DNA Language Model and Interpretable Graph Neural Network Identify Genes and Pathways Involved in Rare Diseases

TL;DR

This paper introduces a novel approach combining DNA language models, graph neural networks, and genetic algorithms to identify causal genes and pathways in rare diseases, validated on patient data and capable of discovering known and new candidates.

Contribution

It presents HyenaDNA, a long-range genomic foundation model that generates dynamic gene embeddings for improved gene and pathway prioritization in rare diseases.

Findings

Successfully re-identified known causal genes and pathways.

Detected novel candidate genes and pathways.

Validated on a rare disease patient cohort.

Abstract

Identification of causal genes and pathways is a critical step for understanding the genetic underpinnings of rare diseases. We propose novel approaches to gene prioritization and pathway identification using DNA language model, graph neural networks, and genetic algorithm. Using HyenaDNA, a long-range genomic foundation model, we generated dynamic gene embeddings that reflect changes caused by deleterious variants. These gene embeddings were then utilized to identify candidate genes and pathways. We validated our method on a cohort of rare disease patients with partially known genetic diagnosis, demonstrating the re-identification of known causal genes and pathways and the detection of novel candidates. These findings have implications for the prevention and treatment of rare diseases by enabling targeted identification of new drug targets and therapeutic pathways.