Related Experiment Video
Updated: Jun 6, 2025
10:12
High-throughput DNA Extraction and Genotyping of 3dpf Zebrafish Larvae by Fin Clipping
Published on: June 29, 2018
14.0K
Deep learning for genomic selection of aquatic animals.
Yangfan Wang1,2, Ping Ni1, Marc Sturrock3
1MOE Key Laboratory of Marine Genetics and Breeding, Ocean University of China, Qingdao, 266003 China.
Marine Life Science & Technology
|December 2, 2024
Summary
Deep learning (DL) enhances genomic selection (GS) in aquatic animals for faster genetic progress. DL methods improve phenotyping, genotyping, and genomic estimated breeding value (GEBV) prediction, advancing molecular breeding in aquaculture.
Area of Science:
- * Aquaculture and Animal Breeding
- * Bioinformatics and Computational Biology
- * Artificial Intelligence in Genetics
Background:
- * Genomic selection (GS) offers superior accuracy and genetic gain over traditional methods in aquatic animal breeding.
- * Artificial intelligence (AI), particularly deep learning (DL), is increasingly explored for complex trait analysis in GS.
- * Existing DL models show promise but require further integration and validation for broad aquaculture applications.
Purpose of the Study:
- * To review the current applications and future potential of deep learning (DL) in genomic selection (GS) for aquatic animals.
- * To evaluate DL's role in phenotyping, genotyping, and predicting genomic estimated breeding values (GEBV).
- * To discuss the expansion of DL techniques to diverse aquaculture species and breeding programs.
Main Methods:
- * Review of deep learning models including deep neural networks (DNNs), convolutional neural networks (CNNs), and autoencoders.
- * Analysis of DL applications in processing phenotype data, identifying genetic variants (SNP calling), and imputing genotypes.
- * Assessment of DL's capability in predicting genomic estimated breeding values (GEBV) by modeling complex genetic relationships.
Main Results:
- * CNNs efficiently acquire phenotype data from aquatic animals non-invasively.
- * DNNs demonstrate high accuracy as single nucleotide polymorphism (SNP) variant callers for next-generation sequencing (NGS) genotyping.
- * Autoencoder-based imputation and sparse DNNs significantly improve genotype imputation accuracy and GEBV prediction by capturing complex genetic interactions.
Conclusions:
- * Deep learning methods are effective tools for enhancing accuracy and efficiency in aquatic animal genomic selection.
- * DL applications in phenotyping, genotyping, and GEBV prediction are crucial for advancing molecular breeding strategies.
- * Future research should focus on expanding DL applications across more aquaculture species to maximize its potential in the industry.
Related Concept Videos
02:46Genetic Screens
4.9K
Genetic screens are tools used to identify genes and mutations responsible for phenotypes of interest. Genetic screens help identify individuals or a group of people at risk of developing genetic diseases and help them with early intervention, targeted therapy, and reproductive options.
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which...
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which...
4.9K
02:54Evolutionary Relationships through Genome Comparisons
5.7K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
5.7K