Neurosymbolic AI for Reasoning on Biomedical Knowledge Graphs

TL;DR

This paper surveys neurosymbolic AI methods applied to biomedical knowledge graphs, highlighting their advantages for biomedical reasoning and prediction tasks like drug repositioning.

Contribution

It provides a comprehensive overview of neurosymbolic approaches for biomedical knowledge graph completion and discusses their potential benefits in biomedical applications.

Findings

Neurosymbolic methods combine rule-based and embedding techniques.

These approaches are increasingly popular for biomedical knowledge graph tasks.

They offer unique advantages for biomedical reasoning and prediction.

Abstract

Biomedical datasets are often modeled as knowledge graphs (KGs) because they capture the multi-relational, heterogeneous, and dynamic natures of biomedical systems. KG completion (KGC), can, therefore, help researchers make predictions to inform tasks like drug repositioning. While previous approaches for KGC were either rule-based or embedding-based, hybrid approaches based on neurosymbolic artificial intelligence are becoming more popular. Many of these methods possess unique characteristics which make them even better suited toward biomedical challenges. Here, we survey such approaches with an emphasis on their utilities and prospective benefits for biomedicine.