Supervised Biomedical Semantic Similarity

Semantic similarity between concepts in knowledge graphs is essential for several bioinformatics applications, including the prediction of protein-protein interactions and the discovery of associations between diseases and genes. Although knowledge graphs describe entities in terms of several perspectives (or semantic aspects), state-of-the-art semantic similarity measures are general-purpose. This can represent a challenge since different use cases for the application of semantic similarity may need different similarity perspectives and ultimately depend on expert knowledge for manual fine-tuning. We present a new approach that uses supervised machine learning to tailor aspect-oriented semantic similarity measures to fit a particular view on biological similarity or relatedness. We implement and evaluate it using different combinations of representative semantic similarity measures and machine learning methods with four biological similarity views: protein-protein interaction, protein function similarity, protein sequence similarity and phenotype-based gene similarity. The results demonstrate that our approach outperforms non-supervised methods, producing semantic similarity models that fit different biological perspectives significantly better than the commonly used manual combinations of semantic aspects.

Automated summary

Semantic similarity plays a crucial role in bioinformatics applications such as protein-protein interaction prediction and disease-gene association discovery. However, existing semantic similarity measures are general-purpose and may not align well with specific biological perspectives. In this study, we introduce a supervised machine learning approach to tailor aspect-oriented semantic similarity measures for different biological views. The results demonstrate the superiority of our method in fitting semantic similarity models to diverse biological perspectives compared to commonly used manual combinations of semantic aspects.