Learning to Describe for Predicting Zero-shot Drug-Drug Interactions

Abstract

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}.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Modeling polypharmacy side effects with graph convolutional networks
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
• Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
• SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
• Knowledge Graph Reasoning with Relational Digraph
• Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
• Exploring the Feasibility of ChatGPT for Event Extraction
• Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family
• TEMPERA: Test-Time Prompting via Reinforcement Learning