Gated graph neural network-based features for epigenetic target detection

Fengwei Jing; Yuxuan Liu; Xinhui Si; Yishu Wang; Fengwei Jing; Yuxuan Liu; Xinhui Si; Yishu Wang

doi:10.3934/era.2026005

Electronic Research Archive

2026, Volume 34, Issue 1: 69-89. doi: 10.3934/era.2026005

Previous Article Next Article

Research article Special Issues

Gated graph neural network-based features for epigenetic target detection

1.
National Engineering Research Center for Advanced Rolling and Intelligent Manufacturing, University of Science and Technology Beijing, Beijing 100083, China
2.
School of Mathematics and Statistics, University of Science and Technology Beijing, Beijing 100083, China

Received: 20 September 2025 Revised: 12 November 2025 Accepted: 24 November 2025 Published: 29 December 2025

Epigenetics refers to genetic modifications that cause changes in gene expression and are not encoded in DNA. These modifications, including histone, DNA, and RNA, as well as miRNA, are closely related to oncology research and have the potential to influence the treatment of metabolic, neurological, inflammatory, and cardiovascular diseases. In cancer treatment, targeting abnormal epigenetic regulation can be achieved through inhibition of abnormal DNA methylation and histone methylation and acetylation. However, the discovery of efficient epigenetic drugs often requires substantial time and resources. To aid in drug research, we propose an extraction method of molecule features based on a gated graph neural network (GGNN) and integrate four supervised classifiers to predict epigenetic targets in screened chemogenomic datasets. Our GGNN+XGBoost integrated model achieves an overall accuracy of 0.8158, with accuracy increasing to 0.981 in certain target datasets. This approach offers a promising solution for predicting epigenetic targets, with implications for cancer treatment and other diseases. Furthermore, our method showcases the potential of utilizing big datasets and predictive models to expedite epigenetic drug discovery.
- GGNN,
- XGBoost,
- epigenetic targets,
- supervised classifiers,
- drug discovery
Citation: Fengwei Jing, Yuxuan Liu, Xinhui Si, Yishu Wang. Gated graph neural network-based features for epigenetic target detection[J]. Electronic Research Archive, 2026, 34(1): 69-89. doi: 10.3934/era.2026005

Related Papers:

Abstract

Epigenetics refers to genetic modifications that cause changes in gene expression and are not encoded in DNA. These modifications, including histone, DNA, and RNA, as well as miRNA, are closely related to oncology research and have the potential to influence the treatment of metabolic, neurological, inflammatory, and cardiovascular diseases. In cancer treatment, targeting abnormal epigenetic regulation can be achieved through inhibition of abnormal DNA methylation and histone methylation and acetylation. However, the discovery of efficient epigenetic drugs often requires substantial time and resources. To aid in drug research, we propose an extraction method of molecule features based on a gated graph neural network (GGNN) and integrate four supervised classifiers to predict epigenetic targets in screened chemogenomic datasets. Our GGNN+XGBoost integrated model achieves an overall accuracy of 0.8158, with accuracy increasing to 0.981 in certain target datasets. This approach offers a promising solution for predicting epigenetic targets, with implications for cancer treatment and other diseases. Furthermore, our method showcases the potential of utilizing big datasets and predictive models to expedite epigenetic drug discovery.

References

[1]	C. H. Waddington, The epigenotype, Int. J. Epidemiol., 41 (2012), 10–13. https://doi.org/10.1093/ije/dyr184
[2]	M. Esteller, Molecular origins of cancer: Epigenetics in cancer, N. Engl. J. Med., 358 (2008), 1148–1159. https://doi.org/10.1056/NEJMra072067 doi: 10.1056/NEJMra072067
[3]	V. Januar, R. Saffery, J. Ryan, Epigenetics and depressive disorders: A review of current progress and future directions, Int. J. Epidemiol., 44 (2015), 1364–1387. https://doi.org/10.1093/ije/dyu273 doi: 10.1093/ije/dyu273
[4]	C. Küçükali, M. Kürtüncü, A. Çoban, M. Çebi, E. Tüzün, Epigenetics of multiple sclerosis: An updated review, NeuroMol. Med., 17 (2015), 83–96. https://doi.org/10.1007/s12017-014-8298-6 doi: 10.1007/s12017-014-8298-6
[5]	M. Brindisi, A. Saraswati, S. Brogi, S.Gemma, S. Butini, G. Campiani, Old but gold: Tracking the new guise of histone deacetylase 6 (HDAC6) enzyme as a biomarker and therapeutic target in rare diseases, J. Med. Chem., 63 (2019), 23–39. https://doi.org/10.1021/acs.jmedchem.9b00924 doi: 10.1021/acs.jmedchem.9b00924
[6]	A. Lera, A. Ganesan, Two-hit wonders: The expanding universe of multitargeting epigenetic agents, Curr. Opin. Chem. Biol., 57 (2020), 135–154. https://doi.org/10.1016/j.cbpa.2020.05.009 doi: 10.1016/j.cbpa.2020.05.009
[7]	U. Norinder, J. Naveja, E. López-López, D. Mucs, J. L. Medina-Franco, Conformal prediction of HDAC inhibitors, SAR QSAR Environ. Res., 30 (2019), 265–277. https://doi.org/10.1080/1062936X.2019.1591503 doi: 10.1080/1062936X.2019.1591503
[8]	P. Filippakopoulos, J. Qi, S. Picaud, Y. Shen, W. B. Smith, O. Fedorov, et al., Selective inhibition of BET bromodomains, Nature, 468 (2010), 1067–1073. https://doi.org/10.1038/nature09504 doi: 10.1038/nature09504
[9]	C. Allis, T. Jenuwein, The molecular hallmarks of epigenetic control, Nat. Rev. Genet., 17 (2016), 487–500. https://doi.org/10.1038/nrg.2016.59 doi: 10.1038/nrg.2016.59
[10]	K. Cao, G. Wang, W. Li, L. Zhang, R. Wang, Y. Huang, et al., Histone deacetylase inhibitors prevent activation-induced cell death and promote anti-tumor immunity, Oncogene, 34 (2015), 5960–5970. https://doi.org/10.1038/onc.2015.46 doi: 10.1038/onc.2015.46
[11]	M. Glozak, N. Sengupta, X. Zhang, E. Seto, Acetylation and deacetylation of non-histone proteins, Gene, 363 (2005), 15–23. https://doi.org/10.1016/j.gene.2005.09.010 doi: 10.1016/j.gene.2005.09.010
[12]	J. Naveja, J. Medina-Franco, Insights from pharmacological similarity of epigenetic targets in epipolypharmacology, Drug Discovery Today, 23 (2018), 141–150. https://doi.org/10.1016/j.drudis.2017.10.006 doi: 10.1016/j.drudis.2017.10.006
[13]	J. Nanda, R. Kumar, G. Raghava, dbEM: A database of epigenetic modifiers curated from cancerous and normal genomes, Sci. Rep., 6 (2016), 19340. https://doi.org/10.1038/srep19340 doi: 10.1038/srep19340
[14]	Y. Medvedeva, A. Lennartsson, R. Ehsani, I. V. Kulakovskiy, I. E. Vorontsov, P. Panahandeh, et al., EpiFactors: A comprehensive database of human epigenetic factors and complexes, Database (Oxford), 2015 (2015), bav067. https://doi.org/10.1093/database/bav067 doi: 10.1093/database/bav067
[15]	S. Loharch, I. Bhutani, K. Jain, P. Gupta, D. K. Sahoo, R. Parkesh, EpiDBase: A manually curated database for small molecule modulators of epigenetic landscape, Database (Oxford), 2015 (2015), bav013. https://doi.org/10.1093/database/bav013 doi: 10.1093/database/bav013
[16]	N. Sánchez-Cruz, J. Medina-Franco, Epigenetic target fishing with accurate machine learning models, J. Med. Chem., 64 (2021), 8208–8220. https://doi.org/10.1021/acs.jmedchem.1c00020 doi: 10.1021/acs.jmedchem.1c00020
[17]	H. Li, K. Sze, G. Lu, P. J. Ballester, Machine-learning scoring functions for structure-based drug lead optimization, WIREs Comput. Mol. Sci., 10 (2020), e1465. https://doi.org/10.1002/wcms.1465 doi: 10.1002/wcms.1465
[18]	F. Miljkovic, R. Rodriguez-Perez, J. Bajorath, Machine learning models for accurate prediction of kinase inhibitors with different binding modes, J. Med. Chem., 63 (2019), 8738–8748. https://doi.org/10.1021/acs.jmedchem.9b00867 doi: 10.1021/acs.jmedchem.9b00867
[19]	Y. Lo, S. Rensi, W. Torng, R. B. Altman, Machine learning in chemoinformatics and drug discovery, Drug Discovery Today, 23 (2018), 1538–1546. https://doi.org/10.1016/j.drudis.2018.05.010 doi: 10.1016/j.drudis.2018.05.010
[20]	A. Abgeena, S. Garg, A novel convolution bi-directional gated recurrent unit neural network for emotion recognition in multichannel electroencephalogram signals, Technol. Health Care, 31 (2023), 1215–1234. https://doi.org/10.3233/THC-220458 doi: 10.3233/THC-220458
[21]	P. Gong, C. Zhang, M. Chen, Deep learning for toxicity and disease prediction, Front. Genet., 11 (2020), 175. https://doi.org/10.3389/fgene.2020.00175 doi: 10.3389/fgene.2020.00175
[22]	A. Lavecchia, Deep learning in drug discovery: Opportunities, challenges and future prospects, Drug Discovery Today, 24 (2019), 2017–2032. https://doi.org/10.1016/j.drudis.2019.07.006 doi: 10.1016/j.drudis.2019.07.006
[23]	R. Dey, F. Salem, Gate-variants of gated recurrent unit (GRU) neural networks, in 2017 IEEE 60th International Midwest Symposium on Circuits and Systems, IEEE, (2017), 1597–1600. https://doi.org/10.1109/MWSCAS.2017.8053243
[24]	L. Breiman, Random Forests, Mach. Learn., 45 (2001), 5–32. https://doi.org/10.1023/A: 1010933404324
[25]	K. Hsu, H. Gupta, S. Sorooshian, Artificial neural network modeling of the rainfall-runoff process, Water Resour. Res., 31 (1995), 2517–2530. https://doi.org/10.1029/95WR01955 doi: 10.1029/95WR01955
[26]	J. Friedman, T. Hastie, R. Tibshirani, Additive logistic regression: A statistical view of boosting (with discussion and a rejoinder by the authors), Ann. Statist., 28 (2000), 337–407. https://doi.org/10.1214/aos/1016218223 doi: 10.1214/aos/1016218223
[27]	S. Kim, J. Chen, T. Cheng, A. Gindulyte, J. He, S. He, et al., PubChem 2019 update: Improved access to chemical data, Nucleic Acids Res., 47 (2019), D1102–D1109. https://doi.org/10.1093/nar/gky1033 doi: 10.1093/nar/gky1033
[28]	Z. Sessions, N. Sánchez-Cruz, F. Prieto-Martínez, V. M. Alves, H. P. Santos Jr., E. Muratov, et al., Recent progress on cheminformatics approaches to epigenetic drug discovery, Drug Discovery Today, 25 (2020), 2268–2276. https://doi.org/10.1016/j.drudis.2020.09.021 doi: 10.1016/j.drudis.2020.09.021
[29]	T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, (2016), 785–794. https://doi.org/10.1145/2939672.2939785
[30]	K. Yang, K. Swanson, W. Jin, C. Coley, P. Elden, H. Gao, et al., Analyzing learned molecular representations for property prediction, J. Chem. Inf. Model., 59 (2019), 3370–3388. https://doi.org/10.1021/acs.jcim.9b00237 doi: 10.1021/acs.jcim.9b00237
[31]	J. Durant, B. Leland, D. Henry, J. G. Nourse, Reoptimization of MDL keys for use in drug discovery, J. Chem. Inf. Comput. Sci., 42 (2002), 1273–1280. https://doi.org/10.1021/ci010132r doi: 10.1021/ci010132r
[32]	S. Bagheri, M. Rahban, F. Bostanian, F. Esmaeilzadeh, A. Bagherabadi, S. Zolghadri, et al., Targeting protein kinases and epigenetic control as combinatorial therapy options for advanced prostate cancer treatment, Pharmaceutics, 14 (2022), 515. https://doi.org/10.3390/pharmaceutics14030515 doi: 10.3390/pharmaceutics14030515

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)