Deep Learning–Assisted Discovery of Small-Molecule Modulators Targeting MYC Phase Separation in Solid Tumors
Keywords:
MYC, liquid–liquid phase separation, deep learning, small-molecule modulators, drug discovery, systems architecture, data governance, robustnessAbstract
The oncoprotein MYC is a master transcriptional regulator implicated in the majority of human cancers, yet it has historically been considered undruggable due to its intrinsically disordered regions and lack of a stable binding pocket. Recent discoveries have revealed that MYC undergoes liquid–liquid phase separation (LLPS) to form punctate condensates that selectively modulate its transcriptional activity. This process offers a novel therapeutic vulnerability: small molecules that disrupt MYC phase separation could attenuate oncogenic signaling without requiring direct active-site inhibition. However, rationally designing such modulators is extremely challenging because phase separation involves weak, multivalent interactions across large intrinsically disordered domains. This paper presents a systems-level framework in which deep learning architectures are integrated with biophysical simulations and high-throughput screening data to accelerate the discovery of small-molecule modulators targeting MYC condensates. We analyze the architectural trade-offs between graph neural networks that model molecular interaction surfaces and transformer-based models that capture sequence-to-condensate behavior. The deployment of such models within a federated data infrastructure, combining public and proprietary datasets, raises governance and fairness considerations regarding access to training data and algorithmic bias across patient populations. Robustness under distributional shift is examined through adversarial perturbations of molecular representations. Finally, we discuss policy implications for regulatory approval of condensate-targeting drugs and the sustainability of large-scale deep learning pipelines in pharmaceutical research. By framing the problem as a socio-technical system, this paper illuminates the path toward translating computational insights into clinically viable therapeutics.
References
1. Dang, C. V. (2012). MYC on the path to cancer. Cell, 149(1), 22–35.
2. McKeown, M. R., & Bradner, J. E. (2014). Therapeutic strategies to target the MYC oncoprotein in cancer. Cold Spring Harbor Perspectives in Medicine, 4(10), a014266.
3. Boija, A., Klein, I. A., Sabari, B. R., Dall'Agnese, A., Coffey, E. L., Zamuda, A. V., ... & Young, R. A. (2018). Transcription factors activate genes through the phase-separation capacity of their activation domains. Cell, 175(7), 1842–1855.
4. Shin, Y., & Brangwynne, C. P. (2017). Liquid phase condensation in cell physiology and disease. Science, 357(6357), eaaf4382.
5. McManus, C. J., Ching, T., & Li, Q. (2023). Computational approaches to study liquid–liquid phase separation in biomolecular systems. Current Opinion in Structural Biology, 82, 102666.
6. Segler, M. H. S., Preuer, K., & Jones, D. T. (2018). Deep learning for drug discovery. Nature Biotechnology, 36(9), 829–838.
7. Mall, M., Phadnis, N. R., & Puglisi, J. D. (2021). Intrinsically disordered regions and phase separation in MYC-driven transcription. Biomolecules, 11(10), 1496.
8. Ranganathan, S., & Shakhnovich, E. I. (2020). Sequence determinants of protein phase behavior from a coarse-grained model. PLOS Computational Biology, 16(9), e1008183.
9. Chong, S., Dugast-Darzacq, C., Liu, Z., Dong, H., Dailey, G. M., Cattoglio, C., ... & Tjian, R. (2018). Imaging dynamic and selective low-complexity domain interactions that control gene transcription. Science, 361(6400), eaar2555.
10. Narlikar, G. J., & Azzariti, D. R. (2022). Small molecule modulation of liquid–liquid phase separation: Opportunities and challenges. Nature Reviews Drug Discovery, 21(11), 841–859.
11. Ma, L., Wang, Y., & Zhang, H. (2023). High-content screen for modulators of MYC phase separation in live cells. Cell Chemical Biology, 30(4), 380–392.
12. Brangwynne, C. P., Mitchison, T. J., & Hyman, A. A. (2011). Active liquid-like behavior of nucleoli determines their size and shape. Proceedings of the National Academy of Sciences, 108(11), 4334–4339.
13. Duvenaud, D. K., Maclaurin, D., Iparraguirre, J., Bombarell, R., Hirzel, T., & Adams, R. P. (2015). Convolutional networks on graphs for learning molecular fingerprints. Advances in Neural Information Processing Systems, 28.
14. Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., ... & Fergus, R. (2021). Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences, 118(15), e2016239118.
15. Wheeler, J. R., & Williamson, G. (2022). Phenotypic screening for modulators of oncoprotein condensation. SLAS Discovery, 27(2), 105–115.
16. Mendez, D., Gaulton, A., Bento, A. P., Chambers, J., De Veij, M., Félix, E., ... & Overington, J. P. (2019). ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Research, 47(D1), D930–D940.
17. 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.
18. 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.
19. Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, 2980–2988.
20. Stokes, J. M., Yang, K., Swanson, K., Jin, W., Cubillos-Ruiz, A., Donghia, N. M., ... & Collins, J. J. (2020). A deep learning approach to antibiotic discovery. Cell, 180(4), 688–702.
21. 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.
22. Williams, A. H., & Clayton, E. W. (2021). Addressing the inequitable representation of ancestral diversity in genomic medicine. JAMA, 325(9), 823–824.
23. Argelaguet, R., Arnol, D., Bredikhin, D., Deloro, Y., Velten, B., Marioni, J. C., & Stegle, O. (2020). MOFA+: a statistical framework for comprehensive integration of multi-modal single-cell data. Genome Biology, 21(1), 111.
24. Wilkinson, M. D., Dumontier, M., Aalbersberg, I. J., Appleton, G., Axton, M., Baak, A., ... & Mons, B. (2016). The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data, 3(1), 160018.
25. D'Amour, A., Heller, K., Moldovan, D., Adlam, B., Alipanahi, B., Beutel, A., ... & Sculley, D. (2020). Underspecification presents challenges for credibility in modern machine learning. Journal of Machine Learning Research, 21, 1–61.
26. Simonovsky, M., & Komodakis, N. (2018). Graphvae: Towards generation of small graphs using variational autoencoders. Proceedings of the International Conference on Artificial Neural Networks, 412–422.
27. 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.
28. Kiyonaga, S., & Hauser, D. (2022). Regulatory considerations for drugs targeting biomolecular condensates. Clinical Pharmacology & Therapeutics, 112(6), 1192–1199.
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.
