–antigen binding specificity, Nature Machine Intelligence, 3, 864, 10.1038/s42256-021-00383-2 · DOI · Paper page
  75. T Saethang, 2013, PAAQD: Predicting immunogenicity of MHC class I binding peptides using amino acid pairwise contact potentials and quantum topological molecular similarity descriptors, Journal of Immunological Methods, 387, 293, 10.1016/j.jim.2012.09.016 · DOI
  76. TJ O’Donnell, 2020, MHCflurry 2.0: improved pan-allele prediction of MHC class I-presented peptides by incorporating antigen processing, Cell systems, 11, 42, 10.1016/j.cels.2020.06.010 · DOI · Paper page
  77. J Wu, 2019, DeepHLApan: a deep learning approach for neoantigen prediction considering both HLA-peptide binding and immunogenicity, Frontiers in Immunology, 2559, 10.3389/fimmu.2019.02559 · DOI
  78. D Hanahan, 2000, The hallmarks of cancer, cell, 100, 57, 10.1016/S0092-8674(00)81683-9 · DOI · Paper page
  79. P Sonveaux, 2008, Targeting lactate-fueled respiration selectively kills hypoxic tumor cells in mice, The Journal of clinical investigation, 118, 3930
  80. N Alghamdi, 2021, A graph neural network model to estimate cell-wise metabolic flux using single-cell RNA-seq data, Genome research, 31, 1867, 10.1101/gr.271205.120 · DOI
  81. K Takahashi, 2006, Induction of pluripotent stem cells from mouse embryonic and adult fibroblast cultures by defined factors, cell, 126, 663, 10.1016/j.cell.2006.07.024 · DOI · Paper page
  82. K Takahashi, 2007, Induction of pluripotent stem cells from adult human fibroblasts by defined factors, cell, 131, 861, 10.1016/j.cell.2007.11.019 · DOI · Paper page
  83. J Wang, 2020, Inductive inference of gene regulatory network using supervised and semi-supervised graph neural networks, Computational and Structural Biotechnology Journal, 18, 3335, 10.1016/j.csbj.2020.10.022 · DOI
  84. Sattar NS, Arifuzzaman S. Community detection using semi-supervised learning with graph convolutional network on GPUs. In: 2020 IEEE International Conference on Big Data (Big Data). IEEE; 2020. p. 5237–5246. · DOI

Metadata

Authors
Jeong, H., Cho, Y.-R., Gim, J., Cha, S.-K., Kim, M., & Kang, D. R.
Affiliations
  • Yonsei University (KR)
  • Yonsei University Mirae Campus (KR)
  • Chosun University (KR)
Corresponding author
Kang, Dae Ryong
ORCID
Venue
PLOS ONE
Publisher
Public Library of Science (PLoS)
Published
2024-03-27
Volume
19
Issue
3
Pages
e0291223
ISSN
1932-6203 (ISSN-L)
DOI
10.1371/journal.pone.0291223
PMC
PMC10971776
OpenAlex
W4393235019
Cited by
14
References
7
Citations by year
2026: 7 · 2025: 6 · 2024: 1
FWCI
1.91
Type
journal article
Language
en
Open access
Licence
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
  • Health Sciences › Medicine › Oncology › Cancer Immunotherapy and Biomarkers
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
Keywords
neoantigen prediction, peptide-MHC binding, graph neural networks, graph attention networks, molecular representation, immune checkpoint inhibitors, melanoma, overall survival, tumor immune microenvironment, IEDB
MeSH terms
Antigens, Neoplasm, Humans, Melanoma, Peptides, Molecular Structure, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review