Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Better Multi-Breed Genomic Predictions for Tropical Bull Fertility Using a Breed-Adjusted Genomic Relationship Matrix.

Journal of animal breeding and genetics = Zeitschrift fur Tierzuchtung und Zuchtungsbiologie·2026

Same author

Harnessing gastrointestinal microbial co-association networks to predict feed efficiency and methane emissions across beef and dairy cattle.

Microbial genomics·2026

Same author

Microbiome by transcriptome interactions triggered by a switch to an alternative diet in Nellore cattle.

Scientific reports·2026

Same author

The genetic relationship between immune competence traits and micro-genetic environmental sensitivity of weight, fat, and muscle traits in Australian Angus cattle.

Genetics, selection, evolution : GSE·2025

Same author

Breeding values and index creation for health and behavior traits in Labrador Retriever guide dogs.

Frontiers in veterinary science·2025

Same author

Single-cell transcriptomics uncovers key immune drivers of vaccine efficacy in cattle.

BMC genomics·2025

Same journal

Transcriptomic analysis reveals FcγR-mediated phagocytosis as a key pathway for the anti-inflammatory action of <i>Polygonatum sibiricum</i> polysaccharides in loach.

Frontiers in genetics·2026

Same journal

A novel <i>ABO</i> splice site variant underlying the A<sub>3</sub> phenotype: immunogenetic basis and functional dissection.

Frontiers in genetics·2026

Same journal

Case Report: Identification of two novel <i>ALMS1</i> variants in a patient with a ciliopathy resembling Alström syndrome.

Frontiers in genetics·2026

Same journal

Integrative analysis identifies Hspa5 as a key regulator of the ERS/UPR-immune axis in spinal cord injury.

Frontiers in genetics·2026

Same journal

Evaluation of genomic selection to improve survival of eastern oysters infected with <i>Perkinsus marinus</i>.

Frontiers in genetics·2026

Same journal

A rescue assay for genetic diagnosis of oculocutaneous albinism using melanocytic MNT1 knock-out cells.

Frontiers in genetics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 21, 2025

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Identification and Classification of Position-specific GABA_A Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

Genomic Prediction of Breeding Values Using a Subset of SNPs Identified by Three Machine Learning Methods.

Bo Li^1,2,3, Nanxi Zhang⁴, You-Gan Wang⁵

¹CSIRO Agriculture and Food, St Lucia, QLD, Australia.

Frontiers in Genetics

|July 20, 2018

Summary

This summary is machine-generated.

Machine learning methods like Random Forests (RF) and Gradient Boosting Machine (GBM) effectively identify important SNPs for genomic prediction in cattle, outperforming other approaches.

Keywords:

beef cattle breeding values genomic prediction live weight machine learning methods single nucleotide polymorphisms

More Related Videos

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Candidate Gene Testing in Clinical Cohort Studies with Multiplexed Genotyping and Mass Spectrometry

Candidate Gene Testing in Clinical Cohort Studies with Multiplexed Genotyping and Mass Spectrometry

Published on: June 21, 2018

Related Experiment Videos

Last Updated: Dec 21, 2025

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Identification and Classification of Position-specific GABA_A Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Candidate Gene Testing in Clinical Cohort Studies with Multiplexed Genotyping and Mass Spectrometry

Candidate Gene Testing in Clinical Cohort Studies with Multiplexed Genotyping and Mass Spectrometry

Published on: June 21, 2018

Area of Science:

Animal Genetics
Bioinformatics
Genomic Prediction

Background:

Genomic data analysis faces challenges like high dimensionality and multicollinearity, often termed 'large P small N'.
Machine learning (ML) methods are adept at handling these complex data structures.
While ML is used in Genome-Wide Association Studies, the application of Gradient Boosting Machine (GBM) and Extreme Gradient Boosting (XgBoost) for SNP selection in genomic prediction remains unexplored.

Purpose of the Study:

To evaluate the efficiency of Random Forests (RF), GBM, and XgBoost in identifying informative SNP subsets for genomic prediction of breeding values in Brahman cattle.
To compare the prediction accuracy of genomic breeding values (GEBVs) derived from selected SNP subsets against those from random SNP subsets and the entire SNP panel.

Main Methods:

Utilized 38,082 SNP markers and body weight phenotypes from 2,093 Brahman cattle (1,097 bulls, 996 cows).
Applied RF, GBM, and XgBoost to identify top 400, 1,000, and 3,000 ranked SNPs.
Constructed genomic relationship matrices (GRMs) using selected SNP subsets for GEBV estimation and compared with random and all-SNP panels.

Main Results:

RF and GBM demonstrated efficiency in identifying SNPs linked to growth traits.
GEBV prediction accuracy using top 3,000 SNPs from RF (0.42) and GBM (0.46) was comparable to using all SNPs (0.43).
RF and GBM subsets significantly outperformed randomly selected, evenly spaced SNP subsets (0.18-0.29), with RF and GBM consistently superior to XgBoost.

Conclusions:

RF and GBM are effective ML methods for selecting informative SNPs for genomic prediction in cattle breeding.
The identified SNP subsets can achieve prediction accuracies similar to using the entire genome-wide SNP panel.
These findings offer valuable insights for optimizing genomic selection strategies by leveraging advanced ML techniques.