Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations
This addresses the need for better computational tools in bioinformatics for analyzing biological data, though it appears incremental as it builds on existing vector representation techniques.
The authors tackled the problem of representing biological entities and their ontology annotations by proposing Onto2Vec, a method that learns feature vectors for entities based on biomedical ontologies, enabling applications like similarity-based protein interaction prediction, classification, and clustering.
We propose the Onto2Vec method, an approach to learn feature vectors for biological entities based on their annotations to biomedical ontologies. Our method can be applied to a wide range of bioinformatics research problems such as similarity-based prediction of interactions between proteins, classification of interaction types using supervised learning, or clustering.