DrugCLIP: Contrastive Drug-Disease Interaction For Drug Repurposing

TL;DR

DrugCLIP is a contrastive learning approach that leverages multimodal data and real-world clinical trial records to improve drug repurposing predictions without requiring negative labels.

Contribution

It introduces a novel contrastive learning framework for drug-disease interaction prediction and curates a new dataset for drug repurposing research.

Findings

DrugCLIP outperforms existing methods in drug repurposing tasks.

The curated dataset enhances the evaluation of drug-disease interaction models.

Contrastive learning effectively captures drug and disease relationships without negative labels.

Abstract

Bringing a novel drug from the original idea to market typically requires more than ten years and billions of dollars. To alleviate the heavy burden, a natural idea is to reuse the approved drug to treat new diseases. The process is also known as drug repurposing or drug repositioning. Machine learning methods exhibited huge potential in automating drug repurposing. However, it still encounter some challenges, such as lack of labels and multimodal feature representation. To address these issues, we design DrugCLIP, a cutting-edge contrastive learning method, to learn drug and disease's interaction without negative labels. Additionally, we have curated a drug repurposing dataset based on real-world clinical trial records. Thorough empirical studies are conducted to validate the effectiveness of the proposed DrugCLIP method.