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

2025-02-25

AI Summary

Traditional knowledge graph embedding methods for drug–target prediction suffer from poor generalization to unseen relations, overreliance on negative sampling, and inadequate modeling of sparse, dynamic biomedical relationships. To address these limitations, this paper proposes a multi-context-aware end-to-end framework. It introduces a novel density-adaptive neighborhood sampling mechanism that eliminates negative triple sampling entirely. Built upon ComplEx and TransE backbones, the framework incorporates density-aware aggregation to capture local topological patterns and integrates BERT to enable contextualized entity representations. Evaluated on the KEGG50k dataset, our method achieves up to a 13% improvement in Mean Reciprocal Rank (MRR) for general relations and a 6% gain for drug–target relations; Hits@10 improves by up to 18%. Crucially, it significantly enhances zero-shot prediction capability for both unseen entities and unseen relations.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Improves drug-target interaction prediction
• Reduces computational complexity and negative sampling
• Enhances accuracy with contextualized embeddings

Innovation

• Multi-Context-Aware Sampling
• BERT for contextualized embeddings
• Eliminates negative triplet sampling