New GRAFT dataset links gene expression to plant traits

Researchers have introduced GRAFT, a new dataset designed to advance the understanding of gene-to-trait relationships in plants. This multi-modal dataset links gene expression profiles with phenotypic trait measurements for Arabidopsis thaliana, a model organism in plant biology. GRAFT aims to support tasks like phenotype prediction and interpretable graph learning, and includes benchmarks for regression and biologically-informed hypergraph baselines to validate gene-trait associations. It is presented as the first dataset of its kind to offer multimodal gene and heterogeneous trait data for the same plant specimens. AI

IMPACT Facilitates AI-driven research into genotype-phenotype correlations, potentially accelerating discoveries in plant breeding and genomics.

RANK_REASON The cluster contains a research paper detailing a new dataset and benchmarks for biological research. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.AI →

• Arabidopsis thaliana
• arXiv
• Gene-Graph Regression for Arabidopsis Functional Traits
• GRAFT
• Hugging Face
• Manuel Serna-Aguilera

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →