Abstract
Lysine methylation is a dynamic and reversible post-translational modification of proteins carried out by lysine methyltransferase enzymes. The role of this modification in epigenetics and gene regulation is relatively well understood, but our understanding of the extent and the role of lysine methylation of non-histone substrates remains somewhat limited. Several lysine methyltransferases which methylate non-histone substrates are overexpressed in a number of cancers and are believed to be key drivers of cancer progression. There is great incentive to identify the lysine methylome, as this is a key step in identifying drug targets. While numerous computational models have been developed in the last decade to identify novel lysine methylation sites, the accuracy of these models has been modest, leaving much room for improvement. In this work, we leverage the most recent advancements in deep learning and present a transformer-based model for lysine methylation site prediction which achieves state-of-the-art accuracy. In addition, we show that other post-translational modifications of lysine are informative and that multitask learning is an effective way to integrate this prior knowledge into our lysine methylation site predictor, MethylSight 2.0. Finally, we validate our model by means of parallel reaction monitoring mass spectrometry experiments and identify 68 novel lysine methylation sites. This work constitutes another contribution towards the completion of a comprehensive map of the lysine methylome by providing a revised estimate of its extent to approximately 155,000 sites. Of those, MethylSight 2.0 is expected to correctly detect ~ 47,000, which is substantially more than expected with competing methods, which we show to be less sensitive on a subset of experimentally validated novel methylation sites. We foresee that MethylSight 2.0, whose performance significantly surpasses that of competing models, will facilitate the discovery of a large number of novel methylation sites.
Data availability
The source code (models and model weights) required to run MethylSight 2.0 and the associated datasets are available on GitHub ([https://github.com/GreenCUBIC/MethylSight2.git](https:/github.com/GreenCUBIC/MethylSight2.git)).
References
Biggar, K. K. & Li, S. S. C. Non-Histone protein methylation as a regulator of cellular signalling and function. Nat. Rev. Mol. Cell Biol. 16, 5–17 (2015).
Carlson, S. M. & Gozani, O. Nonhistone lysine methylation in the regulation of cancer pathways. Cold Spring Harbor Perspect. Med. 6, a26435 (2016).
Han, D. et al. Lysine methylation of transcription factors in cancer. Cell Death Dis. 10, 290 (2019).
Huang, M. et al. Methylation modification of Non-Histone proteins in breast cancer: an emerging targeted therapeutic strategy. Pharmacol. Res. 208, 107354 (2024).
Straining, R., Eighmy, W. & Tazemetostat EZH2 inhibitor. J. Adv. Practitioner Oncol. 13, 158 (2022).
Feoli, A. et al. Lysine methyltransferase inhibitors: where we are now. RSC Chem. Biology. 3, 359–406 (2022).
Xu, K. et al. EZH2 oncogenic activity in Castration-Resistant prostate cancer cells is polycombindependent. Science 338, 1465–1469 (2012).
Kim, E. et al. Phosphorylation of EZH2 activates STAT3 signaling via STAT3 methylation and promotes tumorigenicity of glioblastoma Stem-like cells. Cancer Cell. 23, 839–852 (2013).
Lanouette, S., Mongeon, V., Figeys, D. & Couture, J. F. The functional diversity of protein lysine methylation. Mol. Syst. Biol. 10, 724 (2014).
Chen, H., Xue, Y., Huang, N., Yao, X. & Sun, Z. MeMo: A web tool for prediction of protein methylation modifications. Nucleic Acids Res. 34, W249–W253 (2006).
Qiu, W. R., Xiao, X., Lin, W. Z. & Chou, K. C. iMethyl-PseAAC: Identification of Protein Methylation Sites via a Pseudo Amino Acid Composition Approach. BioMed Research International 947416 (2014). (2014).
Kawashima, S. et al. AAindex: amino acid index Database, progress report 2008. Nucleic Acids Res. 36, D202–205 (2008).
Deng, W. et al. Computational prediction of methylation types of covalently modified lysine and arginine residues in proteins. Brief. Bioinform. 18, 647–658 (2017).
Zheng, W., Wuyun, Q., Cheng, M., Hu, G. & Zhang, Y. Two-Level protein methylation prediction using structure Model-Based features. Sci. Rep. 10, 6008 (2020).
Biggar, K. K. et al. Proteome-Wide prediction of lysine methylation leads to identification of H2BK43 methylation and outlines the potential Methyllysine proteome. Cell. Rep. 32, 107896 (2020).
Ruiz-Blanco, Y. B., Paz, W., Green, J., Marrero-Ponce, Y. & ProtDCal A program to compute GeneralPurpose-Numerical descriptors for sequences and 3D-structures of proteins. BMC Bioinform. 16, 162 (2015).
Spadaro, A., Sharma, A. & Dehzangi, I. Predicting lysine methylation sites using a convolutional neural network. Methods (San Diego Calif). 226, 127–132 (2024).
Peng, F. Z. et al. PTM-Mamba: A PTM-aware protein Language model with bidirectional gated Mamba blocks. Nat. Methods. 22, 945–949 (2025).
Bepler, T. & Berger, B. Learning the protein language: Evolution, Structure, and function. Cell. Syst. 12, 654–669e3 (2021).
Hornbeck, P. V. et al. PhosphoSitePlus, : Mutations, PTMs and Recalibrations. Nucleic Acids Research 43, D512–520 (2015). (2014).
Li, A., Deng, Y., Tan, Y. & Chen, M. A. Transfer Learning-Based approach for lysine propionylation prediction. Frontiers Physiology. 12, 658633 (2021).
Lukinović, V., Casanova, A. G., Roth, G. S., Chuffart, F. & Reynoird, N. Lysine methyltransferases signaling: histones are just the tip of the iceberg. Curr. Protein Pept. Sci. 21, 655–674 (2020).
Narita, T., Weinert, B. T. & Choudhary, C. Functions and mechanisms of Non-Histone protein acetylation. Nat. Rev. Mol. Cell Biol. 20, 156–174 (2019).
Geiss-Friedlander, R. & Melchior, F. Concepts in sumoylation: A decade on. Nat. Rev. Mol. Cell Biol. 8, 947–956 (2007).
Damgaard, R. B. The ubiquitin system: from cell signalling to disease biology and new therapeutic opportunities. Cell. Death Differ. 28, 423–426 (2021).
Shrestha, P., Kandel, J., Tayara, H. & Chong, K. T. DL-SPhos: prediction of Serine phosphorylation sites using transformer Language model. Comput. Biol. Med. 169, 107925 (2024).
Xue, Y. et al. GPS: A comprehensive www server for phosphorylation sites prediction. Nucleic Acids Res. 33, W184–W187 (2005).
Shi, S. P. et al. PMeS: prediction of methylation sites based on enhanced feature encoding scheme. PLOS One. 7, e38772 (2012).
Shi, Y., Guo, Y., Hu, Y. & Li, M. Position-Specific prediction of methylation sites from sequence conservation based on information theory. Sci. Rep. 5, 12403 (2015).
Petersen, B., Petersen, T., Andersen, P., Nielsen, M. & Lundegaard, C. A generic method for assignment of reliability scores applied to solvent accessibility predictions. BMC Struct. Biol. 9, 51 (2009).
Høie, M. H. et al. NetSurfP-3.0: accurate and fast prediction of protein structural features by protein Language models and deep learning. Nucleic Acids Res. 50, W510–W515 (2022).
Fu, L., Niu, B., Zhu, Z., Wu, S. & Li, W. CD-HIT: accelerated for clustering the next-Generation sequencing data. Bioinf. (Oxford England). 28, 3150–3152 (2012).
Lin, Z. et al. Evolutionary-Scale prediction of Atomic-Level protein structure with a Language model. Science 379, 1123–1130 (2023).
Avraham, O., Tsaban, T., Ben-Aharon, Z. & Tsaban, L. Schueler-Furman, O. protein Language models can capture protein quaternary state. BMC Bioinform. 24, 433 (2023).
Hao, X. & Fan, L. ProtT5 and random Forests-Based viscosity prediction method for therapeutic mAbs. Eur. J. Pharm. Sci. 194, 106705 (2024).
Schmirler, R., Heinzinger, M. & Rost, B. Fine-Tuning protein Language models boosts predictions across diverse tasks. Nat. Commun. 15, 7407 (2024).
Elnaggar, A. et al. Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling. (2023).
Brixi, G. et al. SaLT&PepPr is an Interface-Predicting Language model for designing Peptide-Guided protein degraders. Commun. Biology. 6, 1081 (2023).
Bhat, S. et al. De Novo design of peptide binders to conformationally diverse targets with contrastive Language modeling. Sci. Adv. 11, eadr8638 (2025).
Chen, L. T. et al. Target Sequence-Conditioned Design of Peptide Binders Using Masked Language Modeling. Nature Biotechnology 1–9 Preprint at (2025). https://www.nature.com/articles/s41587-02502761-2
Elnaggar, A. 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 7112–7127 Preprint at (2021). https://ieeexplore.ieee.org/document/9477085/
Akiba, T. et al. A Next-generation Hyperparameter Optimization Framework. in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2623–2631Association for Computing Machinery, New York, NY, USA, Preprint at (2019). https://doi.org/10.1145/3292500.3330701
Paszke, A. et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. Preprint at (2019). https://arxiv.org/abs/1912.01703
Kingma, D. P., Ba, J. & Adam A Method for Stochastic Optimization. Preprint at (2017). http://arxiv.org/abs/1412.6980
Vaswani, A. et al. Attention Is All You Need. (2017).
The UniProt Consortium. UniProt: the universal protein knowledgebase in 2025. Nucleic Acids Res. 53, D609–D617 (2025).
Berryhill, C. A. et al. Global lysine methylome profiling using systematically characterized affinity reagents. Sci. Rep. 13, 377 (2023).
Levitsky, L. I., Klein, J. A., Ivanov, M. V. & Gorshkov, M. V. Pyteomics 4.0: five years of development of a python proteomics framework. J. Proteome Res. 18, 709–714 (2018).
MacLean, B. et al. Skyline: an open source document editor for creating and analyzing targeted proteomics experiments. Bioinformatics 26, 966–968 (2010).
Charih, F., Green, J. R. & Biggar, K. K. Using machine learning and targeted mass spectrometry to explore the Methyl-Lys proteome. STAR. Protocols. 1, 100135 (2020).
Fournier, Q. et al. Protein Language Models: Is Scaling Necessary? Preprint at (2024). https://doi.org/10.1101/2024.09.23.614603v1
Cheng, X. et al. Training Compute-Optimal Protein Language Models. Preprint at http://biorxiv.org/lookup/doi/ (2024). https://doi.org/10.1101/2024.06.06.597716
Leutert, M., Entwisle, S. W. & Villén, J. Decoding Post-Translational modification crosstalk with proteomics. Mol. Cell. Proteomics: MCP. 20, 100129 (2021).
Shukri, A. H., Lukinović, V., Charih, F. & Biggar, K. K. Unraveling the battle for lysine: A review of the competition among Post-Translational modifications. Biochim. Et Biophys. Acta (BBA) - Gene Regul. Mech. 1866, 194990 (2023).
Lee, J. M., Hammarén, H. M., Savitski, M. M. & Baek, S. H. Control of protein stability by Post-Translational modifications. Nat. Commun. 14, 201 (2023).
Hamey, J. J., Wienert, B., Quinlan, K. G. R. & Wilkins, M. R. METTL21B is a novel human lysine methyltransferase of translation elongation factor 1A: discovery by CRISPR/Cas9 knockout. Mol. Cell. Proteom. 16, 2229–2242 (2017).
Francis, J. W. et al. FAM86A methylation of eEF2 links mRNA translation elongation to tumorigenesis. Mol. Cell. 84, 1753–1763e7 (2024).
Michail, C., Rodrigues Lima, F., Viguier, M. & Deshayes, F. Structure and function of the lysine methyltransferase SETD2 in cancer: from histones to cytoskeleton. Neoplasia (New York N Y). 59, 101090 (2025).
Park, I. Y. et al. Dual Chromatin and Cytoskeletal Remodeling by SETD2. Cell 166, 950–962 (2016).
Li, L. X. & Li, X. Epigenetically mediated ciliogenesis and cell cycle Regulation, and their translational potential. Cells 10, 1662 (2021).
Casanova, A. G. et al. Cytoskeleton remodeling induced by SMYD2 methyltransferase drives breast cancer metastasis. Cell. Discovery. 10, 1–22 (2024).
Kanehisa, M., Furumichi, M., Sato, Y., Matsuura, Y. & Ishiguro-Watanabe, M. KEGG: biological systems database as a model of the real world. Nucleic Acids Res. 53, D672–D677 (2025).
Sasikumar, A. N., Perez, W. B. & Kinzy, T. G. The many roles of the eukaryotic elongation factor 1 complex. WIREs RNA. 3, 543–555 (2012).
Olarewaju, O., Ortiz, P. A., Chowdhury, W. Q., Chatterjee, I. & Kinzy, T. G. The translation elongation factor eEF1B plays a role in the oxidative stress response pathway. RNA Biol. 1, 89–94 (2004).
Negrutskii, B. S. et al. The eEF1 family of mammalian translation elongation factors. BBA Adv. 3, 100067 (2023).
Vanwetswinkel, S. et al. Solution structure of the 162 residue C-terminal domain of human elongation factor 1Bγ. J. Biol. Chem. 278, 43443–43451 (2003).
Achilonu, I. et al. An update on the biophysical character of the human eukaryotic elongation factor 1 beta: perspectives from interaction with elongation factor 1 gamma. J. Mol. Recognit. 31, e2708 (2018).
Olatona, O. A., Choudhury, S. R., Kresman, R. & Heckman, C. A. Candidate proteins interacting with cytoskeleton in cells from the basal airway epithelium in vitro. Front. Mol. Biosci. 11, 1423503 (2024).
Mimori, K., Mori, M., Tanaka, S., Akiyoshi, T. & Sugimachi, K. The overexpression of elongation factor 1 gamma mRNA in gastric carcinoma. Cancer 75, 1446–1449 (1995).
Chi, K., Jones, D. V. & Frazier, M. L. Expression of an elongation factor 1 Gamma-Related sequence in adenocarcinomas of the colon. Gastroenterology 103, 98–102 (1992).
Lew, Y. et al. Expression of elongation Factor-1 Gamma-Related sequence in human pancreatic cancer. Pancreas 7, 144–152 (1992).
Kim, H. Y. & Hong, S. Multi-Faceted roles of DNAJB protein in cancer metastasis and clinical implications. Int. J. Mol. Sci. 23, 14970 (2022).
Liu, P., Zu, F., Chen, H., Yin, X. & Tan, X. Exosomal DNAJB11 promotes the development of pancreatic cancer by modulating the EGFR/MAPK pathway. Cell. Mol. Biol. Lett. 27, 87 (2022).
Pan, J., Cao, D. & Gong, J. The Endoplasmic reticulum Co-Chaperone ERdj3/DNAJB11 promotes hepatocellular carcinoma progression through suppressing AATZ degradation. Future Oncol. 14, 3001–3013 (2018).
Sun, R. et al. DNAJB11 predicts a poor prognosis and is associated with immune infiltration in thyroid carcinoma: A bioinformatics analysis. J. Int. Med. Res. 49, 03000605211053722 (2021).
Chen, H. Y. et al. ATM-mediated Co-Chaperone DNAJB11 phosphorylation facilitates α-Synuclein folding upon DNA Double-Stranded breaks. NAR Mol. Med. 1, ugae7 (2024).
Sondka, Z. et al. COSMIC: A curated database of somatic variants and clinical data for cancer. Nucleic Acids Res. 52, D1210–D1217 (2024).
Sakata-Yanagimoto, M. et al. Somatic RHOA mutation in angioimmunoblastic T cell lymphoma. Nat. Genet. 46, 171–175 (2014).
Ju, Z., Cao, J. Z. & Gu, H. iLM-2L: A Two-Level predictor for identifying protein lysine methylation sites and their methylation degrees by incorporating K-gap amino acid pairs into Chou׳s general PseAAC. J. Theor. Biol. 385, 50–57 (2015).
Funding
This research was funded by the National Science and Engineering Research Council (NSERC) Canada Discovery grant awarded to Kyle K. Biggar (RGPIN-2023-04651) and James R. Green (RGPIN-2021-04184).
Author information
Authors and Affiliations
Contributions
**François Charih: ** Conceptualization, Methodology, Software, Investigation, Formal analysis, Data Curation, Visualization, Writing - Original Draft, **Mullen Boulter: ** Formal analysis, **Kyle K. Biggar: ** Conceptualization, Resources, Formal analysis, Writing - Review & Editing, Funding acquisition, **James R. Green: ** Conceptualization, Writing - Review & Editing, Funding acquisitionAll authors approved of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Charih, F., Boulter, M., Biggar, K.K. et al. Leveraging learned representations and multitask learning for lysine methylation site discovery. Sci Rep (2026). https://doi.org/10.1038/s41598-026-39136-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-39136-9
