Biomedical Knowledge Graph Embeddings with Negative Statements

TL;DR

This paper introduces TrueWalks, a novel method for incorporating negative statements into biomedical knowledge graph embeddings, improving performance in protein and gene-disease prediction tasks by differentiating positive and negative relations.

Contribution

The paper presents a new walk-generation approach that explicitly models negative statements and their semantic implications in ontology-rich knowledge graphs.

Findings

Improved accuracy in protein-protein interaction prediction.

Enhanced gene-disease association prediction.

Consistent performance gains across benchmarks.

Abstract

A knowledge graph is a powerful representation of real-world entities and their relations. The vast majority of these relations are defined as positive statements, but the importance of negative statements is increasingly recognized, especially under an Open World Assumption. Explicitly considering negative statements has been shown to improve performance on tasks such as entity summarization and question answering or domain-specific tasks such as protein function prediction. However, no attention has been given to the exploration of negative statements by knowledge graph embedding approaches despite the potential of negative statements to produce more accurate representations of entities in a knowledge graph. We propose a novel approach, TrueWalks, to incorporate negative statements into the knowledge graph representation learning process. In particular, we present a novel walk-generation method that is able to not only differentiate between positive and negative statements but also take into account the semantic implications of negation in ontology-rich knowledge graphs. This is of particular importance for applications in the biomedical domain, where the inadequacy of embedding approaches regarding negative statements at the ontology level has been identified as a crucial limitation. We evaluate TrueWalks in ontology-rich biomedical knowledge graphs in two different predictive tasks based on KG embeddings: protein-protein interaction prediction and gene-disease association prediction. We conduct an extensive analysis over established benchmarks and demonstrate that our method is able to improve the performance of knowledge graph embeddings on all tasks.