Accurate and ultra-fast de novo HLA-I immunopeptide sequencing with FoxNovo
摘要
We present FoxNovo, a hybrid deep learning-combinatorial framework for de novo sequencing of immunopeptides trained on a large-scale HLA-I immunopeptidomics dataset assembled and reprocessed from public mass spectrometry (MS) repositories. This integration achieved >90% peptide accuracy on the reported benchmarks while enabling repository-scale analysis at ~2,800 spectra per second—more than 100-fold faster than the evaluated beam-search baseline under the reported benchmark conditions. To mimic the heterogeneous spectral quality encountered in experimental MS analyses, we constructed controlled peak-removal stress tests, in which FoxNovo retained higher accuracy than the evaluated methods at different simulation levels. We subsequently re-analyzed 168 million spectra from all collected 4,423 MS raw files in only 18 hours on a single GPU, equivalent to ~245 raw files per hour. This repository-scale application yielded score-filtered canonical and putative ncORF-mapped peptide predictions and recovered 41 of 42 non-canonical HLA-I peptides previously validated by targeted MS. FoxNovo demonstrates the potential of integrating AI with combinatorial decoding for scalable immunopeptidomics. The source code is available at https://github.com/fennomix/fennomix.novo.
参考文献
1. Chong, C., Coukos, G. & Bassani-Sternberg, M. Identification of tumor antigens with immunopeptidomics. Nat. Biotechnol. 40, 175–188 (2022).
2. Apavaloaei, A. et al. Tumor antigens preferentially derive from unmutated genomic sequences in melanoma and non-small cell lung cancer. Nat. Cancer 6, 1419–1437 (2025).
3. Huber, F. et al. A comprehensive proteogenomic pipeline for neoantigen discovery to advance personalized cancer immunotherapy. Nat. Biotechnol. 43, 1360–1372 (2025).
4. Laumont, C. M. et al. Noncoding regions are the main source of targetable tumor-specific antigens. Sci. Transl. Med. 10, eaau5516 (2018).
5. Chong, C. et al. Integrated proteogenomic deep sequencing and analytics accurately identify non-canonical peptides in tumor immunopeptidomes. Nat. Commun. 11, 1293 (2020).
6. Tsour, S. et al. Alternate RNA decoding results in stable and abundant proteins in mammals. Nature (2026).
7. Schumacher, T. N. & Schreiber, R. D. Neoantigens in cancer immunotherapy. Science. 348, 69–74 (2015).
8. Liao, H. et al. MARS an improved de novo peptide candidate selection method for non-canonical antigen target discovery in cancer. Nat. Commun. 15, 661 (2024).
9. Yilmaz, M. et al. Sequence-to-sequence translation from mass spectra to peptides with a transformer model. Nat. Commun. 15, 6427 (2024).
10. shah, D. et al. Proteogenomics and de novo sequencing based approach for neoantigen discovery from the immunopeptidomes of patient CRC liver metastases using Mass Spectrometry. J. Immunol. 204, 217.16-217.16 (2020).
11. Perez-Riverol, Y. et al. The PRIDE database at 20 years: 2025 update. Nucleic Acids Res. 53, D543–D553 (2025).
12. Ma, J. et al. iProX: an integrated proteome resource. Nucleic Acids Res. 47, D1211–D1217 (2019).
13. Wang, M. et al. Sharing and community curation of mass spectrometry data with Global Natural Products Social Molecular Networking. Nat. Biotechnol. 34, 828–837 (2016).
14. Tran, N. H., Zhang, X., Xin, L., Shan, B. & Li, M. De novo peptide sequencing by deep learning. Proc. Natl. Acad. Sci. USA. 114, 8247–8252 (2017).
15. Eloff, K. et al. InstaNovo enables diffusion-powered de novo peptide sequencing in large-scale proteomics experiments. Nat. Mach. Intell. 7, 565–579 (2025).
16. Zhao, J. et al. A large-scale unified deep learning model for peptide mass spectrum interpretation trained on multimodal data. Nat. Mach. Intell. 8, 997–1011 (2026).
17. Liu, K., Ye, Y., Li, S. & Tang, H. Accurate de novo peptide sequencing using fully convolutional neural networks. Nat. Commun. 14, 7974 (2023).
18. Zhang, X. et al. π-PrimeNovo: an accurate and efficient non-autoregressive deep learning model for de novo peptide sequencing. Nat. Commun. 16, 267 (2025).
19. Chi, H. et al. pNovo+: De Novo Peptide Sequencing Using Complementary HCD and ETD Tandem Mass Spectra. J. Proteome Res. 12, 615–625 (2013).
20. Chi, H. et al. pNovo: De novo Peptide Sequencing and Identification Using HCD Spectra. J. Proteome Res. 9, 2713–2724 (2010).
21. Chi, H. et al. Comprehensive identification of peptides in tandem mass spectra using an efficient open search engine. Nat. Biotechnol. 36, 1059–1061 (2018).
22. Kong, A. T., Leprevost, F. V., Avtonomov, D. M., Mellacheruvu, D. & Nesvizhskii, A. I. MSFragger: ultrafast and comprehensive peptide identification in mass spectrometry–based proteomics. Nat. Methods 14, 513–520 (2017).
23. Yang, K. L. et al. MSBooster: improving peptide identification rates using deep learning-based features. Nat. Commun. 14, 4539 (2023).
24. Wallmann, G. et al. AlphaDIA enables DIA transfer learning for feature-free proteomics. Nat. Biotechnol. 44, 1168–1177 (2026).
25. Zeng, W.-F. et al. AlphaPeptDeep: a modular deep learning framework to predict peptide properties for proteomics. Nat. Commun. 13, 7238 (2022).
26. Sarkizova, S. et al. A large peptidome dataset improves HLA class I epitope prediction across most of the human population. Nat. Biotechnol. 38, 199–209 (2020).
27. Abelin, J. G. et al. Mass Spectrometry Profiling of HLA-Associated Peptidomes in Mono-allelic Cells Enables More Accurate Epitope Prediction. Immunity 46, 315–326 (2017).
28. Wang, C., Cho, K. & Gu, J. Neural Machine Translation with Byte-Level Subwords. Proc. AAAI Conf. Artif. Intell. 34, 9154–9160 (2020).
29. Zhang, J. et al. PEAKS DB: De Novo Sequencing Assisted Database Search for Sensitive and Accurate Peptide Identification. Mol. Cell. Proteomics 11, M111.010587 (2012).
30. Mao, Z. et al. Zero-shot de novo peptide sequencing with open posttranslational modification discovery. Nat. Biotechnol. (2026).
31. Liu, M.-Q. et al. pGlyco 2.0 enables precision N-glycoproteomics with comprehensive quality control and one-step mass spectrometry for intact glycopeptide identification. Nat. Commun. 8, 438 (2017).
32. Bateman, A. et al. UniProt: the Universal Protein Knowledgebase in 2025. Nucleic Acids Res. 53, D609–D617 (2025).
33. Desiere, F. The PeptideAtlas project. Nucleic Acids Res. 34, D655–D658 (2006).
34. Mudge, J. M. et al. Standardized annotation of translated open reading frames. Nat. Biotechnol. 40, 994–999 (2022).
35. Deutsch, E. W. et al. Expanding the human proteome with microproteins and peptideins. Nature 654, 813–825 (2026).
36. Nilsson, J. B., Greenbaum, J., Peters, B. & Nielsen, M. NetMHCpan-4.2: improved prediction of CD8+ epitopes by use of transfer learning and structural features. Front. Immunol. 16, 1616113 (2025).
37. Kessler, A. L. et al. Increased EThcD Efficiency on the Hybrid Orbitrap Excedion Pro Mass Analyzer Extends the Depth in Identification and Sequence Coverage of HLA Class I Immunopeptidomes. Mol. Cell. Proteomics 24, 101049 (2025).
指标
DOI：
Submission ID：
下载次数
已发布
如何引用
下载引用
利益冲突声明
作者声明无任何需要披露的利益冲突。
Copyright
本预印本的版权持有者为作者/资助方。
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.