CoChat
Sign Up
PreprintCited by 9vaccines and immunoinformatics approachesMachine Learning in BioinformaticsImmunotherapy and Immune Responses

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

TransHLA: A Hybrid Transformer Model for HLA-Presented Epitope Detection

Open access
Lu, Tianchi, Wang, Xueying, Nie, Wan, Huo, Miaozhe, Li, Shuaicheng·2025·GigaScience
DOI 10.1101/2025.01.20.634002PMC PMC11878767

Preprint — published as 10.1093/gigascience/giaf008 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Background: Precise prediction of epitope presentation on human leukocyte antigen (HLA) molecules is crucial for advancing vaccine development and immunotherapy. Conventional HLA-peptide binding affinity prediction tools often focus on specific alleles and lack a universal approach for comprehensive HLA site analysis. This limitation hinders efficient filtering of invalid peptide segments. Results: We introduce TransHLA, a pioneering tool designed for epitope prediction across all HLA alleles, integrating Transformer and Residue CNN architectures. TransHLA utilizes the ESM2 large language model for sequence and structure embeddings, achieving high predictive accuracy. For HLA class I, it reaches an accuracy of 84.72% and an AUC of 91.95% on IEDB test data. For HLA class II, it achieves 79.94% accuracy and an AUC of 88.14%. Our case studies using datasets like CEDAR and VDJdb demonstrate that TransHLA surpasses existing models in specificity and sensitivity for identifying immunogenic epitopes and neoepitopes. Conclusions: TransHLA significantly enhances vaccine design and immunotherapy by efficiently identifying broadly reactive peptides. Our resources, including data and code, are publicly accessible at https://github.com/SkywalkerLuke/TransHLA Key Points: We developed TransHLA, a deep learning tool for predicting epitopes across all HLA alleles using Transformer and Residue CNN architectures. The model uses ESM2 embeddings to improve predictive accuracy and efficiency. TransHLA shows superior specificity and sensitivity in identifying immunogenic epitopes and neoepitopes compared to existing models. Our approach offers potential advancements in vaccine design and immunotherapy through enhanced peptide analysis.

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 · 10.1101/2025.01.20.634002

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1: Overview of data acquisition and predictive modeling using TransHLA. (A) Data acquisition: The dataset, derived from the IEDB, features a variety of peptide sequences that bind to HLA class I or II molecules. For negative sample generation, nonoverlapping random peptide fragments were sourced by matching positive peptides to their originating proteins through sequence alignment. Then, the nonoverlapping random peptide fragments were processed with CD-HIT to achieve a reduced redundancy, resulting in the final set of negative samples. (B) With ESM2’s advanced modeling capabilities, we generated high-dimensional sequence embeddings for the peptides associated with both HLA classes. Concurrently, structural insights were obtained through ESM2’s contact map predictions, yielding structure embeddings. These 2 distinct yet complementary sets of embeddings were crafted to capture the intricate nature of peptide–HLA interaction, describes the process from data input to epitope presentation prediction. (C) The architecture of the different modules, including the CNN Module 1, CNN Module 2, and the Transformer module.
Figure 1: Overview of data acquisition and predictive modeling using TransHLA. (A) Data acquisition: The dataset, derived from the IEDB, features a variety of peptide sequences that bind to HLA class I or II molecules. For negative sample generation, nonoverlapping random peptide fragments were sourced by matching positive peptides to their originating proteins through sequence alignment. Then, the nonoverlapping random peptide fragments were processed with CD-HIT to achieve a reduced redundancy, resulting in the final set of negative samples. (B) With ESM2’s advanced modeling capabilities, we generated high-dimensional sequence embeddings for the peptides associated with both HLA classes. Concurrently, structural insights were obtained through ESM2’s contact map predictions, yielding structure embeddings. These 2 distinct yet complementary sets of embeddings were crafted to capture the intricate nature of peptide–HLA interaction, describes the process from data input to epitope presentation prediction. (C) The architecture of the different modules, including the CNN Module 1, CNN Module 2, and the Transformer module.CC BY · PubMed Central
Figure 2: This figure illustrates the experimental distribution of major HLA-I alleles in the IEDB. We plotted the alleles by type, where panel A shows the distribution for all data, B for the training dataset, C for the test dataset, and D for the validation dataset. Left represents HLA-A alleles, middle represents HLA-B alleles, and right represents HLA-C alleles.
Figure 2: This figure illustrates the experimental distribution of major HLA-I alleles in the IEDB. We plotted the alleles by type, where panel A shows the distribution for all data, B for the training dataset, C for the test dataset, and D for the validation dataset. Left represents HLA-A alleles, middle represents HLA-B alleles, and right represents HLA-C alleles.CC BY · PubMed Central
Figure 3: This figure evaluates TransHLA’s epitope prediction capabilities, benchmarked against other models using 2 key statistical metrics: AUROC and AUPRC. Panels (A) and (C) examine HLA-I class performance, with (A) showing AUROC and (C) presenting AUPRC. The graphs demonstrate TransHLA’s proficiency in distinguishing between epitope and nonepitope peptides for HLA-I, where AUROC indicates its discriminative power and AUPRC reflects the precision–recall trade-off. Panels (B) and (D) extend the analysis to HLA-II, with (B) displaying AUROC and (D) illustrating AUPRC. The performance depicted emphasizes TransHLA’s effectiveness in identifying HLA-II epitopes, highlighting its ability to differentiate between classes under imbalanced distributions. Together, the panels demonstrate TransHLA’s advantage over conventional models in epitope prediction for both HLA classes.
Figure 3: This figure evaluates TransHLA’s epitope prediction capabilities, benchmarked against other models using 2 key statistical metrics: AUROC and AUPRC. Panels (A) and (C) examine HLA-I class performance, with (A) showing AUROC and (C) presenting AUPRC. The graphs demonstrate TransHLA’s proficiency in distinguishing between epitope and nonepitope peptides for HLA-I, where AUROC indicates its discriminative power and AUPRC reflects the precision–recall trade-off. Panels (B) and (D) extend the analysis to HLA-II, with (B) displaying AUROC and (D) illustrating AUPRC. The performance depicted emphasizes TransHLA’s effectiveness in identifying HLA-II epitopes, highlighting its ability to differentiate between classes under imbalanced distributions. Together, the panels demonstrate TransHLA’s advantage over conventional models in epitope prediction for both HLA classes.CC BY · PubMed Central
Figure 4: This figure displays the PCA-based 2-dimensional feature space distribution of HLA-I and HLA-II epitope presentation test sets. The space is split into 2 regions: region I for HLA-I epitopes and region II for HLA-II epitopes. Each region shows positive samples as blue dots and negative samples as red dots, with representations from various model embeddings (A–H), including random pattern, TextCNN, TextRCNN, RNN-ATTs, DPCNN, random initial, ESM2 pretrained sequence, structure pretrained, and TransHLA.
Figure 4: This figure displays the PCA-based 2-dimensional feature space distribution of HLA-I and HLA-II epitope presentation test sets. The space is split into 2 regions: region I for HLA-I epitopes and region II for HLA-II epitopes. Each region shows positive samples as blue dots and negative samples as red dots, with representations from various model embeddings (A–H), including random pattern, TextCNN, TextRCNN, RNN-ATTs, DPCNN, random initial, ESM2 pretrained sequence, structure pretrained, and TransHLA.CC BY · PubMed Central
Figure 5: This comprehensive figure presents a series of violin plots illustrating the “helix content” structure property of peptides across various sample subsets for HLA-I and HLA-II molecules. Panel (A) delineates the helix content distribution in independent test samples for HLA-I, separated into positive and negative samples, with each subgroup’s statistical significance assessed via t-tests and annotated with corresponding P values. Panel (C) mirrors this setup for HLA-II independent test samples, highlighting the comparative helix content distributions. The external dataset distributions for HLA-I and HLA-II are respectively showcased in panels (B) and (D), emphasizing the metric’s external validity. Panels (E) and (F) delve deeper, contrasting the helix content of true positives and false negatives against true negatives and false positives within HLA-I and HLA-II datasets, respectively.
Figure 5: This comprehensive figure presents a series of violin plots illustrating the “helix content” structure property of peptides across various sample subsets for HLA-I and HLA-II molecules. Panel (A) delineates the helix content distribution in independent test samples for HLA-I, separated into positive and negative samples, with each subgroup’s statistical significance assessed via t-tests and annotated with corresponding P values. Panel (C) mirrors this setup for HLA-II independent test samples, highlighting the comparative helix content distributions. The external dataset distributions for HLA-I and HLA-II are respectively showcased in panels (B) and (D), emphasizing the metric’s external validity. Panels (E) and (F) delve deeper, contrasting the helix content of true positives and false negatives against true negatives and false positives within HLA-I and HLA-II datasets, respectively.CC BY · PubMed Central

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

Show all 1 references

Research works printed but not linked: 54

  1. Chaffey N , Alberts, B. , Johnson, A. , Lewis, J. , Raff, M. , Roberts, K. and Walter, P. Molecular biology of the cell. 4th edn. Oxford University Press; 2003. · DOI
  2. Murphy K , Weaver C. Janeway’s immunobiology. Garland science; 2016. · DOI
  3. Abbas A , Lichtman A , Pillai S. Cellular and molecular immunology E-book. Elsevier Health Sciences; 2014.
  4. 10.1158/2326-6066.CIR-19-0464 · DOI
  5. 10.1016/j.cels.2020.06.010 · DOI · Paper page
  6. 2021, DeepSeq-PanII: an interpretable recurrent neural network model with attention mechanism for peptide-HLA class II binding prediction, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 19, 2188
  7. 10.1042/BST20210410 · DOI
  8. 10.1093/bib/bbaa415 · DOI
  9. 10.1093/nar/gkaa379 · DOI · Paper page
  10. 10.1038/s42256-022-00459-7 · DOI
  11. Tadros DM , Racle J , Gfeller D. Predicting MHC-I ligands across alleles and species: How far can we go? bioRxiv 2024;p. 2024- 05. · DOI
  12. 10.1016/j.immuni.2023.03.009 · DOI
  13. Vaswani A , Shazeer N , Parmar N , Uszkoreit J , Jones L , Gomez AN , et al. Attention is all you need. Advances in neural information processing systems 2017;30.
  14. He K , Zhang X , Ren S , Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770-778. · DOI · Paper page
  15. 10.1126/science.ade2574 · DOI · Paper page
  16. Kim Y. Convolutional neural networks for sentence classification. arXiv preprint arXiv:14085882 2014;. · DOI · Paper page
  17. Lai S , Xu L , Liu K , Zhao J. Recurrent convolutional neural networks for text classification. In: Proceedings of the AAAI conference on artificial intelligence, vol. 29; 2015.. · DOI
  18. Johnson R , Zhang T. Deep pyramid convolutional neural networks for text categorization. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2017. p. 562-570. · DOI
  19. Zhou P , Shi W , Tian J , Qi Z , Li B , Hao H , et al. Attention-based bidirectional long short-term memory networks for relation classification. In: Proceedings of the 54th annual meeting of the association for computational linguistics (volume 2: Short papers); 2016. p. 207-212. · DOI
  20. 10.1093/nar/gky1006 · DOI
  21. 10.1093/nar/gkac902 · DOI
  22. 10.1093/nar/gkx760 · DOI
  23. Nolan S , Vignali M , Klinger M , Dines JN , Kaplan IM , Svejnoha E , et al. A large-scale database of T-cell receptor beta (TCRβ) sequences and binding associations from natural and synthetic exposure to SARS-CoV-2. Research square 2020;. · DOI
  24. 10.3389/fimmu.2022.855976 · DOI
  25. 10.3389/fimmu.2021.644637 · DOI
  26. 10.1038/nmeth.3176 · DOI · Paper page
  27. 10.1093/nar/gkl842 · DOI
  28. 10.1093/bioinformatics/bts565 · DOI · Paper page
  29. 2024, xTrimoPGLM: unified 100B-scale pre-trained transformer for deciphering the language of protein, arXiv preprint
  30. Elnaggar A , Heinzinger M , Dallago C , Rehawi G , Yu W , Jones L , et al. ProtTrans: Towards Cracking the Language of Lifes Code Through Self-Supervised Deep Learning and High Performance Computing. IEEE Transactions on Pattern Analysis and Machine Intelligence 2021;p. 1-1. · DOI
  31. 2020, Language Models are Few-Shot Learners, Advances in Neural Information Processing Systems, 33, 1877
  32. 10.1093/bib/bbad135 · DOI
  33. Xu Z , Zhong H , He B , Wang X , Lu T. PTransIPs: Identification of Phosphorylation Sites Enhanced by Protein PLM Embeddings. IEEE Journal of Biomedical and Health Informatics 2024;. · DOI
  34. 10.1038/s41592-022-01488-1 · DOI · Paper page
  35. 2018, Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv preprint
  36. 10.1038/s41587-019-0289-6 · DOI
  37. Nagler A , Kalaora S , Barbolin C , Gangaev A , Ketelaars SL , Alon M , et al. Identification of presented SARS-CoV-2 HLA class I and HLA class II peptides using HLA peptidomics. Cell Reports 2021;35(13). · DOI
  38. 10.3389/fimmu.2024.1293706 · DOI
  39. 10.1016/0098-3004(93)90090-R · DOI
  40. 10.1038/311123a0 · DOI
  41. 10.1021/acs.jcim.0c01397 · DOI
  42. Klatt MG , Mack KN , Bai Y , Aretz ZE , Nathan LI , Mun SS , et al. Solving an MHC allele-specific bias in the reported immunopeptidome. JCI insight 2020;5(19). · DOI
  43. 10.1093/bioinformatics/btp163 · DOI · Paper page
  44. 10.1002/prot.340190207 · DOI
  45. Chen T , Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016. p. 785-794. · DOI · Paper page
  46. 10.1038/s41586-022-04417-6 · DOI
  47. 10.6026/97320630081220 · DOI
  48. Baker E. Hydrogen bonding in biological macromolecules 2012;. · DOI
  49. 10.1021/la503865b · DOI
  50. 10.1039/c1sm05849e · DOI
  51. 10.1039/c3sm50807b · DOI
  52. 10.1016/j.bbapap.2013.02.011 · DOI
  53. Tianchi L , Xueying W , Wan N , Huo M , Shuaicheng L. Supporting data for “TransHLA: A Hybrid Transformer Model for HLA-Presented Epitope Detection”. GigaDB 2024; https://urldefense.com/v3/__https://doi.org/10.5524/102633__;!!KjDnqvtInNPT!i0agEmhs5f2c-6xn78vf1UHeQDc7MIvRJjXtTKhowEM818-6OF2FSrgCa2kiVF4O5NMkHRJhDcvGVR-Dmyvs$. · DOI
  54. Tianchi L , Xueying W , Wan N , Huo M , Shuaicheng L , TransHLA: A Hybrid Transformer Model for HLA-Presented Epitope Detection; 2024. https://urldefense.com/v3/__https://registry.dome-ml.org/review/peuywb6nkx__;!!KjDnqvtInNPT!i0agEmhs5f2c-6xn78vf1UHeQDc7MIvRJjXtTKhowEM818-6OF2FSrgCa2kiVF4O5NMkHRJhDcvGVW88ZMPB$. [DOME-ML Annotations].

Metadata

Authors
Lu, T., Wang, X., Nie, W., Huo, M., & Li, S.
Affiliations
  • City University of Hong Kong (HK)
  • Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong
ORCID
Venue
GigaScience
Publisher
openRxiv
Published
2025-01-24
Volume
14
ISSN
2047-217X (ISSN-L)
DOI
10.1101/2025.01.20.634002
PMC
PMC11878767
OpenAlex
W4408141849
Cited by
9
References
1
Citations by year
2026: 5 · 2025: 4
FWCI
2.67
Type
journal article
Language
en
Open access
Licence
Locations
  • GigaScience (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • CityU Scholars (submittedVersion, cc-by)
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
  • Life Sciences › Immunology and Microbiology › Immunology › Immunotherapy and Immune Responses
Keywords
HLA class I, HLA class II, ESM-2 embeddings, immunogenic epitopes, neoantigens, vaccine design, immunotherapy, IEDB, cedar
MeSH terms
Alleles, Epitopes, HLA Antigens, Humans, Software, Antigen Presentation, Epitope Mapping, Computational Biology

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: TransHLA: A Hybrid Transformer Model for HLA-Presented Epitope Detection. https://app.cochat.ai/papers/10.1101/2025.01.20.634002
The paper
Lu, T., Wang, X., Nie, W., Huo, M., & Li, S. (2025). TransHLA: A Hybrid Transformer Model for HLA-Presented Epitope Detection. GigaScience. https://doi.org/10.1101/2025.01.20.634002