MuCoS: Efficient Drug-Target Prediction through Multi-Context-Aware Sampling

TL;DR

MuCoS is a novel drug-target prediction method that efficiently captures structural patterns and contextual information, outperforming existing models especially on unseen entities and relationships, with reduced computational costs.

Contribution

We introduce MuCoS, a multi-context-aware sampling approach that improves drug-target prediction accuracy without negative triplet sampling, reducing computational complexity.

Findings

MuCoS outperforms existing models on KEGG50k dataset by up to 18% in Hits@10.

MuCoS achieves 13% higher MRR compared to baseline methods.

MuCoS effectively predicts unseen drug-target relationships with improved accuracy.

Abstract

Drug-target interactions are critical for understanding biological processes and advancing drug discovery. However, traditional methods such as ComplEx-SE, TransE, and DistMult struggle with unseen relationships and negative triplets, which limits their effectiveness in drug-target prediction. To address these challenges, we propose Multi-Context-Aware Sampling (MuCoS), an efficient and positively accurate method for drug-target prediction. MuCoS reduces computational complexity by prioritizing neighbors of higher density to capture informative structural patterns. These optimized neighborhood representations are integrated with BERT, enabling contextualized embeddings for accurate prediction of missing relationships or tail entities. MuCoS avoids the need for negative triplet sampling, reducing computation while improving performance over unseen entities and relations. Experiments on the KEGG50k biomedical dataset show that MuCoS improved over existing models by 13\% on MRR, 7\% on Hits@1, 4\% on Hits@3, and 18\% on Hits@10 for the general relationship, and by 6\% on MRR, 1\% on Hits@1, 3\% on Hits@3, and 12\% on Hits@10 for prediction of drug-target relationship.