Abstract:

Knowledge Graphs (KGs) have emerged as powerful tools for drug discovery, but existing methods often fail to capture the multi-contextual nature of biomedical relationships. We introduce MuCoS (Multi Context Aware Sampling), a novel approach that efficiently discovers drug targets by sampling diverse contextual neighborhoods in biomedical KGs. Our method significantly improves target identification accuracy while reducing computational overhead.

Methodology:

MuCoS employs a multi-context aware sampling strategy that explores different relationship types and entity neighborhoods simultaneously. We evaluate on standard drug discovery benchmarks and compare against state-of-the-art KG completion methods. Performance is measured by target prediction accuracy, computational efficiency, and biological relevance of discovered relationships.

MuCoS: Drug Target Discovery via Knowledge Graphs

Abstract:

Methodology: