GRAFT: Biological Graph and Hypergraph Benchmarks for Linked Gene Expression and Phenotypic Trait Prediction in Arabidopsis thaliana

2026-06-25

AI Summary

This study addresses a core challenge in genotype-to-phenotype (G2P) mapping: the precise identification of key genes governing specific traits, which is hindered by the scarcity of multimodal gene expression and heterogeneous phenotypic data from the same plant. To overcome this limitation, the authors present GRAFT, the first homologous multimodal dataset in *Arabidopsis thaliana*, and introduce a novel graph and hypergraph neural network framework that integrates biological prior knowledge. This approach enables both accurate phenotype prediction and interpretable gene–trait association analysis. Experimental results demonstrate that hypergraph-based modeling substantially enhances predictive performance, establishing a new paradigm and benchmark for plant functional genomics and intelligent breeding.

Abstract

Understanding which genes control which traits in an organism remains one of the central challenges in biology. Despite significant advances in data collection technology, our ability to map genes to traits is still limited. This genome-to-phenome (G2P) challenge spans several problem domains, including plant breeding, and requires methods capable of reasoning over high-dimensional, heterogeneous, and biologically structured data. Current datasets and data repositories, however, are not well-equipped for this task. Current studies do not link gene expression and trait data, and most focus on very specific traits, limiting the breadth of possible correlations. To address this gap, we present the novel Gene-Graph Regression for Arabidopsis Functional Traits (GRAFT) dataset, a curated multi-modal dataset linking gene expression profiles with phenotypic trait measurements in Arabidopsis thaliana, a model organism in plant biology. GRAFT supports tasks such as phenotype prediction and interpretable graph learning. In addition, we benchmark conventional regression and explanatory baselines, including a biologically-informed hypergraph baseline, to validate gene-trait associations. To the best of our knowledge, this is the first dataset to provide multimodal gene information and heterogeneous trait or phenotype data for the same Arabidopsis thaliana specimens. With GRAFT, we aim to foster research to accurately understand the relationship between genotypes and phenotypes using gene information, higher-order gene pairings, and trait data from multiple sources.

Problem

• gene-to-trait mapping
• genome-to-phenome
• phenotypic trait prediction
• gene expression
• Arabidopsis thaliana

Innovation

• multimodal dataset
• gene-trait association
• hypergraph learning
• phenotype prediction
• Arabidopsis thaliana