GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype

TL;DR

GRAPE is a novel heterogeneous graph neural network that integrates gene descriptions, DNA sequences, and biotype information to improve the prediction of genetic perturbations and gene regulatory networks.

Contribution

It introduces the use of gene biotype information and combines pre-trained language and DNA models for enhanced gene representation learning.

Findings

Achieves state-of-the-art performance on public datasets

Effectively captures functional differences between gene biotypes

Improves gene regulatory network construction accuracy

Abstract

Predicting genetic perturbations enables the identification of potentially crucial genes prior to wet-lab experiments, significantly improving overall experimental efficiency. Since genes are the foundation of cellular life, building gene regulatory networks (GRN) is essential to understand and predict the effects of genetic perturbations. However, current methods fail to fully leverage gene-related information, and solely rely on simple evaluation metrics to construct coarse-grained GRN. More importantly, they ignore functional differences between biotypes, limiting the ability to capture potential gene interactions. In this work, we leverage pre-trained large language model and DNA sequence model to extract features from gene descriptions and DNA sequence data, respectively, which serve as the initialization for gene representations. Additionally, we introduce gene biotype information for the first time in genetic perturbation, simulating the distinct roles of genes with different biotypes in regulating cellular processes, while capturing implicit gene relationships through graph structure learning (GSL). We propose GRAPE, a heterogeneous graph neural network (HGNN) that leverages gene representations initialized with features from descriptions and sequences, models the distinct roles of genes with different biotypes, and dynamically refines the GRN through GSL. The results on publicly available datasets show that our method achieves state-of-the-art performance.