Learning to Describe for Predicting Zero-shot Drug-Drug Interactions
This addresses a critical healthcare challenge by enabling DDI prediction for new drugs, which is incremental as it builds on existing computational methods by incorporating textual data and zero-shot learning.
The paper tackles the problem of predicting adverse drug-drug interactions (DDIs) for new drugs with no prior knowledge, introducing a zero-shot DDI prediction setup. It proposes TextDDI, which uses a language model and reinforcement learning to select relevant text from online databases, achieving accurate predictions in zero-shot and few-shot settings, with empirical results showing benefits in these scenarios.
Adverse drug-drug interactions~(DDIs) can compromise the effectiveness of concurrent drug administration, posing a significant challenge in healthcare. As the development of new drugs continues, the potential for unknown adverse effects resulting from DDIs becomes a growing concern. Traditional computational methods for DDI prediction may fail to capture interactions for new drugs due to the lack of knowledge. In this paper, we introduce a new problem setup as zero-shot DDI prediction that deals with the case of new drugs. Leveraging textual information from online databases like DrugBank and PubChem, we propose an innovative approach TextDDI with a language model-based DDI predictor and a reinforcement learning~(RL)-based information selector, enabling the selection of concise and pertinent text for accurate DDI prediction on new drugs. Empirical results show the benefits of the proposed approach on several settings including zero-shot and few-shot DDI prediction, and the selected texts are semantically relevant. Our code and data are available at \url{https://github.com/zhufq00/DDIs-Prediction}.