Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations

TL;DR

Onto2Vec is a method that creates vector representations of biological entities based on their ontology annotations, enabling various bioinformatics tasks like similarity prediction, classification, and clustering.

Contribution

This paper introduces Onto2Vec, a novel approach for embedding biological entities and their ontology annotations into vector space for improved analysis.

Findings

Effective in predicting protein interactions

Supports classification of interaction types

Facilitates clustering of biological entities

Abstract

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.