Causality Discovery with Domain Knowledge for Drug-Drug Interactions Discovery
Bayesian Network Probabilistic Graphs have recently been applied to the problem of discovery drug-drug interactions, i.e., the identification of drugs that, when consumed together, produce an unwanted side effect. These methods have the advantage of being explainable: the cause of the interaction is made explicit. However, they suffer from two intrinsic problems: (1) the high time-complexity for computing causation, i.e., exponential; and (2) the difficult identification of causality directions, i.e., it is difficult to identify in drug-drug interactions databases whether a drug causes an adverse effect – or vice versa, an adverse effect causes a drug consumption. While solutions for addressing the causality direction identification exist, e.g., the CARD method, these assume statistical independence between drug pairs considered for interaction: real data often does not satisfy this condition.
In this paper, we propose a novel causality discovery algorithm for drug-drug interactions that goes beyond these limitations: Domain-knowledge-driven Causality Discovery (DCD). In DCD, a knowledge base that contains known drug-side effect pairs is used to prime a greedy drug-drug interaction algorithm that detects the drugs that, when consumed together, cause a side effect. This algorithm resolves the drug-drug interaction discovery problem in \(O(n^2)\) time and provides the causal direction of combined causes and their effect, without resorting to assuming statistical independence of drugs intake. Comprehensive experiments on real-world and synthetic datasets show the proposed method is more effective and efficient than current state-of-the-art solutions, while also addressing a number of drawbacks of current solutions, including the high time complexity, and the strong assumptions regarding real-world data that are often violated.
KeywordsCausality discovery Bayesian network Drug-drug interaction
The authors would like to acknowledge Meng Wang from Southeast University, China, and Mingyang Zhong from The University of Queensland, Australia, for their input on the initial stages of this work.
- 8.Jin, Z., Li, J., Liu, L., Le, T.D., Sun, B., Wang, R.: Discovery of causal rules using partial association. In: IEEE 12th International Conference on Data Mining, pp. 309–318. IEEE (2012)Google Scholar
- 10.Li, J., Le, T.D., Liu, L., Liu, J., Jin, Z., Sun, B.: Mining causal association rules. In: IEEE 13th International Conference on Data Mining (Workshops), pp. 114–123. IEEE (2013)Google Scholar
- 13.Neapolitan, R.E., et al.: Learning Bayesian Networks, vol. 38. Pearson Prentice Hall, Upper Saddle River (2004)Google Scholar
- 16.Qin, X., Kakar, T., Wunnava, S., Rundensteiner, E.A., Cao, L.: MARAS: signaling multi-drug adverse reactions. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1615–1623. ACM (2017)Google Scholar
- 18.Rodrigues, A.D.: Drug-Drug Interactions. CRC Press, Boca Raton (2008)Google Scholar
- 19.Van Puijenbroek, E.P., Egberts, A.C., Meyboom, R.H., Leufkens, H.G.: Signalling possible drug-drug interactions in a spontaneous reporting system: delay of withdrawal bleeding during concomitant use of oral contraceptives and itraconazole. Br. J. Clin. Pharmacol. 47(6), 689–693 (1999)CrossRefGoogle Scholar
- 20.Waldmann, M.R., Martignon, L.: A Bayesian network model of causal learning. In: Proceedings of the 20th annual conference of the Cognitive Science Society, pp. 1102–1107 (1998)Google Scholar