Smart breeding driven by big data, artificial intelligence, and integrated genomic-enviromic prediction

Molecular Plant, Journal Year: 2022, Volume and Issue: 15(11), P. 1664 - 1695

Published: Sept. 7, 2022

The first paradigm of plant breeding involves direct selection-based phenotypic observation, followed by predictive using statistical models for quantitative traits constructed based on genetic experimental design and, more recently, incorporation molecular marker genotypes. However, performance or phenotype (P) is determined the combined effects genotype (G), envirotype (E), and environment interaction (GEI). Phenotypes can be predicted precisely training a model data collected from multiple sources, including spatiotemporal omics (genomics, phenomics, enviromics across time space). Integration 3D information profiles (G-P-E), each with multidimensionality, provides both tremendous opportunities great challenges. Here, we review innovative technologies breeding. We then evaluate multidimensional that integrated strategy, particularly envirotypic data, which have largely been neglected in collection are nearly untouched construction. propose smart scheme, genomic-enviromic prediction (iGEP), as an extension genomic prediction, multiomics information, big technology, artificial intelligence (mainly focused machine deep learning). discuss how to implement iGEP, models, environmental indices, factorial structure cross-species prediction. A strategy proposed prediction-based crop redesign at macro (individual, population, species) micro (gene, metabolism, network) scales. Finally, provide perspectives translating into gain through integrative platforms open-source initiatives. call coordinated efforts institutional partnerships, technological support.

Language: Английский

---

A Comprehensive Review of High Throughput Phenotyping and Machine Learning for Plant Stress Phenotyping

Phenomics, Journal Year: 2022, Volume and Issue: 2(3), P. 156 - 183

Published: April 4, 2022

Language: Английский

---

Important wheat diseases in the US and their management in the 21st century

Frontiers in Plant Science, Journal Year: 2023, Volume and Issue: 13

Published: Jan. 12, 2023

Wheat is a crop of historical significance, as it marks the turning point human civilization 10,000 years ago with its domestication. Due to rapid increase in population, wheat production needs be increased by 50% 2050 and this growth will mainly based on yield increases, there strong competition for scarce productive arable land from other sectors. This increasing demand can further achieved using sustainable approaches including integrated disease pest management, adaption warmer climates, less use water resources frequency abiotic stress tolerances. Out 200 diseases wheat, 50 cause economic losses are widely distributed. Each year, about 20% lost due diseases. Some major rusts, smut, tan spot, spot blotch, fusarium head blight, common root rot, septoria powdery mildew, blast, several viral, nematode, bacterial These badly impact mortality plants. review focuses important present United States, comprehensive information causal organism, damage, symptoms host range, favorable conditions, management strategies. Furthermore, genetic breeding efforts control manage these discussed. A detailed description all QTLs, genes reported cloned provided review. study utmost importance programs throughout world breed resistance under changing environmental conditions.

Language: Английский

---

Consensus genomic regions associated with multiple abiotic stress tolerance in wheat and implications for wheat breeding

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Aug. 11, 2022

In wheat, a meta-analysis was performed using previously identified QTLs associated with drought stress (DS), heat (HS), salinity (SS), water-logging (WS), pre-harvest sprouting (PHS), and aluminium (AS) which predicted total of 134 meta-QTLs (MQTLs) that involved at least 28 consistent stable MQTLs conferring tolerance to five or all six abiotic stresses under study. Seventy-six out the 132 physically anchored were also verified genome-wide association studies. Around 43% had genetic physical confidence intervals less than 1 cM 5 Mb, respectively. Consequently, 539 genes in some selected providing 6 stresses. Comparative analysis underlying four RNA-seq based transcriptomic datasets unravelled 189 differentially expressed included 11 most promising candidate common among different datasets. The promoter showed promoters these include many responsiveness cis-regulatory elements, such as ARE, MBS, TC-rich repeats, As-1 element, STRE, LTR, WRE3, WUN-motif others. Further, overlapped 34 known genes. addition, numerous ortho-MQTLs maize, rice genomes discovered. These findings could help fine mapping gene cloning, well marker-assisted breeding for multiple tolerances wheat.

Language: Английский

---

Genome Editing and Improvement of Abiotic Stress Tolerance in Crop Plants

Life, Journal Year: 2023, Volume and Issue: 13(7), P. 1456 - 1456

Published: June 27, 2023

Genome editing aims to revolutionise plant breeding and could assist in safeguarding the global food supply. The inclusion of a 12–40 bp recognition site makes mega nucleases first tools utilized for genome generation gene-editing tools. Zinc finger (ZFNs) are second technique, because they create double-stranded breaks, more dependable effective. ZFNs were original designed nuclease-based approach editing. Cys2-His2 zinc domain’s discovery made this technique possible. Clustered regularly interspaced short palindromic repeats (CRISPR) improve genetics, boost biomass production, increase nutrient usage efficiency, develop disease resistance. Plant genomes can be effectively modified using genome-editing technologies enhance characteristics without introducing foreign DNA into genome. Next-generation will soon defined by these exact methods. There is abroad promise that genome-edited crops essential years come improving sustainability climate-change resilience systems. This method also has great potential enhancing crops’ resistance various abiotic stressors. In review paper, we summarize most recent findings about mechanism stress response crop plants use CRISPR/Cas mediated systems tolerance stresses including drought, salinity, cold, heat, heavy metals.

Language: Английский

---

Wheat end-use quality: State of art, genetics, genomics-assisted improvement, future challenges, and opportunities

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

Published: Jan. 5, 2023

Wheat is the most important source of food, feed, and nutrition for humans livestock around world. The expanding population has increasing demands various wheat products with different quality attributes requiring development cultivars that fulfills specific end-users including millers bakers in international market. Therefore, breeding programs continually strive to meet these standards by screening their improved lines every year. However, direct measurement end-use traits such as milling baking qualities requires a large quantity grain, traits-specific expensive instruments, time, an expert workforce which limits process. With advancement sequencing technologies, study entire plant genome possible, genetic mapping techniques quantitative trait locus genome-wide association studies have enabled researchers identify loci/genes associated wheat. Modern marker-assisted selection genomic allow utilization resources prediction high accuracy efficiency speeds up crop improvement cultivar endeavors. In addition, candidate gene approach through functional well comparative genomics facilitated translation information from several species wild relatives This review discusses wheat, control mechanisms, use genetics approaches improvement, future challenges opportunities breeding.

Language: Английский

---

Crop genomic selection with deep learning and environmental data: A survey

Frontiers in Artificial Intelligence, Journal Year: 2023, Volume and Issue: 5

Published: Jan. 10, 2023

Machine learning techniques for crop genomic selections, especially single-environment plants, are well-developed. These machine models, which use dense genome-wide markers to predict phenotype, routinely perform well on datasets, complex traits affected by multiple markers. On the other hand, models predicting deep using datasets that span different environmental conditions, have only recently emerged. Models can accept heterogeneous data sources, such as temperature, soil conditions and precipitation, natural choices modeling GxE in multi-environment prediction. Here, we review emerging incorporate directly into selection models.

Language: Английский

---

GWAS and genomic prediction for pre-harvest sprouting tolerance involving sprouting score and two other related traits in spring wheat

Molecular Breeding, Journal Year: 2023, Volume and Issue: 43(3)

Published: Feb. 20, 2023

Language: Английский

---

Utilizing genomic prediction to boost hybrid performance in a sweet corn breeding program

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: April 25, 2024

Sweet corn breeding programs, like field corn, focus on the development of elite inbred lines to produce commercial hybrids. For this reason, genomic selection models can help in silico prediction hybrid crosses from lines, which is hypothesized improve test cross scheme, leading higher genetic gain a program. This study aimed explore potential implementing sweet program through within-site across-year and across-site framework. A total 506 hybrids were evaluated six environments (California, Florida, Wisconsin, years 2020 2021). 20 traits three different groups measured (plant-, ear-, flavor-related traits) across environments. Eight statistical considered for prediction, as combination two (GBLUP RKHS) with kernels (additive additive + dominance), single- multi-trait Also, cross-validation schemes tested (CV1, CV0, CV00). The then compared based correlation between estimated values/total values phenotypic measurements. Overall, heritabilities correlations varied among traits. implemented showed good accuracies trait prediction. GBLUP implementation outperformed RKHS all models. Models plus dominance presented slight improvement over only some examined. In addition, performed better CV0 than CV00 average. Hence, should be standard model we found that reliable results, testcross stage by identifying top candidates will reach advanced field-testing stages.

Language: Английский

---

Genomic Prediction of Wheat Grain Yield Using Machine Learning

Agriculture, Journal Year: 2022, Volume and Issue: 12(9), P. 1406 - 1406

Published: Sept. 6, 2022

Genomic Prediction (GP) is a powerful approach for inferring complex phenotypes from genetic markers. GP critical improving grain yield, particularly staple crops such as wheat and rice, which are crucial to feeding the world. While machine learning (ML) models have recently started be applied in GP, it often unclear what best algorithms how their results affected by feature selection (FS) methods. Here, we compared ML deep (DL) with classical Bayesian approaches, across range of different FS methods, performance predicting yield (in three datasets). Model was generally more prediction algorithm than method. Among all models, obtained tree-based methods (random forests gradient boosting) However, latter prone fitting problems. This issue also observed developed features selected BayesA, only method used here. Nonetheless, other led no problem but similar performance. Thus, our indicate that choice important developing highly predictive models. Moreover, concluded random boosting generate robust

Language: Английский

---