Comprehensive Metapath-based Heterogeneous Graph Transformer for Gene-Disease Association Prediction

TL;DR

COMET is a novel transformer-based model that integrates diverse biological data and Metapaths to improve gene-disease association predictions, effectively capturing complex network semantics and dependencies.

Contribution

It introduces a comprehensive heterogeneous graph transformer leveraging multiple Metapaths and BioGPT features for enhanced gene-disease association prediction.

Findings

Outperforms state-of-the-art methods in accuracy and robustness.

Effectively captures long-distance dependencies in biological networks.

Provides interpretability through attention mechanisms.

Abstract

Discovering gene-disease associations is crucial for understanding disease mechanisms, yet identifying these associations remains challenging due to the time and cost of biological experiments. Computational methods are increasingly vital for efficient and scalable gene-disease association prediction. Graph-based learning models, which leverage node features and network relationships, are commonly employed for biomolecular predictions. However, existing methods often struggle to effectively integrate node features, heterogeneous structures, and semantic information. To address these challenges, we propose COmprehensive MEtapath-based heterogeneous graph Transformer(COMET) for predicting gene-disease associations. COMET integrates diverse datasets to construct comprehensive heterogeneous networks, initializing node features with BioGPT. We define seven Metapaths and utilize a transformer framework to aggregate Metapath instances, capturing global contexts and long-distance dependencies. Through intra- and inter-metapath aggregation using attention mechanisms, COMET fuses latent vectors from multiple Metapaths to enhance GDA prediction accuracy. Our method demonstrates superior robustness compared to state-of-the-art approaches. Ablation studies and visualizations validate COMET's effectiveness, providing valuable insights for advancing human health research.