A social theory-enhanced graph representation learning framework for multitask prediction of drug-drug interactions

Current machine learning-based methods have achieved inspiring predictions in the scenarios of mono-type and multi-type drug-drug interactions (DDIs), but they all ignore enhancive and depressive pharmacological changes triggered by DDIs. In addition, these pharmacological changes are asymmetric since the roles of two drugs in an interaction are different. More importantly, these pharmacological changes imply significant topological patterns among DDIs. To address the above issues, we first leverage Balance theory and Status theory in social networks to reveal the topological patterns among directed pharmacological DDIs, which are modeled as a signed and directed network. Then, we design a novel graph representation learning model named SGRL-DDI (social theory-enhanced graph representation learning for DDI) to realize the multitask prediction of DDIs. SGRL-DDI model can capture the task-joint information by integrating relation graph convolutional networks with Balance and Status patterns. Moreover, we utilize task-specific deep neural networks to perform two tasks, including the prediction of enhancive/depressive DDIs and the prediction of directed DDIs. Based on DDI entries collected from DrugBank, the superiority of our model is demonstrated by the comparison with other state-of-the-art methods. Furthermore, the ablation study verifies that Balance and Status patterns help characterize directed pharmacological DDIs, and that the joint of two tasks provides better DDI representations than individual tasks. Last, we demonstrate the practical effectiveness of our model by a version-dependent test, where 88.47 and 81.38% DDI out of newly added entries provided by the latest release of DrugBank are validated in two predicting tasks respectively.

Automated summary

Current machine learning-based methods have made impressive predictions in mono-type and multi-type drug-drug interactions (DDIs) scenarios, but they fail to consider the enhancing and depressive pharmacological changes triggered by DDIs. Additionally, these pharmacological changes are asymmetric due to the different roles of the two drugs involved in an interaction. To address these issues, this study utilizes Balance and Status theories from social networks to reveal the topological patterns in directed pharmacological DDIs. A novel graph representation learning model named SGRL-DDI is then proposed to achieve multitask prediction of DDIs by integrating relation graph convolutional networks with Balance and Status patterns. Experimental results using DDI entries collected from DrugBank demonstrate the superiority of the SGRL-DDI model compared to other state-of-the-art methods. Moreover, the practical effectiveness of the model is demonstrated through a version-dependent test.