CoChat
Sign Up
PreprintCited by 25vaccines and immunoinformatics approachesMachine Learning in BioinformaticsChemical Synthesis and Analysis

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Improved Predictions of MHC-Peptide Binding using Protein Language Models

Open access
Hashemi, Nasser, Hao, Boran, Ignatov, Mikhail, Paschalidis, Ioannis, Vakili, Pirooz, Vajda, Sandor, Kozakov, Dima·2022·Frontiers in Bioinformatics
DOI 10.1101/2022.02.11.479844PMC PMC10469926

Preprint — published as 10.3389/fbinf.2023.1207380 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

A bstract: Major histocompatibility complex (MHC) molecules bind to peptides from exogenous antigens, and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipulation of the cellular immune system [1]. Predicting whether a given peptide will bind to the MHC is an important step in the above process, motivating the introduction of many computational approaches. NetMHCPan [2], a pan-specific model predicting binding of peptides to any MHC molecule, is one of the most widely used methods which focuses on solving this binary classification problem using a shallow neural network. The successful results of AI methods, especially Natural Language Processing (NLP-based) pretrained models in various applications including protein structure determination, motivated us to explore their use in this problem as well. Specifically, we considered fine-tuning these large deep learning models using as dataset the peptide-MHC sequences. Using standard metrics in this area, and the same training and test sets, we show that our model outperforms NetMHCpan4.1 which has been shown to outperform all other earlier methods [2].

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 · 10.1101/2022.02.11.479844

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: 49

  1. 10.1021/ACS.JPROTEOME.9B00874 · DOI
  2. 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
  3. Charles A Janeway , Paul Travers , Mark Walport , and Donald J Capra . Immunobiology. Taylor & Francis Group UK: Garland Science, 2001.
  4. 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
  5. 10.1016/0092-8674(90)90366-M · DOI
  6. 2015, Analysis of major histocompatibility complex (mhc) immunopeptidomes using mass spectrometry, Molecular & Cellular Proteomics, 14, 3105, 10.1074/mcp.O115.052431 · DOI
  7. 2019, Nnalign_ma; mhc peptidome deconvolution for accurate mhc binding motif characterization and improved t-cell epitope predictions, Molecular & Cellular Proteomics, 18, 2459, 10.1074/mcp.TIR119.001658 · DOI
  8. 10.1186/s12859-019-2669-9 · DOI
  9. 10.1007/s00251-005-0798-y · DOI
  10. 10.1110/ps.0239403 · DOI
  11. 10.1142/S0219720006002314 · DOI
  12. 10.1021/jm010021j · DOI
  13. 1994, Scheme for ranking potential hla-a2 binding peptides based on independent binding of individual peptide side-chains, The Journal of Immunology, 152, 163, 10.4049/jimmunol.152.1.163 · DOI
  14. 10.1093/nar/gky1006 · DOI
  15. 2018, The systemhc atlas project, Nucleic acids research, 46, D1237, 10.1093/nar/gkx664 · DOI
  16. 10.1093/bioinformatics/btz330 · DOI
  17. JC Tong . Blocks substitution matrix (blosum). Encyclopedia of Systems Biology.—NY: Springer, 2013. · DOI
  18. 10.1038/nature14539 · DOI · Paper page
  19. 2018, A review on the application of deep learning in system health management, Mechanical Systems and Signal Processing, 107, 241, 10.1016/j.ymssp.2017.11.024 · DOI · Paper page
  20. Saeed Mohammadzadeh and Emma Lejeune . Predicting mechanically driven full-field quantities of interest with deep learning-based metamodels. Extreme Mechanics Letters, page 101566, 2021. · DOI
  21. Athanasios Voulodimos , Nikolaos Doulamis , Anastasios Doulamis , and Eftychios Protopapadakis . Deep learning for computer vision: A brief review. Computational intelligence and neuroscience, 2018, 2018. · DOI · Paper page
  22. Li Deng , Jinyu Li , Jui-Ting Huang , Kaisheng Yao , Dong Yu , Frank Seide , Michael Seltzer , Geoff Zweig , Xiaodong He , Jason Williams , et al. Recent advances in deep learning for speech research at microsoft. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 8604–8608. IEEE, 2013. · DOI · Paper page
  23. Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , Lukasz Kaiser , and Illia Polosukhin . Attention is all you need. arXiv preprint arXiv:1706.03762, 2017. · arXiv
  24. Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. · arXiv
  25. 2019, Evaluating protein transfer learning with tape, Advances in Neural Information Processing Systems, 32, 9689
  26. Alexander Rives , Siddharth Goyal , Joshua Meier , Demi Guo , Myle Ott , C Lawrence Zitnick , Jerry Ma , and Rob Fergus . Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. bioRxiv, page 622803, 2019. · DOI · Paper page
  27. 2020, High accuracy protein structure prediction using deep learning, Fourteenth Critical Assessment of Techniques for Protein Structure Prediction (Abstract Book), 22, 24
  28. 2021, Prediction of protein assemblies, the next frontier: The casp14-capri experiment, Proteins: Structure, Function, and Bioinformatics, 89, 1800, 10.1002/prot.26222 · DOI
  29. Megan Egbert , Usman Ghani , Ryota Ashizawa , Sergei Kotelnikov , Thu Nguyen , Israel Desta , Nasser Hashemi , Dzmitry Padhorny , Dima Kozakov , and Sandor Vajda . Assessing the binding properties of casp14 targets and models. Proteins: Structure, Function, and Bioinformatics, 2021. · DOI
  30. Usman Ghani , Israel Desta , Akhil Jindal , Omeir Khan , George Jones , Sergey Kotelnikov , Dzmitry Padhorny , Sandor Vajda , and Dima Kozakov . Improved docking of protein models by a combination of alphafold2 and cluspro. bioRxiv, 2021. · DOI · Paper page
  31. Ahmed Elnaggar , Michael Heinzinger , Christian Dallago , Ghalia Rihawi , Yu Wang , Llion Jones , Tom Gibbs , Tamas Feher , Christoph Angerer , Debsindhu Bhowmik , et al. Prottrans: Towards cracking the language of life’s code through self-supervised deep learning and high performance computing. arXiv preprint arXiv:2007.06225, 2020. · DOI
  32. Roshan Rao , Jason Liu , Robert Verkuil , Joshua Meier , John F Canny , Pieter Abbeel , Tom Sercu , and Alexander Rives . Msa transformer. bioRxiv, 2021.
  33. Roshan M Rao , Joshua Meier , Tom Sercu , Sergey Ovchinnikov , and Alexander Rives . Transformer protein language models are unsupervised structure learners. bioRxiv, 2020.
  34. Jun Cheng , Kaïdre Bendjama , Karola Rittner , and Brandon Malone . Bertmhc: Improves mhc-peptide class ii interaction prediction with transformer and multiple instance learning. bioRxiv, 2020. · DOI
  35. Hans-Christof Gasser , Georges Bedran , Bo Ren , David Goodlett , Javier Alfaro , and Ajitha Rajan . Interpreting bert architecture predictions for peptide presentation by mhc class i proteins. arXiv preprint arXiv:2111.07137, 2021. · arXiv
  36. Yinhan Liu , Myle Ott , Naman Goyal , Jingfei Du , Mandar Joshi , Danqi Chen , Omer Levy , Mike Lewis , Luke Zettlemoyer , and Veselin Stoyanov . Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019. · arXiv
  37. Victor Sanh , Lysandre Debut , Julien Chaumond , and Thomas Wolf . Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108, 2019. · arXiv
  38. Zhilin Yang , Zihang Dai , Yiming Yang , Jaime Carbonell , Russ R Salakhutdinov , and Quoc V Le . Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems, 32, 2019.
  39. Samuel R Bowman , Gabor Angeli , Christopher Potts , and Christopher D Manning . A large annotated corpus for learning natural language inference. arXiv preprint arXiv:1508.05326, 2015. · DOI · Paper page
  40. Xiao-Meng Zhang , Li Liang , Lin Liu , and Ming-Jing Tang . Graph neural networks and their current applications in bioinformatics. Frontiers in Genetics, 12, 2021. · DOI
  41. Petar Veličković , Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Lio , and Yoshua Bengio . Graph attention networks. arXiv preprint arXiv:1710.10903, 2017. · arXiv
  42. 2016, Unsupervised hla peptidome deconvolution improves ligand prediction accuracy and predicts cooperative effects in peptide–hla interactions, The Journal of Immunology, 197, 2492, 10.4049/jimmunol.1600808 · DOI
  43. 2017, Deciphering hla-i motifs across hla peptidomes improves neo-antigen predictions and identifies allostery regulating hla specificity, PLoS computational biology, 13, e1005725, 10.1371/journal.pcbi.1005725 · DOI
  44. Oded Maron and Tomás Lozano-Pérez . A framework for multiple-instance learning. Advances in neural information processing systems, pages 570–576, 1998.
  45. 10.1016/j.immuni.2017.02.007 · DOI
  46. 2018, Mhcflurry: open-source class i mhc binding affinity prediction, Cell systems, 7, 129, 10.1016/j.cels.2018.05.014 · DOI
  47. 2017, The cluspro web server for protein–protein docking, Nature protocols, 12, 255, 10.1038/nprot.2016.169 · DOI
  48. Shahabeddin Sotudian , Ruidi Chen , and Ioannis Paschalidis . Distributionally robust multi-output regression ranking. arXiv preprint arXiv:2109.12803, 2021. · arXiv
  49. 2017, New additions to the c lus p ro server motivated by capri, Proteins: Structure, Function, and Bioinformatics, 85, 435, 10.1002/prot.25219 · DOI

Metadata

Authors
Hashemi, N., Hao, B., Ignatov, M., Paschalidis, I., Vakili, P., Vajda, S., & Kozakov, D.
Affiliations
  • Boston University (US)
  • Stony Brook University (US)
Corresponding author
  • Hashemi, Nasser
  • Kozakov, Dima
ORCID
Venue
Frontiers in Bioinformatics
Publisher
openRxiv
Published
2022-02-12
Volume
3
Pages
1207380-1207380
ISSN
2673-7647 (ISSN-L)
DOI
10.1101/2022.02.11.479844
PMC
PMC10469926
OpenAlex
W4385982832
Cited by
25
References
1
Citations by year
2026: 10 · 2025: 3 · 2024: 8 · 2023: 3 · 2022: 1
FWCI
2.14
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Frontiers in Bioinformatics (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • OpenBU (Boston University) (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Science Foundation (1645681, 2054251, 1664644, RM1135136, 1914792)
  • Georgia Clinical and Translational Science Alliance (UL54 TR004130)
  • National Institutes of Health (UL54 TR004130, RM1135136)
  • Office of Naval Research (N00014-19-1-2571, N00014-19, N00014)
  • National Institute of General Medical Sciences (R01GM135930, R01GM140098, R35GM118078)
  • National Center for Advancing Translational Sciences (UL54 TR004130)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Physical Sciences › Chemistry › Organic Chemistry › Chemical Synthesis and Analysis
Keywords
MHC-peptide binding prediction, MHC class I, protein language models, NetMHCpan, antigen presentation, T cell recognition, binary classification, deep learning

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