Integrating Graph Neural Networks and Molecular Interaction Data for Discovering Novel Therapeutic Targets in Autoimmune Disorders

Authors

  • Lilla Totino Department of Computer Science, George Mason University, Fairfax, VA, USA. Author

Keywords:

graph neural networks; molecular interaction networks; autoimmune disorders; therapeutic target discovery; uncertainty quantification; network medicine

Abstract

Autoimmune disorders present a difficult target-discovery problem because their molecular mechanisms are distributed across interacting proteins, pathways, and immune cell contexts rather than localized to a small number of isolated genes. Molecular interaction networks encode this distributed structure, but current computational approaches often treat target prioritization as a ranking problem over individual nodes, thereby underusing relational context, interaction type, and evidence reliability. This manuscript develops a methodological framework that integrates multi-relational molecular interaction data with graph neural networks to discover candidate therapeutic targets in autoimmune disorders. The framework represents genes, proteins, diseases, and drugs as a heterogeneous graph and uses relation-specific message passing with attention to learn context-dependent node embeddings. Heterogeneous evidence from protein interaction databases, pathway repositories, drug-target resources, and gene-set collections is fused through an edge-confidence function, allowing the model to distinguish high-quality from noisy or indirect interactions. Target discovery is formulated as probabilistic link prediction between molecular entities and disease phenotypes, trained with a discriminative objective and regularized to limit overfitting. Because candidate ranking is sensitive to model variance and incomplete interactome coverage, an uncertainty-aware ranking rule penalizes candidates with unstable ensemble predictions. The paper specifies the architectural components, objective functions, evidence-fusion logic, and evaluation conditions required for a reproducible target-discovery pipeline. The resulting analytical framework provides a disciplined route from heterogeneous molecular interaction data to experimentally testable autoimmune target hypotheses and clarifies where graph learning adds value beyond conventional network-proximity and differential-expression analyses.

References

1. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.

2. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. arXiv preprint arXiv:1710.10903.

3. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017). Neural message passing for quantum chemistry. In Proceedings of the 34th International Conference on Machine Learning (pp. 1263-1272). PMLR.

4. Zitnik, M., Agrawal, M., & Leskovec, J. (2018). Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13), i457-i466.

5. HerbSyner_Finder: a network community-based model for identifying synergistic combinations from herbal medicines and complex systems. Targetome. 2026;2(2):0-0. doi: 10.48130/targetome-0026-001

6. Barabási, A.-L., Gulbahce, N., & Loscalzo, J. (2011). Network medicine: a network-based approach to human disease. Nature Reviews Genetics, 12(1), 56-68.

7. Menche, J., Sharma, A., Kitsak, M., Ghiassian, S. D., Vidal, M., Loscalzo, J., & Barabási, A.-L. (2015). Uncovering disease-disease relationships through the incomplete interactome. Science, 347(6224), 1257601.

8. Goh, K.-I., Cusick, M. E., Valle, D., Childs, B., Vidal, M., & Barabási, A.-L. (2007). The human disease network. Proceedings of the National Academy of Sciences, 104(21), 8685-8690.

9. Öztürk, H., Özgür, A., & Ozkirimli, E. (2018). DeepDTA: deep drug-target binding affinity prediction. Bioinformatics, 34(17), i821-i829.

10. Luo, Y., Zhao, X., Zhou, J., Yang, J., Zhang, Y., Kuang, W., ... & Zeng, J. (2017). A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nature Communications, 8(1), 573.

11. Wishart, D. S., Feunang, Y. D., Guo, A. C., Lo, E. J., Marcu, A., Grant, J. R., ... & Assempour, N. (2018). DrugBank 5.0: a major update to the DrugBank database for 2018. Nucleic Acids Research, 46(D1), D1074-D1082.

12. Szklarczyk, D., Gable, A. L., Lyon, D., Junge, A., Wyder, S., Huerta-Cepas, J., ... & von Mering, C. (2019). STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets. Nucleic Acids Research, 47(D1), D607-D613.

13. Oughtred, R., Rust, J., Chang, C., Breitkreutz, B. J., Stark, C., Willems, A., ... & Tyers, M. (2021). The BioGRID database: A comprehensive biomedical resource of curated protein, genetic, and chemical interactions. Protein Science, 30(1), 187-200.

14. Kanehisa, M., & Goto, S. (2000). KEGG: Kyoto Encyclopedia of Genes and Genomes. Nucleic Acids Research, 28(1), 27-30.

15. Liberzon, A., Birger, C., Thorvaldsdóttir, H., Ghandi, M., Mesirov, J. P., & Tamayo, P. (2015). The Molecular Signatures Database (MSigDB) hallmark gene set collection. Cell Systems, 1(6), 417-425.

16. Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., ... & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open, 1, 57-81.

17. Tsubaki, M., Tomii, K., & Sese, J. (2019). Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences. Bioinformatics, 35(2), 309-318.

18. Pahikkala, T., Airola, A., Pietilä, S., Shakyawar, S., Szwajda, A., Tang, J., & Aittokallio, T. (2015). Toward more realistic drug-target interaction predictions. Briefings in Bioinformatics, 16(2), 325-337.

19. Bleakley, K., & Yamanishi, Y. (2009). Supervised prediction of drug-target interactions using bipartite local models. Bioinformatics, 25(18), 2397-2403.

20. Yamanishi, Y., Araki, M., Gutteridge, A., Honda, W., & Kanehisa, M. (2008). Prediction of drug-target interaction networks from the integration of chemical and genomic spaces. Bioinformatics, 24(13), i232-i240.

Downloads

Published

2026-09-26