Causal Deep Learning for Drug–Gene–Disease Interaction Discovery
DOI:
https://doi.org/10.63282/3050-922X.ICAILLMBA-108Keywords:
Drug Discovery, Gene Interaction, Deep Learning, Biomedical AIAbstract
Identifying causal drug–gene–disease interactions is a fundamental challenge in drug discovery and precision medicine. Existing deep learning approaches predominantly rely on correlation-based predictions, limiting interpretability and biological validity. In this work, we propose CausalDGD, a causal deep learning framework that integrates structural causal models, mediation analysis, and deep neural representations to discover mechanistically grounded interaction triplets. By explicitly modeling Drug → Gene → Disease pathways and accounting for confounding factors, CausalDGD enables interpretable and causally faithful discovery. Extensive experiments on real-world biomedical datasets, including LINCS, DrugBank, and DisGeNET, demonstrate that the proposed approach outperforms state-ofthe-art baselines while providing biologically meaningful explanations. Our results highlight the importance of causal reasoning as a core component of trustworthy biomedical AI.
References
[1] Guney, E., Menche, J., Vidal, M., & Barábasi, A.-L. (2016). Network-based in silico drug efficacy screening. Bioinformatics, 32(4), 550–557.
[2] Cheng, F., Liu, C., Jiang, J., Lu, W., Li, W., Liu, G., Zhou, W., & Huang, J. (2012). Prediction of drug–target interactions and drug repositioning via network-based inference. PLoS Computational Biology, 8(5), e1002503.
[3] Wu, Z., Wang, Y., Chen, L., & Liu, Y. (2018). A comprehensive review of network-based methods for drug discovery. Briefings in Bioinformatics, 19(4), 718–734.
[4] Zhang, W., Chen, Y., Liu, F., Luo, F., Tian, G., & Li, X. (2015). Predicting potential drug–drug interactions by integrating chemical, biological, phenotypic and network data. Bioinformatics, 33(7), 936–944.
[5] Kipf, T. N., & Welling, M. (2017). Semi supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR).
[6] 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 (ICML) (pp. 1263–1272).
[7] Zong, N., Kim, H., Ngo, V., & Harismendy, O. (2017). Deep mining heterogeneous networks of biomedical linked data to predict novel drug–target associations. Bioinformatics, 33(15), 2337–2344.
[8] Zitnik, M., Agrawal, M., & Leskovec, J. (2018). Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13), 1457–1466.
[9] Wang, X., Sun, Z., Zhang, Y., Li, Y., & Wang, Y. (2021). Predicting drug–target interactions using multi-view deep learning. Briefings in Bioinformatics, 22(4), bbaa327.
[10] Lamb, J., Crawford, E. D., Peck, D., Modell, J. W., Blat, I. C., Wrobel, M. J., Golub, T. R. (2006). The Connectivity Map: Using gene-expression signatures to connect small molecules, genes, and disease. Science, 313(5795), 1929–1935.
[11] Subramanian, A., Narayan, R., Corsello, S. M., Peck, D. D., Natoli, T. E., Lu, X., Golub, T. R. (2017). A next generation Connectivity Map: L1000 platform and the first 1,000,000 profiles. Cell, 171(6), 1437–1452.e17.
[12] Kim, E., & Nam, H. (2022). DeSIDE-DDI: An interpretable deep learning framework for drug–drug interaction prediction using drug-induced gene expression. Journal of Cheminformatics, 14(1), 1–16.
[13] Aliper, A., Plis, S., Artemov, A., Ulloa, A., Mamoshina, P., Zhavoronkov, A. (2016). Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data. Molecular Pharmaceutics, 13(7), 2524–2530.
[14] Nickel, M., Murphy, K., Tresp, V., & Gabrilovich, E. (2016). A review of relational machine learning for knowledge graphs. Proceedings of the IEEE, 104(1), 11–33.
[15] Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems (pp. 2787–2795).
[16] Yang, B., Yih, W.-T., He, X., Gao, J., Deng, L. (2015). Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of the International Conference on Learning Representations (ICLR).
[17] Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press.
[18] Imai, K., Keele, L., & Tingley, D. (2010). A general approach to causal mediation analysis. Psychological Methods, 15(4), 309–334.
[19] VanderWeele, T. J. (2015). Explanation in causal inference: Methods for mediation and interaction. Oxford University Press.
[20] Shalit, U., Johansson, F. D., & Sontag, D. (2017). Estimating individual treatment effect: Generalization bounds and algorithms. In Proceedings of the 34th International Conference on Machine Learning (ICML) (pp. 3076–3085).
