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

The DOI matches its Crossref record; 1 of the 1 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·2023·PLoS ONE
DOI 10.1101/2023.08.25.554848PMC PMC10971776

Preprint — published as 10.1371/journal.pone.0291223 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Neoantigens are biomarkers that can predict the prognosis associated with immune checkpoint inhibition by estimating the binding potential of candidate peptides to somatic mutation and major histocompatibility complex (MHC) proteins. Although deep neural networks have been primarily used for these prediction models, it is difficult to consider 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 through 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. Bindings are classified by feeding them into the GraphMHC network, comprising stacked graph attention and convolution layers. 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 the baseline model. Moreover, by applying the GraphMHC model to melanoma patient data from the Cancer Genome Atlas project, we found a borderline difference 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. The model can provide highly accurate suitability information for cancer patients who want to apply immune checkpoint inhibitors. Author summary:

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 · 10.1101/2023.08.25.554848

Cites

1 of 1 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: 70

  1. 10.1158/1078-0432.CCR-20-4314 · DOI
  2. 10.1007/s11095-008-9661-9 · DOI · Paper page
  3. 10.1093/bioinformatics/btv639 · DOI
  4. Bahdanau et al., 2014. Bahdanau, D. , Cho, K. , and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473. · arXiv
  5. 10.1126/science.aaf2834 · DOI · Paper page
  6. Coelho et al., 2020, 2020, neoant-hill: an integrated tool for identification of potential neoantigens, BMC Medical Genomics, 13, 1
  7. Deac et al., 2019. Deac, A. , Huang, Y.-H. , Veličković, P. , Lio, P. , and Tang, J. (2019). Drug-drug adverse effect prediction with graph co-attention. arXiv preprint arXiv:1905.00534. · arXiv
  8. Delaunay et al., 2022. Delaunay, A. P. , Fu, Y. , Begue, A. , McHardy, R. , Djermani, B. A. , Rooney, M. , Tovchigrechko, A. , Copoiu, L. , Skwark, M. J. , Carranza, N. L. , et al. (2022). Peptide-mhc structure prediction with mixed residue and atom graph neural network. bioRxiv. · DOI
  9. DeLong et al., 1988. DeLong, E. R. , DeLong, D. M. , and Clarke-Pearson, D. L. (1988). Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics, pages 837–845. · DOI · Paper page
  10. 10.1371/journal.pone.0124786 · DOI
  11. Fey and Lenssen, 2019. Fey, M. and Lenssen, J. E. (2019). Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds.
  12. 10.1158/2326-6066.CIR-13-0227 · DOI
  13. Galon et al., 2012. Galon, J. , Marincola, F. M. , Thurin, M. , Trinchieri, G. , Fox, B. A. , Gajewski, T. F. , Ascierto, P. A. , et al. (2012). The immune score as a new possible approach for the classification of cancer. · DOI
  14. 10.1093/annonc/mdx687 · DOI
  15. 10.1016/j.cell.2011.02.013 · DOI · Paper page
  16. He et al., 2016. He, K. , Zhang, X. , Ren, S. , and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778. · DOI · Paper page
  17. Jiang et al., 2019, 2019, Tumor neoantigens: from basic research to clinical applications, Journal of hematology & oncology, 12, 1
  18. Jung et al., 2020, 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
  19. Jurtz et al., 2017, 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
  20. 10.1038/nrc1877 · DOI · Paper page
  21. 10.1016/0020-0190(89)90102-6 · DOI
  22. Khan et al., 2022, 2022, Characterization of hla-a* 33: 03 epitopes via immunoprecipitation and lc-ms/ms, Proteomics, 22, 2100171, 10.1002/pmic.202100171 · DOI
  23. Kim, 2020. Kim, J. H. (2020). Genome data analysis 2: NGS edition, cancer and disease genome. Number V. 2. Panmun Education, Seoul, Republic of Korea.
  24. Kim et al., 2020, 2020, Predicting clinical benefit of immunotherapy by antigenic or functional mutations affecting tumour immunogenicity, Nature communications, 11, 1
  25. Kingma and Ba, 2014. Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. · arXiv
  26. Kipf and Welling, 2016. Kipf, T. N. and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. · arXiv
  27. 10.1093/bib/bbab160 · DOI · Paper page
  28. Lu et al., 2021, 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
  29. 10.1038/nature24473 · DOI
  30. 10.1126/science.aaf1490 · DOI · Paper page
  31. 10.1186/s13059-015-0866-z · DOI · Paper page
  32. Nam et al., 2019, 2019, Cancer nanomedicine for combination cancer immunotherapy, Nature Reviews Materials, 4, 398, 10.1038/s41578-019-0108-1 · DOI
  33. Nguyen et al., 2021, 2021, Graphdta: Predicting drug–target binding affinity with graph neural networks, Bioinformatics, 37, 1140, 10.1093/bioinformatics/btaa921 · DOI
  34. Nyamabo et al., 2021, 2021, Ssi–ddi: substructure–substructure interactions for drug–drug interaction prediction, Briefings in Bioinformatics, 22, bbab133, 10.1093/bib/bbab133 · DOI
  35. 10.1038/nature22991 · DOI · Paper page
  36. 10.1093/bioinformatics/bty593 · DOI
  37. O’Donnell et al., 2020, 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
  38. Park et al., 2021. Park, S. , Won, D. , Kim, D. J. , Park, S. Y. , and Lee, S.-T. (2021). Genetic alterations of esophageal squamous cell carcinoma in korean patients. · DOI
  39. Paszke et al., 2019. Paszke, A. , Gross, S. , Massa, F. , Lerer, A. , Bradbury, J. , Chanan, G. , Killeen, T. , Lin, Z. , Gimelshein, N. , Antiga, L. , et al. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  40. Pedregosa et al., 2011, 2011, Scikit-learn: Machine learning in python, the Journal of machine Learning research, 12, 2825
  41. 10.1038/nbt.4235 · DOI · Paper page
  42. 10.1038/s41598-020-62658-9 · DOI
  43. Pyke et al., 2018, 2018, Evolutionary pressure against mhc class ii binding cancer mutations, Cell, 175, 416, 10.1016/j.cell.2018.08.048 · DOI
  44. Reynisson et al., 2020, 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
  45. Richman et al., 2019, 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
  46. 10.1016/j.jim.2012.09.016 · DOI
  47. 10.1038/nature23003 · DOI · Paper page
  48. 10.1016/0169-2607(95)01703-8 · DOI
  49. 10.1016/0161-5890(94)90019-1 · DOI
  50. 10.1158/2326-6066.CIR-19-0464 · DOI
  51. 10.1016/j.cell.2015.03.030 · DOI · Paper page
  52. 10.1016/J.CANLET.2016.12.039 · DOI
  53. 10.3322/caac.21660 · DOI · Paper page
  54. 10.1093/bioinformatics/btu548 · DOI
  55. 10.1093/bioinformatics/btm061 · DOI
  56. 10.1186/1471-2105-12-1 · DOI
  57. Veličković et al., 2017. Veličković, P. , Cucurull, G. , Casanova, A. , Romero, A. , Lio, P. , and Bengio, Y. (2017). Graph attention networks. arXiv preprint arXiv:1710.10903. · arXiv
  58. Venkatesh et al., 2020, 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
  59. Ventola, 2017, 2017, Cancer immunotherapy, part 3: challenges and future trends, Pharmacy and Therapeutics, 42, 514
  60. 10.1093/nar/gku938 · DOI
  61. 10.1038/nbt.3932 · DOI
  62. 10.1093/bioinformatics/btt543 · DOI · Paper page
  63. 10.1021/ci00057a005 · DOI · Paper page
  64. 10.1038/ng.2764 · DOI · Paper page
  65. Wu et al., 2019. Wu, J. , Wang, W. , Zhang, J. , Zhou, B. , Zhao, W. , Su, Z. , Gu, X. , Wu, J. , Zhou, Z. , and Chen, S. (2019). Deephlapan: a deep learning approach for neoantigen prediction considering both hla-peptide binding and immunogenicity. Frontiers in Immunology, page 2559. · DOI
  66. Yang et al., 2022, 2022, Mgraphdta: deep multiscale graph neural network for explainable drug–target binding affinity prediction, Chemical science, 13, 816, 10.1039/D1SC05180F · DOI
  67. Yi et al., 2018, 2018, The role of neoantigen in immune checkpoint blockade therapy, Experimental Hematology & Oncology, 7, 1
  68. Yoshihara et al., 2013, 2013, Inferring tumour purity and stromal and immune cell admixture from expression data, Nature communications, 4, 1
  69. 10.1158/2326-6066.CIR-16-0374 · DOI
  70. 10.1093/bioinformatics/btp137 · 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
openRxiv
Published
2023-08-27
Volume
19
Issue
3
Pages
e0291223-e0291223
ISSN
1932-6203 (ISSN-L)
DOI
10.1101/2023.08.25.554848
PMC
PMC10971776
OpenAlex
W4393235019
Cited by
14
References
1
Citations by year
2026: 7 · 2025: 6 · 2024: 1
FWCI
1.90
Type
journal article
Language
en
Open access
Licence
cc-by
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