Ridge regression and deep learning models for genomewide selection of complex traits in New Mexican chile peppers DOI Creative Commons
Dennis N. Lozada, Karansher Singh Sandhu, Madhav Bhatta

et al.

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: June 27, 2023

Abstract Background. Genomewide prediction estimates the genomic breeding values of selection candidates which can be utilized for population improvement and cultivar development. Ridge regression deep learning-based models were implemented yield agronomic traits 204 chile pepper genotypes evaluated in multi-environment trials New Mexico, USA. Results. Accuracy differed across different under five-fold cross-validations, where high accuracy was observed highly heritable such as plant height width. No model superior using 14,922 SNP markers genomewide selection. Bayesian ridge had highest average first pod date (0.77) total per (0.33). Multilayer perceptron (MLP) most flowering time (0.76) (0.73), whereas BLUP width (0.62). Using a subset 7,690 loci resulting from grouping based on linkage disequilibrium coefficients resulted improved date, ten weight, plant, even relatively small training size MLP random forest models. Genomic sufficient optimal accuracies size. Combining phenotypic response yield-related traits, indicating that integrated approaches result gains achieved through Conclusions. learning demonstrate potential implementing genetic programs. Ultimately, large data is relevant

Language: Английский

AI-driven aquaculture: A review of technological innovations and their sustainable impacts DOI Creative Commons
Hang Yang, Feng Qi, Shibin Xia

et al.

Artificial Intelligence in Agriculture, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

1
Genetics and Genomics of Infectious Diseases in Key Aquaculture Species DOI Creative Commons
Nguyen Hong Nguyen

Biology, Journal Year: 2024, Volume and Issue: 13(1), P. 29 - 29

Published: Jan. 4, 2024

Diseases pose a significant and pressing concern for the sustainable development of aquaculture sector, particularly as their impact continues to grow due climatic shifts such rising water temperatures. While various approaches, ranging from biosecurity measures vaccines, have been devised combat infectious diseases, efficacy is disease species specific contingent upon multitude factors. The fields genetics genomics offer effective tools control prevent outbreaks in aquatic animal species. In this study, we present key findings our recent research, focusing on genetic resistance three diseases: White Spot Syndrome Virus (WSSV) white shrimp, Bacterial Necrotic Pancreatitis (BNP) striped catfish, skin fluke (a parasitic ailment) yellowtail kingfish. Our investigations reveal that all possess substantial heritable components disease-resistant traits, indicating potential responsiveness artificial selection improvement programs tailored these diseases. Also, observed high association between traits survival rates. Through selective breeding aimed at enhancing pathogens, achieved gains, averaging 10% per generation. These also contributed positively overall production performance productivity Although effects immunological or immune responses were not they yielded favorable results catfish. Furthermore, genomic analyses, including shallow genome sequencing pedigreed populations, enriched understanding architecture underlying traits. are primarily governed by polygenic nature, with numerous genes variants, each small effects. Leveraging range advanced statistical methods, mixed models machine deep learning, developed prediction demonstrated moderate-to-high levels accuracy forecasting disease-related addition genomics, RNA-seq experiments identified several undergo upregulation response infection viral loads within populations. Preliminary microbiome data, while offering limited predictive one studied species, underscore combining data sequence information enhance power Lastly, paper briefly discusses roles precision agriculture systems AI algorithms outlines path future research expedite lines target conclusion, study underscores critical role fortifying sector against threats posed paving way more resilient development.

Language: Английский

Citations

7
Multi-Trait Genomic Prediction of Meat Yield in Pacific Whiteleg Shrimp (Penaeus vannamei) DOI Creative Commons
Shiwei Zhang,

Jie Kong,

Jian Tan

et al.

Animals, Journal Year: 2025, Volume and Issue: 15(8), P. 1165 - 1165

Published: April 18, 2025

The meat yield (MY) is a key economic trait in Pacific whiteleg shrimp (Penaeus vannamei) breeding, necessitating accurate genomic prediction for efficient genetic improvement. In this study, we investigated single-trait (STGMs) and multi-trait models (MTGMs) predicting MY related traits, using two cross-validation strategies reflecting different data-availability scenarios. A total of 899 individuals from 63 full-sibling families were phenotyped MY, net weight (MW), body (BW), length (BL), abdominal segment (AL). We estimated the heritability correlations traits P. vannamei, followed by comparing accuracy STGMs MTGMs MW. Two validation approaches then applied: CV1 retained auxiliary sets, CV2 excluded both target traits. Heritability estimates indicated that had low (STGM: 0.160; MTGMs: 0.145–0.156), whereas MW, BW, BL, AL showed low-to-moderate (0.099–0.204). Genetic revealed strong associations between MW/BW/BL (rg = 0.605–0.783), yet positive correlation with 0.286). Across all comparisons, consistently surpassed STGMs. For improved 4.8–58.8% relative to STGM (0.187), MY-MW model achieving highest (0.297) under CV1. Similarly, enhanced MW 36.6–138.2% over (0.254), MW-BW reaching (0.605) Notably, retaining (CV1) boosted gains substantially (up 138.2%), excluding them (CV2) yielded only marginal improvements (≤8.6%). Moreover, incorporating as an increased BL 5.4–7.6%, indicating its synergistic value MTGMs. Overall, these results demonstrate markedly enhance carcass compared STGMs, particularly when data are accessible (CV1). findings underscore importance maintaining records breeding populations, offering robust framework improving vannamei through models.

Language: Английский

Citations

0
Integrated Approach in Genomic Selection to Accelerate Genetic Gain in Sugarcane DOI Creative Commons
Karansher Singh Sandhu, Aalok Shiv, Gurleen Kaur

et al.

Plants, Journal Year: 2022, Volume and Issue: 11(16), P. 2139 - 2139

Published: Aug. 17, 2022

Marker-assisted selection (MAS) has been widely used in the last few decades plant breeding programs for mapping and introgression of genes economically important traits, which enabled development a number superior cultivars different crops. In sugarcane, is most source sugar bioethanol, marker work was initiated long ago; however, marker-assisted sugarcane lagging, mainly due to its large complex genome, high levels polyploidy heterozygosity, varied chromosomes, use low/medium-density markers. Genomic (GS) proven technology animal recently incorporated programs. GS potential tool rapid genotypes accelerating cycle. However, full could be realized by an integrated approach combining high-throughput phenotyping, genotyping, machine learning, speed with genomic selection. For better understanding integration, we comprehensively discuss concept genetic gain through breeder’s equation, methodology, prediction models, current status challenges accuracy, GS, phenotyping (HTP), genotyping (HTG), followed prospective applications improvement.

Language: Английский

Citations

18
Ridge regression and deep learning models for genome-wide selection of complex traits in New Mexican Chile peppers DOI Creative Commons
Dennis N. Lozada, Karansher Singh Sandhu, Madhav Bhatta

et al.

BMC Genomic Data, Journal Year: 2023, Volume and Issue: 24(1)

Published: Dec. 18, 2023

Abstract Background Genomewide prediction estimates the genomic breeding values of selection candidates which can be utilized for population improvement and cultivar development. Ridge regression deep learning-based models were implemented yield agronomic traits 204 chile pepper genotypes evaluated in multi-environment trials New Mexico, USA. Results Accuracy differed across different under ten-fold cross-validations, where high accuracy was observed highly heritable such as plant height width. No model superior using 14,922 SNP markers genomewide selection. Bayesian ridge had highest average first pod date (0.77) total per (0.33). Multilayer perceptron (MLP) most flowering time (0.76) (0.73), whereas BLUP width (0.62). Using a subset 7,690 loci resulting from grouping based on linkage disequilibrium coefficients resulted improved date, ten weight, plant, even relatively small training size MLP random forest models. Genomic sufficient optimal accuracies size. Combining phenotypic response yield-related traits, indicating that integrated approaches result gains achieved through Conclusions learning demonstrate potential implementing genetic programs. Ultimately, large data is relevant

Language: Английский

Citations

5
Breeding evaluations in aquaculture using neural networks DOI Creative Commons
Christos Palaiokostas

Aquaculture Reports, Journal Year: 2024, Volume and Issue: 39, P. 102468 - 102468

Published: Nov. 15, 2024

Language: Английский

Citations

1
Effects of common full-sib families on accuracy of genomic prediction for tagging weight in striped catfish Pangasianodon hypophthalmus DOI Creative Commons
Nguyen Thanh Vu,

Trần Hữu Phúc,

Nguyen Hong Nguyen

et al.

Frontiers in Genetics, Journal Year: 2023, Volume and Issue: 13

Published: Jan. 4, 2023

Common full-sib families (c2 ) make up a substantial proportion of total phenotypic variation in traits commercial importance aquaculture species and omission or inclusion the c2 resulted possible changes genetic parameter estimates re-ranking estimated breeding values. However, impacts common on accuracy genomic prediction for economic are not well known many species, including aquatic animals. This research explored tagging weight population striped catfish comprising 11,918 fish traced back to base (four generations), which 560 individuals had genotype records 14,154 SNPs. Our single step best linear unbiased (ssGLBUP) showed that was reduced by 96.5%-130.3% when were included statistical models. The reduction smaller extent multivariate analysis than univariate Imputation missing genotypes somewhat upward biases weight. It is therefore suggested evaluation models recorded during early phase growth development should account minimise hence, selection response.

Language: Английский

Citations

3
Effectiveness of SNPs for Sibship Assignment in Farmed Banana Shrimp (Penaeus merguiensis) DOI Creative Commons
Chontida Phuthaworn, Nguyen Hong Nguyen, Wayne Knibb

et al.

Journal of Marine Science and Engineering, Journal Year: 2023, Volume and Issue: 11(7), P. 1281 - 1281

Published: June 24, 2023

Pedigrees are essential components in selective breeding programs to manage genetic diversity and obtain accurate parameter estimates ensure long-term response selection captive populations. High throughput cost-effective sequencing technologies has offered opportunities of using single nucleotide polymorphisms (SNPs) resolve penaeid shrimp pedigrees from mass spawning cohorts communal rearing. Effects SNPs for sibship assignment were investigated on 546 two software programs, Colony Sequoia. Assignment rates accuracies SNP subsets with six different minor allele frequencies (MAFs), four sets SNPs, five genotyping error compared the microsatellite-based pedigree established a previous study. MAFs numbers contributed significant increases accuracies, whereas showed negligible impacts results. Sibship assignments achieved 98% 83%, respectively, minimum number 91 (average MAF ≥ 0.14), exhibited similar resulting patterns subsets. consistencies between SNP-based that could be by thus contribute farmed banana shrimp.

Language: Английский

Citations

3
100 years domestication of penaeid shrimp and meta-analysis of breeding traits DOI
Shengjie Ren, José M. Yáñez, Ricardo Pérez-Enríquez

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: June 27, 2024

Abstract Penaeid shrimp farming plays a pivotal role in ensuring future food security and promoting economic sustainability. Compared to the extensive long history of domestication observed terrestrial agriculture species, selective breeding penaeids are relatively recent endeavors. Selective aimed at improving production traits holds significant promise for enhancing efficiency reducing environmental impact farming, thereby contributing its long-term Assessing genotype-by-environment (G-by-E) interactions is essential programs ensure that improved penaeid strains perform consistently across different environments, with genomic selection proving more effective than sib-testing alone mitigating sensitivity. Genome editing tools like CRISPR/Cas9 offer potential accelerate genetic gains by enabling rapid introduction desired changes, advancements showing promising results achieving high transfection embryos. Additionally, artificial intelligence machine learning being leveraged streamline phenotyping enhance decision-making accuracy managing predicting disease outbreaks. Herein, we provide an overview update on shrimp, including current status principal farmed key milestones history, targeted programs, advantages integrating genomeic traits, directions shrimp.

Language: Английский

Citations

0
Genetics and Genomics of Infectious Diseases in Key Aquaculture Species DOI Open Access
Nguyen Hong Nguyen

Published: Dec. 6, 2023

Diseases pose a significant and pressing concern for the sustainable development of aquaculture sector, particularly as their impact continues to grow due climatic shifts such rising water temperatures. While various approaches, ranging from biosecurity measures vaccines, have been devised combat infectious diseases, efficacy is disease- species-specific contingent upon multitude factors. The field genetics genomics offer effective tools control prevent disease outbreaks in aquatic animal species. In this study, we present key findings our recent research, focusing on genetic resistance three specific diseases: White Spot Syndrome Virus WSSV) white shrimp, Bacterial Necrotic Pancreatitis (BNP) striped catfish skin fluke (a parasitic ailment) yellowtail kingfish. Our investigations reveal that all species possess substantial heritable components resistant traits, indicating potential responsiveness artificial selection improvement programs tailored these diseases. Also, observed high association between traits survival rates. Through selective breeding aimed at enhancing pathogens, achieved gains, averaging 10% per generation. These also contributed positively overall production performance productivity Although effects immunological or immune responses were not they yielded favourable results catfish. Furthermore, genomic analyses, including shallow genome sequencing pedigreed populations, enriched understanding architecture underlying traits. are primarily governed by polygenic nature, with numerous genes variants, each small effects. Leveraging range advanced statistical methods, mixed models machine deep learning, developed prediction demonstrated moderate levels accuracy forecasting disease-related addition genomics, RNA-seq experiments identified several undergo upregulation response infection viral loads within populations. Preliminary microbiome data, while offering limited predictive one studied species, underscore combining data sequence information enhance power Lastly, paper briefly discusses roles precision agriculture systems, AI algorithms, outlines path future research expedite disease-resistant lines target conclusion, study underscores critical role fortifying sector against threats posed paving way more resilient development.

Language: Английский

Citations

1