Multigenerational machine learning-based genomic prediction for dermo resistance in eastern oyster Crassostrea virginica
- 1Rutgers University
Abstract
Dermo disease caused by the protist Perkinsus marinus poses a major threat to Eastern oyster aquaculture. We previously conducted genomic selection for dermo resistance and found increased effectiveness over phenotypic selection. Here, we report improved genomic predictions using combined data from three successive generations. We evaluated nine different genomic selection models, including three supervised machine learning architectures: gradient boosting, logistic regression, and random forest. Combining data across multiple generations did not, by itself, substantially improve the accuracy of most models, but the increased sample size provided genotyping confidence of loci with rare alleles. Correlation accuracy of all models significantly increased with the inclusion of low-frequency variants and strong-effect markers identified through a genome-wide association study. Gradient boosting machine learning models outperformed other genomic selection models across all training scenarios, suggesting enhanced capacity to learn generalizable genomic signals associated with dermo resistance. The best gradient boosting model achieved a peak correlation accuracy of 0.410, a substantial improvement over the previous peak accuracy of 0.274 from traditional models. Together, our results highlight the potential of machine learning for genomic selection and the significance of rare variants in determining dermo resistance.
Related
- Chromosomal-Level Whole Genome Assemblies of Crassostrea Virginica
- Genetic Diversity and Structure Analysis of Wild Oysters (Crassostrea virginica) Within and Between River Systems Reveals Spatial Genetic Structure and Salinity-Adaptive Variation Across the Canadian Maritimes.
- Machine learning–driven prediction of antimicrobial resistance in Staphylococcus aureus using genomic and allelic signatures
- Natural Genetic Variation in a Multigenerational Phenotype in C. elegans
- A New Disease Gene for Hypokalemic Periodic Paralysis, KCNA7, Established in a Multigenerational Family
BibTeX
@misc{sun2026multigenerational,
title = {{Multigenerational machine learning-based genomic prediction for dermo resistance in eastern oyster Crassostrea virginica}},
author = {H. Sun and P. Coyne and Z. Wang and S. Casas and J. La Peyre and M. L. Williams and S. Rikard and D. Bushek and J. Wong and X. Guo},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.08.750100},
url = {https://www.biorxiv.org/content/10.64898/2026.09.08.750100v1},
note = {CC0},
}
RIS
TY - UNPB
TI - Multigenerational machine learning-based genomic prediction for dermo resistance in eastern oyster Crassostrea virginica
AU - H. Sun
AU - P. Coyne
AU - Z. Wang
AU - S. Casas
AU - J. La Peyre
AU - M. L. Williams
AU - S. Rikard
AU - D. Bushek
AU - J. Wong
AU - X. Guo
PY - 2026
DA - 2026/09/08
PB - bioRxiv
DO - 10.64898/2026.09.08.750100
UR - https://www.biorxiv.org/content/10.64898/2026.09.08.750100v1
AB - Dermo disease caused by the protist Perkinsus marinus poses a major threat to Eastern oyster aquaculture. We previously conducted genomic selection for dermo resistance and found increased effectiveness over phenotypic selection. Here, we report improved genomic predictions using combined data from three successive generations. We evaluated nine different genomic selection models, including three supervised machine learning architectures: gradient boosting, logistic regression, and random forest. Combining data across multiple generations did not, by itself, substantially improve the accuracy of most models, but the increased sample size provided genotyping confidence of loci with rare alleles. Correlation accuracy of all models significantly increased with the inclusion of low-frequency variants and strong-effect markers identified through a genome-wide association study. Gradient boosting machine learning models outperformed other genomic selection models across all training scenarios, suggesting enhanced capacity to learn generalizable genomic signals associated with dermo resistance. The best gradient boosting model achieved a peak correlation accuracy of 0.410, a substantial improvement over the previous peak accuracy of 0.274 from traditional models. Together, our results highlight the potential of machine learning for genomic selection and the significance of rare variants in determining dermo resistance.
ER -