VitisGP: Multi-Task Benchmark for Genotype to Phenotype Grapevine Prediction
Abstract
As climate change reshapes grape-growing conditions, predicting grapevine phenotypes from genomic variation is increasingly important for identifying and breeding cultivars suited to emerging environmental pressures. Existing research on the grapevine genotype-phenotype relationship using machine learning has often focused on individual traits, isolated regions, or a limited set of predictive models. We introduce VitisGP, a multi-phenotype curated dataset, integrating genome-wide SNP data with 26 heterogeneous phenotype prediction tasks spanning sommelier-curated aroma traits (N=11), botanical traits (N=14) and wine color---across 1,197 Vitis vinifera cultivars. We employ VitisGP to benchmark phenotype prediction, comparing machine-learning models with differing inductive biases---L2-regularized logistic regression, Random Forest, XGBoost, CatBoost, GBLUP and Transformer-based models, providing the first systematic comparison of this breadth on harmonized grapevine data. Across the benchmark, CatBoost achieves the strongest overall performance (macro-average AUROC=0.696 across 26 tasks), although model performance varies substantially across phenotype classes, with sensory and color traits showing stronger predictability than agronomic characteristics. VitisGP provides the community with a resource for investigating the genomic basis of phenotypic traits and screening grapevine diversity for climate-relevant characteristics.
Related
- A linear-transformer hybrid for single-nucleotide polymorphism-based genotype-to-phenotype prediction in grapevine.
- Grapevine genotype and medium composition as drivers of culturable bacterial communities: From co-occurrence patterns to ISR against Plasmopara viticola
- Genomic and Epigenomic Relationships Capture Different Patterns of Genotype-by-Environment Interaction in Grapevine Clones
- An Evidence-Tiered Developmental Framework for Congenital Vertebral Malformations: Spatiotemporal Thresholds in Genotype–Phenotype Interpretation
- NOTCH2 VUS Interpretation in Pediatric Cholestasis: A 365-Variant Landscape and Genotype–Phenotype Analysis of 7 Cases
BibTeX
@misc{dercoli2026vitisgp,
title = {{VitisGP: Multi-Task Benchmark for Genotype to Phenotype Grapevine Prediction}},
author = {Chiara D'Ercoli and May Levin and Pietro Liò},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40668},
eprint = {2610.40668},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40668},
}
RIS
TY - UNPB
TI - VitisGP: Multi-Task Benchmark for Genotype to Phenotype Grapevine Prediction
AU - Chiara D'Ercoli
AU - May Levin
AU - Pietro Liò
PY - 2026
DA - 2026/10/13
PB - arXiv
DO - 10.48550/arxiv.2610.40668
UR - https://arxiv.org/abs/2610.40668
AB - As climate change reshapes grape-growing conditions, predicting grapevine phenotypes from genomic variation is increasingly important for identifying and breeding cultivars suited to emerging environmental pressures. Existing research on the grapevine genotype-phenotype relationship using machine learning has often focused on individual traits, isolated regions, or a limited set of predictive models. We introduce VitisGP, a multi-phenotype curated dataset, integrating genome-wide SNP data with 26 heterogeneous phenotype prediction tasks spanning sommelier-curated aroma traits (N=11), botanical traits (N=14) and wine color---across 1,197 Vitis vinifera cultivars. We employ VitisGP to benchmark phenotype prediction, comparing machine-learning models with differing inductive biases---L2-regularized logistic regression, Random Forest, XGBoost, CatBoost, GBLUP and Transformer-based models, providing the first systematic comparison of this breadth on harmonized grapevine data. Across the benchmark, CatBoost achieves the strongest overall performance (macro-average AUROC=0.696 across 26 tasks), although model performance varies substantially across phenotype classes, with sensory and color traits showing stronger predictability than agronomic characteristics. VitisGP provides the community with a resource for investigating the genomic basis of phenotypic traits and screening grapevine diversity for climate-relevant characteristics.
ER -