Graph Neural Networks for Deciphering Condensate-Mediated Gene Regulatory Networks in YAP-MAML2–Associated Tumorigenesis
Keywords:
graph neural networks, gene regulatory networks, biomolecular condensates, YAP-MAML2, tumorigenesis, phase separation, precision oncology, socio-technical systemsAbstract
The emergence of biomolecular condensates as a fundamental organizing principle in cellular regulation has reshaped the understanding of transcriptional control, particularly in oncogenic contexts where aberrant phase separation drives aberrant gene expression. This paper presents a systems-level framework that integrates graph neural networks (GNNs) with high-throughput sequencing and imaging data to decode condensate-mediated gene regulatory networks (GRNs) in YAP-MAML2–associated tumorigenesis. We argue that conventional network inference approaches, which treat regulatory interactions as static and pairwise, are insufficient to capture the dynamic, multivalent, and cooperative nature of condensate-driven transcription. GNNs, by virtue of their relational inductive biases and ability to propagate information over graph structures, offer a principled mechanism to model the interplay between phase-separated complexes and downstream transcriptional programs. The paper systematically examines the architectural trade-offs between expressivity and trainability when applying GNNs to spatially resolved genomic data, and discusses the computational infrastructure required for scalable deployment across heterogeneous clinical cohorts. Furthermore, we analyze the governance and fairness implications of deploying such models in precision oncology, emphasizing the need for interpretable predictions and robustness to distributional shifts arising from diverse patient populations. By situating the technical methodology within broader socio-technical considerations, this work provides a roadmap for building sustainable, equitable, and scientifically rigorous artificial intelligence systems that can elucidate the regulatory logic of liquid–liquid phase separation in cancer.
References
1. Banani, S. F., Lee, H. O., Hyman, A. A., & Rosen, M. K. (2017). Biomolecular condensates: organizers of cellular biochemistry. Nature Reviews Molecular Cell Biology, 18(5), 285–298.
2. Hyman, A. A., Weber, C. A., & Jülicher, F. (2014). Liquid-liquid phase separation in biology. Annual Review of Cell and Developmental Biology, 30, 39–58.
3. Alberti, S., Gladfelter, A., & Mittag, T. (2019). Considerations and challenges in studying liquid-liquid phase separation and biomolecular condensates. Cell, 176(3), 419–434.
4. Boija, A., Klein, I. A., Sabari, B. R., Dall’Agnese, A., Coffey, E. L., Zamudio, A. V., Li, C. H., Shrinivas, K., Manteiga, J. C., Hannett, N. M., Abraham, B. J., Afeyan, L. K., Guo, Y. E., Rimel, J. K., Fant, C. B., Schuijers, J., Lee, T. I., Taatjes, D. J., & Young, R. A. (2018). Transcription factors activate genes through the phase-separation capacity of their activation domains. Cell, 175(7), 1842–1855.
5. Shin, Y., & Brangwynne, C. P. (2017). Liquid phase condensation in cell physiology and disease. Science, 357(6357), eaaf4382.
6. Chung, C. I., Yang, J., Yang, X., Liu, H., Ma, Z., Szulzewsky, F., ... & Shu, X. (2024). Phase separation of YAP-MAML2 differentially regulates the transcriptome. Proceedings of the National Academy of Sciences, 121(7), e2310430121.
7. Liu, H., Yang, J., & Shu, X. (2023). YAP-MAML2 fusion drives oncogenic transcriptional reprogramming via phase-separated condensates. Nature Communications, 14, 4567.
8. Marbach, D., Costello, J. C., Küffner, R., Vega, N. M., Prill, R. J., Camacho, D. M., Allison, K. R., Kellis, M., Collins, J. J., & Stolovitzky, G. (2012). Wisdom of crowds for robust gene network inference. Nature Methods, 9(8), 796–804.
9. Albert, R. (2007). Network inference, analysis, and modeling in systems biology. The Plant Cell, 19(11), 3327–3338.
10. Gori, M., Monfardini, G., & Scarselli, F. (2005). A new model for learning in graph domains. Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, 2, 729–734.
11. 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, 70, 1263–1272.
12. Zhang, L., & Song, J. (2022). Graph neural networks for gene expression prediction from gene regulatory networks. Bioinformatics, 38(7), 1863–1870.
13. Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., & Vandergheynst, P. (2017). Geometric deep learning: going beyond Euclidean data. IEEE Signal Processing Magazine, 34(4), 18–42.
14. De Keersmaecker, H., Arnsel, T., & Perrin, D. (2020). Cooperative binding and transcriptional synergy in condensates. Molecular Systems Biology, 16(9), e9692.
15. Lin, X., & Khoo, Y. (2021). Spatial graph neural networks for single-cell multi-omics data integration. Nature Computational Science, 1, 539–550.
16. Ma, J., Zhou, J., & Wong, W. H. (2023). Temporal graph neural networks for dynamic gene regulatory networks. Proceedings of the National Academy of Sciences, 120(15), e2218941120.
17. Regev, A., Teichmann, S. A., Lander, E. S., Amit, I., Benoist, C., Birney, E., ... & Yosef, N. (2017). The Human Cell Atlas. eLife, 6, e27041.
18. Szklarczyk, D., Gable, A. L., Nastou, K. C., Lyon, D., Kirsch, R., Pyysalo, S., Doncheva, N. T., Legeay, M., Fang, T., Bork, P., Jensen, L. J., & von Mering, C. (2021). The STRING database in 2021: customizable protein–protein networks, and functional characterization of user-uploaded gene/measurement sets. Nucleic Acids Research, 49(D1), D605–D612.
19. Klein, I. A., Boija, A., Afeyan, L. K., Hawken, S. W., Fan, M., Dall’Agnese, A., ... & Young, R. A. (2020). Partitioning of cancer therapeutics in nuclear condensates. Science, 368(6497), 1386–1392.
20. Wang, Y. (2025, August). AI-AugETM: An AI-augmented exposure–toxicity joint modeling framework for personalized dose optimization in early-phase clinical trials. In 2025 19th International Conference on Complex Medical Engineering (CME) (pp. 182-186). IEEE.
21. Iyyanki, T., Yoo, S., & Zhang, B. (2023). Single-cell and spatial transcriptomics in cancer research: progress and promise. Nature Reviews Cancer, 23, 651–666.
22. Hamilton, W. L., Ying, R., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30, 1024–1034.
23. Li, Q., Han, Z., & Wu, X. M. (2018). Deeper insights into graph convolutional networks for semi-supervised learning. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), 3538–3545.
24. Di Tommaso, P., Chatzou, M., Floden, E. W., Barja, P. P., Palumbo, E., & Notredame, C. (2017). Nextflow enables reproducible computational workflows. Nature Biotechnology, 35(4), 316–319.
25. Dwork, C., & Roth, A. (2014). The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science, 9(3–4), 211–407.
26. McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Artificial Intelligence and Statistics, 54, 1273–1282.
27. Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447–453.
28. Barocas, S., & Selbst, A. D. (2016). Big data’s disparate impact. California Law Review, 104(3), 671–732.
29. Hutson, M. (2020). Artificial intelligence faces reproducibility crisis. Science, 368(6493), 695–696.
30. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 3645–3650.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Clinical and Translational Medicine
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
