Graph Neural Networks for Modeling MYC Phase-Separation Regulatory Networks in Cancer Transcriptomics
Keywords:
graph neural networks, MYC phase separation, cancer transcriptomics, regulatory networks, systems biology, machine learning governance, robustness, fairness, precision oncologyAbstract
The emergence of phase separation as a fundamental organizing principle in transcriptional regulation has opened new frontiers in cancer biology, particularly concerning the MYC oncoprotein. MYC phase separation concentrates transcriptional cofactors and RNA polymerase II into condensates that selectively modulate target gene expression, yet the underlying regulatory network exhibits complex, non-linear interactions that are poorly captured by traditional statistical models. This paper proposes a computational framework based on graph neural networks (GNNs) to represent and infer the dynamics of MYC phase-separation regulatory networks using cancer transcriptomic data. We argue that GNNs offer structural advantages over conventional neural architectures because they can explicitly encode the spatial and functional connectivity among biomolecular condensates, chromatin loci, and transcription factor binding sites. The discussion emphasizes systemic trade-offs in architectural design, including the choice between inductive and transductive learning paradigms, the integration of multi-omics data streams, and the governance of model interpretability in clinical settings. Infrastructure challenges such as data heterogeneity, missing node attributes, and the need for scalable training on large-scale single-cell datasets are examined. Robustness to distributional shifts across cancer subtypes and fairness considerations when deploying such models across diverse patient populations are analyzed within a policy-oriented framework. A comparative case illustration is drawn from analogous applications of GNNs to protein interaction networks and drug repurposing. The paper concludes with forward-looking perspectives on sustainable model deployment, privacy-preserving federated learning architectures, and the regulatory implications of using black-box graph models in precision oncology. By synthesizing concepts from computational biology, complex systems theory, and socio-technical infrastructure, this work provides a blueprint for integrating phase-separation biology with graph-based machine learning in cancer research.
References
1. Boija, A., Klein, I. A., Sabari, B. R., Dall’Agnese, A., Coffey, E. L., Zamudio, A. V., ... & Young, R. A. (2018). Transcription factors activate genes through the phase-separation capacity of their activation domains. Cell, 175(7), 1842-1855.
2. Shin, Y., & Brangwynne, C. P. (2017). Liquid phase condensation in cell physiology and disease. Science, 357(6357), eaaf4382.
3. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. Proceedings of the 5th International Conference on Learning Representations (ICLR).
4. Dang, C. V. (2012). MYC on the path to cancer. Cell, 149(1), 22-35.
5. Sabari, B. R., Dall’Agnese, A., Boija, A., Klein, I. A., Coffey, E. L., Shrinivas, K., ... & Young, R. A. (2018). Coactivator condensation at super-enhancers links phase separation and gene control. Science, 361(6400), eaar3958.
6. Yang, J., Chung, C. I., Koach, J., Liu, H., Navalkar, A., He, H., ... & Shu, X. (2024). MYC phase separation selectively modulates the transcriptome. Nature Structural & Molecular Biology, 31(10), 1567-1579.
7. Berry, J., Brangwynne, C. P., & Haataja, M. (2018). Physical principles of intracellular organization via active and passive phase transitions. Reports on Progress in Physics, 81(4), 046601.
8. van Mierlo, G., Jansen, J. R. G., Wang, J., Poser, I., van Hees, L., & Vermeulen, M. (2021). Predicting protein phase separation from sequence. Nature Methods, 18(8), 888-894.
9. Zhang, Z., Cui, P., & Zhu, W. (2020). Deep learning on graphs: A survey. IEEE Transactions on Knowledge and Data Engineering, 34(1), 249-274.
10. Zitnik, M., Agrawal, M., & Leskovec, J. (2018). Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13), i457-i466.
11. Ritchie, M. D., & Moore, J. H. (2020). Graph convolutional neural networks for prediction of transcription factor target genes. Proceedings of the 11th ACM Conference on Bioinformatics, Computational Biology and Health Informatics, 243-252.
12. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. Proceedings of the 6th International Conference on Learning Representations (ICLR).
13. Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30, 1024-1034.
14. Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018). Modeling relational data with graph convolutional networks. Proceedings of the 15th European Semantic Web Conference, 593-607.
15. Ying, R., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. (2019). GNNExplainer: Generating explanations for graph neural networks. Advances in Neural Information Processing Systems, 32, 9240-9251.
16. Chen, J., Zhu, J., & Song, L. (2018). Stochastic training of graph convolutional networks with variance reduction. Proceedings of the 35th International Conference on Machine Learning, 942-950.
17. Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50-60.
18. Zugner, D., & Günnemann, S. (2019). Adversarial attacks on graph neural networks via meta learning. Proceedings of the 7th International Conference on Learning Representations (ICLR).
19. Martin, A. R., Kanai, M., Kamatani, Y., Okada, Y., Neale, B. M., & Daly, M. J. (2019). Clinical use of current polygenic risk scores may exacerbate health disparities. Nature Genetics, 51(4), 584-591.
20. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017). Neural message passing for quantum chemistry. Proceedings of the 34th International Conference on Machine Learning, 1263-1272.
21. Lelarge, M., & Millington, J. T. (2020). Overlapping community detection in large networks using non-negative matrix factorization. Journal of Complex Networks, 8(2), cnaa010.
22. Polino, A., Pascanu, R., & Alistarh, D. (2018). Model compression via distillation and quantization. Proceedings of the 6th International Conference on Learning Representations (ICLR).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Bioinformatics Insights and Analytics
This work is licensed under a Creative Commons Attribution 4.0 International License.
