GraphSeqLM: A Unified Graph Language Framework for Omic Graph Learning

TL;DR

GraphSeqLM introduces a novel framework combining graph neural networks with large language model-derived biological sequence embeddings to improve multi-omic data analysis for complex disease understanding.

Contribution

It is the first to integrate LLM-generated sequence embeddings with GNNs for enhanced biological data analysis in a unified framework.

Findings

Achieves higher predictive accuracy than existing methods.

Effectively captures complex biological relationships.

Enhances multi-omic data integration for precision medicine.

Abstract

The integration of multi-omic data is pivotal for understanding complex diseases, but its high dimensionality and noise present significant challenges. Graph Neural Networks (GNNs) offer a robust framework for analyzing large-scale signaling pathways and protein-protein interaction networks, yet they face limitations in expressivity when capturing intricate biological relationships. To address this, we propose Graph Sequence Language Model (GraphSeqLM), a framework that enhances GNNs with biological sequence embeddings generated by Large Language Models (LLMs). These embeddings encode structural and biological properties of DNA, RNA, and proteins, augmenting GNNs with enriched features for analyzing sample-specific multi-omic data. By integrating topological, sequence-derived, and biological information, GraphSeqLM demonstrates superior predictive accuracy and outperforms existing methods, paving the way for more effective multi-omic data integration in precision medicine.