Machine Learning-Based Accurate Full-Sib Family Assignment in Sturgeon Using Whole-Genome Sequencing Data
Open Access
- 14 May 2026
- journal article
- research article
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 27 (10) , 4359
Abstract
Accurate pedigree reconstruction is essential for genetic evaluation, inbreeding control, and family management in aquaculture breeding programs. In sturgeon, extremely high fecundity and communal rearing during early developmental stages often lead to the loss of family information, making reliable full-sib family assignment a critical challenge. In this study, we developed a machine learning-based framework for full-sib family assignment using simulated genotype datasets and whole-genome resequencing data from Russian sturgeon. Simulation analyses across five machine learning algorithms showed that training set size and marker density were the primary determinants of assignment accuracy. When at least 10 individuals per family were included in the training set, mean identification accuracy exceeded 99% across all evaluated scenarios, and exceeded 99.9% for all methods except XGBoost. In contrast, performance declined when the marker number was reduced to 200. At moderate marker densities (500–1000 markers), performance remained stable, with mean identification accuracy around 99% even when only 3–4 individuals per family were included in the training set. Validation using whole-genome resequencing data (sequencing depth ranging from 9.43× to 11.86×) from 582 individuals representing 19 full-sib families of Russian sturgeon confirmed the simulation findings, with several algorithms achieving assignment accuracies exceeding 99%. These results demonstrate that machine learning provides an accurate and robust approach for full-sib family assignment using genome-wide single nucleotide polymorphism (SNP) data. The proposed framework offers an effective solution for pedigree reconstruction and family identification in sturgeon breeding populations lacking reliable pedigree records.Keywords
Funding Information
- Beijing Academy of Agricultural and Forestry Sciences (YKPY2025004)
- Beijing Academy of Agricultural and Forestry Sciences (KJCX20230216)
- National Natural Science Foundation of China (32341059)
- Beijing Innovation Consortium of Agriculture Research System (BAIC07-2026-1)
- Beijing International Science & Technology Cooperation Base (GHPT2026-06)
This publication has 52 references indexed in Scilit:
- Genomic selection for hard-to-measure traits in aquaculture: Challenges in balancing genetic gain and diversityAquaculture, 2025
- Whole genome resequencing data enables a targeted SNP panel for conservation and aquaculture of Oreochromis cichlid fishesAquaculture, 2022
- Fast two-stage phasing of large-scale sequence dataThe American Journal of Human Genetics, 2021
- Impact of phenotypic information and composition of reference population on genomic prediction in fish under the presence of genotype by environment interactionAquaculture, 2020
- A new strain group of common carp: The genetic differences and admixture events between Cyprinus carpio breedsEcology and Evolution, 2020
- Characterizing the genetic structure of introduced Nile tilapia (Oreochromis niloticus) strains in Tanzania using double digest RAD sequencingAquaculture International, 2019
- SNP marker panels for parentage assignment and traceability in the Florida bass ( Micropterus floridanus )Aquaculture, 2018
- A workflow used to design low density SNP panels for parentage assignment and traceability in aquaculture species and its validation in Atlantic salmonAquaculture, 2017
- Effect of assortative mating on genetic gain and inbreeding in aquaculture selective breeding programsAquaculture, 2017
- Selection and use of SNP markers for animal identification and paternity analysis in U.S. beef cattleMammalian Genome, 2002