Knowledge Graph Sparsification for GNN-based Rare Disease Diagnosis

2025-10-09

AI Summary

Diagnosing rare genetic disorders faces core challenges: scarcity of patient data, limited accessibility of whole-genome sequencing, and the vastness of the pathogenic gene space—particularly acute in resource-constrained settings. To address this, we propose RareNet—the first phenotype-driven method integrating knowledge graph subgraph sparsification with graph neural networks (GNNs). RareNet constructs patient-specific subgraphs solely from standardized clinical phenotypes, enabling high-accuracy prioritization of causal genes. Its key contributions are: (1) structure-aware sparsification that retains biomedically salient relationships; (2) plug-and-play compatibility and intrinsic interpretability—functioning either as a standalone model or as an augmentation module within existing diagnostic pipelines; and (3) superior performance over state-of-the-art methods on two authoritative biomedical benchmarks, demonstrating robustness and scalability in low-resource scenarios.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Rare genetic disease diagnosis faces critical challenges: insufficient patient data, inaccessible full genome sequencing, and the immense number of possible causative genes. These limitations cause prolonged diagnostic journeys, inappropriate treatments, and critical delays, disproportionately affecting patients in resource-limited settings where diagnostic tools are scarce. We propose RareNet, a subgraph-based Graph Neural Network that requires only patient phenotypes to identify the most likely causal gene and retrieve focused patient subgraphs for targeted clinical investigation. RareNet can function as a standalone method or serve as a pre-processing or post-processing filter for other candidate gene prioritization methods, consistently enhancing their performance while potentially enabling explainable insights. Through comprehensive evaluation on two biomedical datasets, we demonstrate competitive and robust causal gene prediction and significant performance gains when integrated with other frameworks. By requiring only phenotypic data, which is readily available in any clinical setting, RareNet democratizes access to sophisticated genetic analysis, offering particular value for underserved populations lacking advanced genomic infrastructure.

Problem

• Diagnosing rare genetic diseases with limited patient data
• Overcoming inaccessible genome sequencing in resource-limited settings
• Identifying causal genes using only phenotypic information

Innovation

• Uses phenotype-only input for gene prioritization
• Leverages subgraph-based GNN for rare disease diagnosis
• Functions as standalone or integrated filter method