Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Low-input deep learning platform for citrullinated peptide identification, autoantigen discovery and rheumatoid arthritis treatment stratification

Nature Biomedical Engineering (2026) Cite this article

Subjects

Abstract

Post-translationally modified proteins are crucial autoantigens in autoimmune diseases, with citrullinated proteins being key targets of autoantibodies in rheumatoid arthritis (RA). However, accurate citrullinome profiling and autoantigen identification remain limited by insufficient detection methods and computational tools. Here we develop Iseq-Cit (internal standard-assisted enrichment-free approach for high-throughput quantitative analysis of citrullinome), for global citrullinome profiling in individuals at RA risk and in patients with RA across a longitudinal cohort, requiring less than 1% of the sample input needed for conventional methods. We find that plasma citrullinome profiles closely correlate with RA development and severity. Moreover, we develop models integrating clinical indicators and citrullination data, achieving high accuracy in predicting treatment response. To evaluate the RA-sera reactivity of identified citrullinated peptides, we train a bidirectional gated recurrent unit model using 67,399 RA-sera negative and 8,816 RA-sera positive peptides. External validation through enzyme-linked immunosorbent assays confirms 84.2% accuracy in predicting RA-sera reactivity of citrullinated peptides, yielding 19 promising candidates for RA diagnosis. This work provides strategies for citrullinated peptide identification, autoantigen discovery and RA treatment stratification.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Workflow of Iseq-Cit and data quality assessment.
The alternative text for this image may have been generated using AI.
Fig. 2: Validation of citrullinome data by targeted MS.
The alternative text for this image may have been generated using AI.
Fig. 3: Citrullinomic characteristics in at-risk individuals and patients with RA.
The alternative text for this image may have been generated using AI.
Fig. 4: Association of citrullination with RA disease activity and treatment response.
The alternative text for this image may have been generated using AI.
Fig. 5: Machine learning models for predicting treatment response.
The alternative text for this image may have been generated using AI.
Fig. 6: Predicting RA-sera reactivity of citrullinated peptides by deep learning models.
The alternative text for this image may have been generated using AI.
Fig. 7: Validation of the antigenicity of citrullinated peptides.
The alternative text for this image may have been generated using AI.

Similar content being viewed by others

Data availability

The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (https://proteomecentral.proteomexchange.org) via the iProX partner repository with the dataset identifier PXD054979 (ref. 98) and PXD048245 (ref. 99). Source data are provided with this paper.

Code availability

The code supporting this study is available at https://github.com/MonnaHu/Iseq-Cit-RA/tree/master/20250404.

References

  1. Kacen, A. et al. Post-translational modifications reshape the antigenic landscape of the MHC I immunopeptidome in tumors. Nat. Biotechnol. 41, 239–251 (2023).

    Article  CAS  PubMed  Google Scholar 

  2. Kelly, S. D., Allas, M. J., Goodridge, L. D., Lowary, T. L. & Whitfield, C. Structure, biosynthesis and regulation of the T1 antigen, a phase-variable surface polysaccharide conserved in many Salmonella serovars. Nat. Commun. 15, 6504 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Teplensky, M. H. et al. Multi-antigen spherical nucleic acid cancer vaccines. Nat. Biomed. Eng. 7, 911–927 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Ando, Y. et al. Using tumor marker gene variants to improve the diagnostic accuracy of DUPAN-2 and carbohydrate antigen 19-9 for pancreatic cancer. J. Clin. Oncol. 42, 2196–2206 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Liang, X., Cheng, H., Liu, C. & Liu, G. Antigen self-presenting nanovaccine for cancer immunotherapy. Sci. Bull. 67, 1611–1613 (2022).

    Article  Google Scholar 

  6. Yang, J., Chen, Y., Jing, Y., Green, M. R. & Han, L. Advancing CAR T cell therapy through the use of multidimensional omics data. Nat. Rev. Clin. Oncol. 20, 211–228 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Xie, N. et al. Neoantigens: promising targets for cancer therapy. Signal Transduct. Target. Ther. 8, 9 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Ding, Q. et al. Signaling pathways in rheumatoid arthritis: implications for targeted therapy. Signal Transduct. Target. Ther. 8, 68 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  9. Zhong, Q. et al. Protein posttranslational modifications in health and diseases: functions, regulatory mechanisms, and therapeutic implications. MedComm 4, e261 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Curran, A. M. et al. Citrullination modulates antigen processing and presentation by revealing cryptic epitopes in rheumatoid arthritis. Nat. Commun. 14, 1061 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Alivernini, S., Firestein, G. S. & McInnes, I. B. The pathogenesis of rheumatoid arthritis. Immunity 55, 2255–2270 (2022).

    Article  CAS  PubMed  Google Scholar 

  12. Maggi, J. et al. Isolation of HLA-DR-naturally presented peptides identifies T-cell epitopes for rheumatoid arthritis. Ann. Rheum. Dis. 81, 1096–1105 (2022).

    Article  PubMed  Google Scholar 

  13. Toes, R. & Pisetsky, D. S. Pathogenic effector functions of ACPA: where do we stand? Ann. Rheum. Dis. 78, 716–721 (2019).

    Article  PubMed  Google Scholar 

  14. Ge, C. et al. Structural basis of cross-reactivity of anti-citrullinated protein antibodies. Arthritis Rheumatol. 71, 210–221 (2019).

    Article  CAS  PubMed  Google Scholar 

  15. Steen, J. et al. Recognition of amino acid motifs, rather than specific proteins, by human plasma cell-derived monoclonal antibodies to posttranslationally modified proteins in rheumatoid arthritis. Arthritis Rheumatol. 71, 196–209 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Lewallen, D. M. et al. Chemical proteomic platform to identify citrullinated proteins. ACS Chem. Biol. 10, 2520–2528 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Tilvawala, R. et al. The rheumatoid arthritis-associated citrullinome. Cell Chem. Biol. 25, 691–704.e696 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Juarez, M. et al. Identification of novel antiacetylated vimentin antibodies in patients with early inflammatory arthritis. Ann. Rheum. Dis. 75, 1099–1107 (2016).

    Article  CAS  PubMed  Google Scholar 

  19. Scherer, H. U., van der Woude, D. & Toes, R. E. M. From risk to chronicity: evolution of autoreactive B cell and antibody responses in rheumatoid arthritis. Nat. Rev. Rheumatol. 18, 371–383 (2022).

    Article  CAS  PubMed  Google Scholar 

  20. Suwannalai, P. et al. Low-avidity anticitrullinated protein antibodies (ACPA) are associated with a higher rate of joint destruction in rheumatoid arthritis. Ann. Rheum. Dis. 73, 270–276 (2014).

    Article  CAS  PubMed  Google Scholar 

  21. Bondt, A. et al. ACPA IgG galactosylation associates with disease activity in pregnant patients with rheumatoid arthritis. Ann. Rheum. Dis. 77, 1130–1136 (2018).

    Article  CAS  PubMed  Google Scholar 

  22. Willemze, A., Trouw, L. A., Toes, R. E. & Huizinga, T. W. The influence of ACPA status and characteristics on the course of RA. Nat. Rev. Rheumatol. 8, 144–152 (2012).

    Article  CAS  PubMed  Google Scholar 

  23. van der Woude, D. & Toes, R. E. M. Immune response to post-translationally modified proteins in rheumatoid arthritis: what makes it special?. Ann. Rheum. Dis. 83, 838–846 (2024).

    Article  PubMed  Google Scholar 

  24. Gerlag, D. M. et al. EULAR recommendations for terminology and research in individuals at risk of rheumatoid arthritis: report from the study group for risk factors for rheumatoid arthritis. Ann. Rheum. Dis. 71, 638–641 (2012).

    Article  PubMed  PubMed Central  Google Scholar 

  25. He, S. et al. A longitudinal cohort study uncovers plasma protein biomarkers predating clinical onset and treatment response of rheumatoid arthritis. Nat. Commun. 16, 6692 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Mondal, S. & Thompson, P. R. Protein arginine deiminases (PADs): biochemistry and chemical biology of protein citrullination. Acc. Chem. Res. 52, 818–832 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Assohou-Luty, C. et al. The human peptidylarginine deiminases type 2 and type 4 have distinct substrate specificities. Biochim. Biophys. Acta. 1844, 829–836 (2014).

    Article  CAS  PubMed  Google Scholar 

  28. Gong, Y. et al. Acetylation profiling by Iseq-Kac reveals insights into HSC aging and lineage decision. Nat. Chem. Biol. 21, 1675–1687 (2025).

    Article  CAS  PubMed  Google Scholar 

  29. Rebak, A. S. et al. A quantitative and site-specific atlas of the citrullinome reveals widespread existence of citrullination and insights into PADI4 substrates. Nat. Struct. Mol. Biol. 31, 977–995 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Clancy, K. W., Weerapana, E. & Thompson, P. R. Detection and identification of protein citrullination in complex biological systems. Curr. Opin. Chem. Biol. 30, 1–6 (2016).

    Article  CAS  PubMed  Google Scholar 

  31. Lee, C. Y. et al. Mining the human tissue proteome for protein citrullination. Mol. Cell. Proteom. 17, 1378–1391 (2018).

    Article  CAS  Google Scholar 

  32. Hensen, S. M. & Pruijn, G. J. Methods for the detection of peptidylarginine deiminase (PAD) activity and protein citrullination. Mol. Cell. Proteom. 13, 388–396 (2014).

    Article  CAS  Google Scholar 

  33. Buda, M., Maki, A. & Mazurowski, M. A. A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 106, 249–259 (2018).

    Article  PubMed  Google Scholar 

  34. Murata, K. et al. Hypoxia-sensitive COMMD1 integrates signaling and cellular metabolism in human macrophages and suppresses osteoclastogenesis. Immunity 47, 66–79.e65 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  35. Lee, S. et al. Identification of MYH9 as a key regulator for synoviocyte migration and invasion through secretome profiling. Ann. Rheum. Dis. 82, 1035–1048 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  36. Zhao, X. et al. Circulating immune complexes contain citrullinated fibrinogen in rheumatoid arthritis. Arthritis Res. Ther. 10, R94 (2008).

    Article  PubMed  PubMed Central  Google Scholar 

  37. Iwamoto, N. et al. Osteogenic differentiation of fibroblast-like synovial cells in rheumatoid arthritis is induced by microRNA-218 through a ROBO/Slit pathway. Arthritis Res. Ther. 20, 189 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  38. Muller, S. & Radic, M. Citrullinated autoantigens: from diagnostic markers to pathogenetic mechanisms. Clin. Rev. Allergy Immunol. 49, 232–239 (2015).

    Article  CAS  PubMed  Google Scholar 

  39. Sturfelt, G. & Truedsson, L. Complement in the immunopathogenesis of rheumatic disease. Nat. Rev. Rheumatol. 8, 458–468 (2012).

    Article  CAS  PubMed  Google Scholar 

  40. Tran, L. S. et al. ER O-glycosylation in synovial fibroblasts drives cartilage degradation. Nat. Commun. 16, 2535 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Olumuyiwa-Akeredolu, O. O., Page, M. J., Soma, P. & Pretorius, E. Platelets: emerging facilitators of cellular crosstalk in rheumatoid arthritis. Nat. Rev. Rheumatol. 15, 237–248 (2019).

    Article  PubMed  Google Scholar 

  42. Niehaus, J. K., Taylor-Blake, B., Loo, L., Simon, J. M. & Zylka, M. J. Spinal macrophages resolve nociceptive hypersensitivity after peripheral injury. Neuron 109, 1274–1282.e1276 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Ummarino, D. Rheumatoid arthritis: ACPA status influences RA development. Nat. Rev. Rheumatol. 13, 450 (2017).

    PubMed  Google Scholar 

  44. Pertsinidou, E. et al. In early rheumatoid arthritis, anticitrullinated peptide antibodies associate with low number of affected joints and rheumatoid factor associates with systemic inflammation. Ann. Rheum. Dis. 83, 277–287 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  45. Kastbom, A. et al. Changes in anti-citrullinated protein antibody isotype levels in relation to disease activity and response to treatment in early rheumatoid arthritis. Clin. Exp. Immunol. 194, 391–399 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  46. Takeuchi, T. et al. High titers of both rheumatoid factor and anti-CCP antibodies at baseline in patients with rheumatoid arthritis are associated with increased circulating baseline TNF level, low drug levels, and reduced clinical responses: a post hoc analysis of the RISING study. Arthritis Res. Ther. 19, 194 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  47. Wells, G. et al. Validation of the 28-joint disease activity score (DAS28) and European league against rheumatism response criteria based on C-reactive protein against disease progression in patients with rheumatoid arthritis, and comparison with the DAS28 based on erythrocyte sedimentation rate. Ann. Rheum. Dis. 68, 954–960 (2009).

    Article  CAS  PubMed  Google Scholar 

  48. Smolen, J. S. et al. EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs. Ann. Rheum. Dis. 69, 964–975 (2010).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  49. Megahed, F. M. et al. The class imbalance problem. Nat. Methods 18, 1270–1272 (2021).

    Article  CAS  PubMed  Google Scholar 

  50. Muthukrishnan, R. & Rohini, R. in 2016 IEEE International Conference on Advances in Computer Applications (ICACA) 18–20 (IEEE, 2016).

  51. Zhu, X. W., Xin, Y. J. & Ge, H. L. Recursive random forests enable better predictive performance and model interpretation than variable selection by LASSO. J. Chem. Inf. Model. 55, 736–746 (2015).

    Article  CAS  PubMed  Google Scholar 

  52. Shieh, M.-D. & Yang, C.-C. Multiclass SVM-RFE for product form feature selection. Expert Syst. Appl. 35, 531–541 (2008).

    Article  Google Scholar 

  53. Guan, S. et al. Identifying potential targets for preventing cancer progression through the PLA2G1B recombinant protein using bioinformatics and machine learning methods. Int. J. Biol. Macromol. 276, 133918 (2024).

    Article  CAS  PubMed  Google Scholar 

  54. Efthimiou, O. et al. Developing clinical prediction models: a step-by-step guide. BMJ 386, e078276 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  55. Sahlström, P. et al. Different hierarchies of anti-modified protein autoantibody reactivities in rheumatoid arthritis. Arthritis Rheumatol. 72, 1643–1657 (2020).

    Article  PubMed  Google Scholar 

  56. Zheng, Z. et al. Disordered antigens and epitope overlap between anti-citrullinated protein antibodies and rheumatoid factor in rheumatoid arthritis. Arthritis Rheumatol. 72, 262–272 (2020).

    Article  CAS  PubMed  Google Scholar 

  57. Lo, K. C. et al. Comprehensive profiling of the rheumatoid arthritis antibody repertoire. Arthritis Rheumatol. 72, 242–250 (2020).

    Article  CAS  PubMed  Google Scholar 

  58. Thandapani, P., O’Connor, T. R., Bailey, T. L. & Richard, S. Defining the RGG/RG motif. Mol. Cell 50, 613–623 (2013).

    Article  CAS  PubMed  Google Scholar 

  59. Ali, S. M. et al. Baseline serum NTx levels are prognostic in metastatic breast cancer patients with bone-only metastasis. Ann. Oncol. 15, 455–459 (2004).

    Article  CAS  PubMed  Google Scholar 

  60. Fert-Bober, J., Darrah, E. & Andrade, F. Insights into the study and origin of the citrullinome in rheumatoid arthritis. Immunol. Rev. 294, 133–147 (2020).

    Article  CAS  PubMed  Google Scholar 

  61. Kokkonen, H. et al. Antibodies of IgG, IgA and IgM isotypes against cyclic citrullinated peptide precede the development of rheumatoid arthritis. Arthritis Res. Ther. 13, R13 (2011).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  62. Ten Brinck, R. M., Toes, R. E. M. & van der Helm-van Mil, A. H. M. Inflammation functions as a key mediator in the link between ACPA and erosion development: an association study in clinically suspect arthralgia. Arthritis Res. Ther. 20, 89 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  63. van Delft, M. A. M. & Huizinga, T. W. J. An overview of autoantibodies in rheumatoid arthritis. J. Autoimmun. 110, 102392 (2020).

    Article  PubMed  Google Scholar 

  64. Yu, K. & Proost, P. Insights into peptidylarginine deiminase expression and citrullination pathways. Trends Cell Biol. 32, 746–761 (2022).

    Article  CAS  PubMed  Google Scholar 

  65. Wouters, F. et al. Determining in which pre-arthritis stage HLA-shared epitope alleles and smoking exert their effect on the development of rheumatoid arthritis. Ann. Rheum. Dis. 81, 48–55 (2022).

    Article  CAS  PubMed  Google Scholar 

  66. Di Matteo, A., Bathon, J. M. & Emery, P. Rheumatoid arthritis. Lancet 402, 2019–2033 (2023).

    Article  PubMed  Google Scholar 

  67. Sparks, J. A. & Costenbader, K. H. Rheumatoid arthritis in 2017: protective dietary and hormonal factors brought to light. Nat. Rev. Rheumatol. 14, 71–72 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  68. Smolen, J. S., Aletaha, D. & McInnes, I. B. Rheumatoid arthritis. Lancet 388, 2023–2038 (2016).

    Article  CAS  PubMed  Google Scholar 

  69. Jiang, L. et al. A high-fiber diet synergizes with Prevotella copri and exacerbates rheumatoid arthritis. Cell. Mol. Immunol. 19, 1414–1424 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  70. Trocmé, C. et al. Apolipoprotein A-I and platelet factor 4 are biomarkers for infliximab response in rheumatoid arthritis. Ann. Rheum. Dis. 68, 1328–1333 (2009).

    Article  PubMed  Google Scholar 

  71. Cho, A. et al. A multi-biomarker panel for predicting tocilizumab response in rheumatoid arthritis patients. Transl. Res. 273, 23–31 (2024).

    Article  CAS  PubMed  Google Scholar 

  72. Smolen, J. S. et al. EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs: 2019 update. Ann. Rheum. Dis. 79, 685–699 (2020).

    Article  CAS  PubMed  Google Scholar 

  73. Zhang, T. et al. Serum proteomics analysis of biomarkers for evaluating clinical response to MTX/IGU therapy in early rheumatoid arthritis. Mol. Immunol. 153, 119–125 (2023).

    Article  CAS  PubMed  Google Scholar 

  74. Ponchel, F. et al. An immunological biomarker to predict MTX response in early RA. Ann. Rheum. Dis. 73, 2047–2053 (2014).

    Article  CAS  PubMed  Google Scholar 

  75. Maciejewski, M. et al. Prediction of response of methotrexate in patients with rheumatoid arthritis using serum lipidomics. Sci. Rep. 11, 7266 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  76. Owen, S. A. et al. Genetic polymorphisms in key methotrexate pathway genes are associated with response to treatment in rheumatoid arthritis patients. Pharmacogenomics J. 13, 227–234 (2013).

    Article  CAS  PubMed  Google Scholar 

  77. Liu, T., Shi, K. & Li, W. Deep learning methods improve linear B-cell epitope prediction. BioData Min. 13, 1 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  78. Shashkova, T. I. et al. SEMA: antigen B-cell conformational epitope prediction using deep transfer learning. Front. Immunol. 13, 960985 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  79. Ju, Z. & Wang, S. Y. Prediction of citrullination sites by incorporating k-spaced amino acid pairs into Chou’s general pseudo amino acid composition. Gene 664, 78–83 (2018).

    Article  CAS  PubMed  Google Scholar 

  80. Liu, Y., Li, A., Zhao, X. M. & Wang, M. DeepTL-Ubi: a novel deep transfer learning method for effectively predicting ubiquitination sites of multiple species. Methods 192, 103–111 (2021).

    Article  CAS  PubMed  Google Scholar 

  81. Yang, H., Wang, M., Liu, X., Zhao, X. M. & Li, A. PhosIDN: an integrated deep neural network for improving protein phosphorylation site prediction by combining sequence and protein-protein interaction information. Bioinformatics 37, 4668–4676 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  82. Wang, H., Zhao, H., Yan, Z., Zhao, J. & Han, J. MDCAN-Lys: a model for predicting succinylation sites based on multilane dense convolutional attention network. Biomolecules 11, 872 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  83. Meng, L. et al. TransPTM: a transformer-based model for non-histone acetylation site prediction. Brief. Bioinform. 25, 3 (2024).

    Article  Google Scholar 

  84. Luo, F., Wang, M., Liu, Y., Zhao, X. M. & Li, A. DeepPhos: prediction of protein phosphorylation sites with deep learning. Bioinformatics 35, 2766–2773 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  85. Deznabi, I., Arabaci, B., Koyutürk, M. & Tastan, O. DeepKinZero: zero-shot learning for predicting kinase-phosphosite associations involving understudied kinases. Bioinformatics 36, 3652–3661 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  86. Parvez, A., Ali, S. D., Tayara, H. & Chong, K. T. Stacking based ensemble learning framework for identification of nitrotyrosine sites. Comput. Biol. Med. 183, 109200 (2024).

    Article  CAS  PubMed  Google Scholar 

  87. Anashkina, A. A. et al. A novel approach for predicting protein S-glutathionylation. BMC Bioinform. 21, 282 (2020).

    Article  CAS  Google Scholar 

  88. Guo, Y. et al. GPS-PBS: a deep learning framework to predict phosphorylation sites that specifically interact with phosphoprotein-binding domains. Cells 9, 1266 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  89. Ahmed, S., Kabir, M., Arif, M., Khan, Z. U. & Yu, D. J. DeepPPSite: a deep learning-based model for analysis and prediction of phosphorylation sites using efficient sequence information. Anal. Biochem. 612, 113955 (2021).

    Article  CAS  PubMed  Google Scholar 

  90. Tilvawala, R. et al. The role of SERPIN citrullination in thrombosis. Cell Chem. Biol. 28, 1728–1739.e1725 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  91. Sun, L. et al. A new unconventional HLA-A2-restricted epitope from HBV core protein elicits antiviral cytotoxic T lymphocytes. Protein Cell 5, 317–327 (2014).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  92. Lagattuta, K. A. et al. Repertoire analyses reveal T cell antigen receptor sequence features that influence T cell fate. Nat. Immunol. 23, 446–457 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  93. Sakuma, S. et al. FK506 potently inhibits T cell activation induced TNF-alpha and IL-1beta production in vitro by human peripheral blood mononuclear cells. Br. J. Pharmacol. 130, 1655–1663 (2000).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  94. Sanchez-Trincado, J. L., Gomez-Perosanz, M. & Reche, P. A. Fundamentals and methods for T- and B-cell epitope prediction. J. Immunol. Res. 2017, 2680160 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  95. Hao, G. et al. Neutral loss of isocyanic acid in peptide CID spectra: a novel diagnostic marker for mass spectrometric identification of protein citrullination. J. Am. Soc. Mass Spectrom. 20, 723–727 (2009).

    Article  CAS  PubMed  Google Scholar 

  96. Chaerkady, R. et al. Characterization of citrullination sites in neutrophils and mast cells activated by ionomycin via integration of mass spectrometry and machine learning. J. Proteome Res. 20, 3150–3164 (2021).

    Article  CAS  PubMed  Google Scholar 

  97. Sonnett, M., Yeung, E. & Wühr, M. Accurate, sensitive, and precise multiplexed proteomics using the complement reporter ion cluster. Anal. Chem. 90, 5032–5039 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  98. Hu, M. et al. Low-input, deep learning platform for citrullinated peptide identification, autoantigen discovery, and rheumatoid arthritis treatment stratification. iProX https://www.iprox.cn//page/project.html?id=IPX0009393000 (2025).

  99. He, S. et al. A longitudinal cohort study uncovers plasma protein biomarkers predating clinical onset and treatment response of rheumatoid arthritis. iProX https://www.iprox.cn//page/project.html?id=IPX0005696000 (2025).

Download references

Acknowledgements

We thank M. Wühr at Princeton University for generously sharing the TMTc+ algorithm. This work was supported by the Noncommunicable Chronic Diseases-National Science and Technology Major Project (2024ZD0531100 to L.D.), the National Key Research and Development Program of China (numbers 2022YFA1303200 to L.D. and 2019YFE0108200 to Y.Z.), the Program of Tianfu Jincheng Laboratory (number 2025ZH024 to L.D.), the National Natural Science Foundation of China (numbers 81570060, 82073221 and 31870826 to L.D., 82471830 and W2431021 to R.H.), the Science and Technology Project of Sichuan Province (number 2024YFFK0099 to L.D.), the Sichuan International Science and Technology Cooperation Project (numbers 2022YFH0023, 2024YFHZ0231 and 2024JDHJ0044 to Y.Z.), the Science Popularization Base Project of Chengdu Science and Technology Bureau (number 2022-GH03-00003-HZ to Y.Z.), the West China Hospital 135 Project for Disciplines of Excellence (number 21HXFH002 to Y.Z.), the West China Hospital Hospital-Enterprise Cooperation Clinical Research Innovation Project (number 21HXCX004 to Y.Z.), the National Clinical Research Center for Geriatrics, West China Hospital (number Z2024JC002 to L.D.), the West China Hospital 135 project (number ZYYC23013 to L.D.) and Vetenskapsrådet (number 2024-02575 to R.H.).

Author information

Author notes

  1. These authors contributed equally: Meng Hu, Chenxi Zhu, Rui Sun, Zhiqiang Xu, Yanqiu Gong, Yi Liu.

Authors and Affiliations

  1. Department of Rheumatology and Immunology and Department of Laboratory Medicine, National Clinical Research Center for Geriatrics, State Key Laboratory of Biotherapy, West China Hospital, Sichuan University, Chengdu, China

    Meng Hu, Chenxi Zhu, Rui Sun, Zhiqiang Xu, Yanqiu Gong, Yi Liu, Yan Liu, Jiayi Xu, Huifang Hu, Tao Chen, Heng Xu, Binwu Ying, Yong Peng, Yi Zhao & Lunzhi Dai

  2. Department of Rheumatology and Immunology, Clinical Institute of Inflammation and Immunology, Frontiers Science Center for Disease-related Molecular Network, West China Hospital, Sichuan University, Chengdu, China

    Chenxi Zhu, Martin Herrmann & Yi Zhao

  3. Department of Dermatology and Venereology, West China Hospital, Sichuan University, Chengdu, China

    Chenxi Zhu

  4. Tianfu Jincheng Laboratory, Chengdu, China

    Zhiqiang Xu

  5. College of Optical Science and Engineering, Zhejiang University, Hangzhou, China

    Mengyue Zhang

  6. Department of Rheumatology and Immunology, First Affiliated Hospital of Army Military Medical University, Chongqing, China

    Qinghua Zou

  7. Department of Rheumatology and Immunology, The First Hospital of China Medical University, Shenyang, China

    Pingting Yang

  8. Department of Rheumatology and Immunology, Mianyang Central Hospital, Mianyang, China

    Jinmei Zou

  9. Department of Rheumatology and Immunology, Minda Hospital of Hubei, Minzu University, Enshi, China

    Linchong Su

  10. Department of Rheumatology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China

    Wenfeng Tan

  11. Department of Rheumatology, and National Joint Engineering Research Center of Biodiagnostics and Biotherapy, Second Affiliated Hospital, Xi’an Jiaotong University, Xi’an, China

    Liesu Meng

  12. Department of Pediatric Surgery, University Medical Center Mannheim, University of Heidelberg, Mannheim, Germany

    Martin Herrmann & Luis E. Muñoz

  13. Department of Urology and Institute of Urology (Laboratory of Reconstructive Urology), State Key Laboratory of Biotherapy and Cancer Center, West China Hospital, Sichuan University, Chengdu, China

    Shijian Feng & Tao Lin

  14. Department of Rheumatology and Inflammation Research, Institute for Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden

    Inger Gjertsson

  15. Section of Medical Inflammation Research, Department of Medical Biochemistry and Biophysics, Karolinska Institute, Stockholm, Sweden

    Rikard Holmdahl

Authors
  1. Meng Hu
    View author publications

    Search author on:PubMed Google Scholar

  2. Chenxi Zhu
    View author publications

    Search author on:PubMed Google Scholar

  3. Rui Sun
    View author publications

    Search author on:PubMed Google Scholar

  4. Zhiqiang Xu
    View author publications

    Search author on:PubMed Google Scholar

  5. Yanqiu Gong
    View author publications

    Search author on:PubMed Google Scholar

  6. Yi Liu
    View author publications

    Search author on:PubMed Google Scholar

  7. Yan Liu
    View author publications

    Search author on:PubMed Google Scholar

  8. Jiayi Xu
    View author publications

    Search author on:PubMed Google Scholar

  9. Huifang Hu
    View author publications

    Search author on:PubMed Google Scholar

  10. Tao Chen
    View author publications

    Search author on:PubMed Google Scholar

  11. Mengyue Zhang
    View author publications

    Search author on:PubMed Google Scholar

  12. Qinghua Zou
    View author publications

    Search author on:PubMed Google Scholar

  13. Pingting Yang
    View author publications

    Search author on:PubMed Google Scholar

  14. Jinmei Zou
    View author publications

    Search author on:PubMed Google Scholar

  15. Linchong Su
    View author publications

    Search author on:PubMed Google Scholar

  16. Wenfeng Tan
    View author publications

    Search author on:PubMed Google Scholar

  17. Liesu Meng
    View author publications

    Search author on:PubMed Google Scholar

  18. Martin Herrmann
    View author publications

    Search author on:PubMed Google Scholar

  19. Luis E. Muñoz
    View author publications

    Search author on:PubMed Google Scholar

  20. Shijian Feng
    View author publications

    Search author on:PubMed Google Scholar

  21. Tao Lin
    View author publications

    Search author on:PubMed Google Scholar

  22. Heng Xu
    View author publications

    Search author on:PubMed Google Scholar

  23. Binwu Ying
    View author publications

    Search author on:PubMed Google Scholar

  24. Yong Peng
    View author publications

    Search author on:PubMed Google Scholar

  25. Inger Gjertsson
    View author publications

    Search author on:PubMed Google Scholar

  26. Rikard Holmdahl
    View author publications

    Search author on:PubMed Google Scholar

  27. Yi Zhao
    View author publications

    Search author on:PubMed Google Scholar

  28. Lunzhi Dai
    View author publications

    Search author on:PubMed Google Scholar

Contributions

L.D. and Y.Z. designed the project and wrote the paper. Z.X., R.S. and M. Hu performed citrullinome profiling and participated in the validation of antigen peptides. M. Hu and C.Z. established the antigen prediction model and performed the cell experiments. R.S. conducted the validation of antigen peptides. M. Hu analysed the omics data and generated figures. Y.G. completed MRM analysis. Yi Liu collected the samples and carried out follow-ups. Yan Liu purified the ACPAs. M.Z. assisted in establishing the model. J.X., H.H. and T.C. supported the validation of the antigens. Q.Z., P.Y., J.Z., L.S., W.T. and L.M. managed the data processing of participating study populations. S.F., T.L. and Y.P. provided technical support and tissues samples. B.Y., I.G., R.H., M. Herrmann, H.X. and L.E.M. revised the paper and provided helpful suggestions.

Corresponding authors

Correspondence to Yi Zhao or Lunzhi Dai.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Biomedical Engineering thanks Jared Delmar and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Peer reviewer reports are available.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information (download PDF )

Supplementary Figs. 1–8.

Reporting Summary (download PDF )

Peer Review File (download PDF )

Supplementary Data 1 (download XLSX )

The clinical information and citrullinome data.

Supplementary Data 2 (download XLSX )

Training datasets and training metrics tables for the deep learning models.

Supplementary Data 3 (download XLSX )

Clinical information of samples subjected to ELISA and T cell assays.

Source data

Source Data Figs. 1, 3–5, 7 and 8 and Supplementary Figs. 1–5 and 8 (download XLSX )

Source data for Figs. 1 and 3–8 and Supplementary Figs. 1–5 and 8.

Source Data Fig. 2 (download PDF )

Source data for MRM and blots.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, M., Zhu, C., Sun, R. et al. Low-input deep learning platform for citrullinated peptide identification, autoantigen discovery and rheumatoid arthritis treatment stratification. Nat. Biomed. Eng (2026). https://doi.org/10.1038/s41551-026-01628-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s41551-026-01628-4

Search

Advanced search

Quick links

Nature Briefing: Translational Research

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research