Predictive breeding for maize: Making use of molecular phenotypes, machine learning, and physiological crop models

Washburn, Jacob D.; Burch, Merritt B.; Franco, José A. Valdes

doi:10.1002/csc2.20052

Cited by 37 publications

(30 citation statements)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent study in semi-winter rapeseed demonstrated that already low-density marker sets comprising a few hundred to thousand markers enable high prediction accuracies in breeding populations with strong LD (Werner et al 2018 ). As reviewed by Washburn et al ( 2020 ), key improvements of genomic prediction might come from high‐throughput phenotyping, the use of molecular phenotypes and/or component traits, machine learning methodologies, and replacing individual genetic markers with high‐quality haplotype data.…”

Section: Discussionmentioning

confidence: 99%

Multi-omics-based prediction of hybrid performance in canola

et al. 2021

View full text Add to dashboard Cite

Key message Complementing or replacing genetic markers with transcriptomic data and use of reproducing kernel Hilbert space regression based on Gaussian kernels increases hybrid prediction accuracies for complex agronomic traits in canola. In plant breeding, hybrids gained particular importance due to heterosis, the superior performance of offspring compared to their inbred parents. Since the development of new top performing hybrids requires labour-intensive and costly breeding programmes, including testing of large numbers of experimental hybrids, the prediction of hybrid performance is of utmost interest to plant breeders. In this study, we tested the effectiveness of hybrid prediction models in spring-type oilseed rape (Brassica napus L./canola) employing different omics profiles, individually and in combination. To this end, a population of 950 F1 hybrids was evaluated for seed yield and six other agronomically relevant traits in commercial field trials at several locations throughout Europe. A subset of these hybrids was also evaluated in a climatized glasshouse regarding early biomass production. For each of the 477 parental rapeseed lines, 13,201 single nucleotide polymorphisms (SNPs), 154 primary metabolites, and 19,479 transcripts were determined and used as predictive variables. Both, SNP markers and transcripts, effectively predict hybrid performance using (genomic) best linear unbiased prediction models (gBLUP). Compared to models using pure genetic markers, models incorporating transcriptome data resulted in significantly higher prediction accuracies for five out of seven agronomic traits, indicating that transcripts carry important information beyond genomic data. Notably, reproducing kernel Hilbert space regression based on Gaussian kernels significantly exceeded the predictive abilities of gBLUP models for six of the seven agronomic traits, demonstrating its potential for implementation in future canola breeding programmes.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-omics-based prediction of hybrid performance in canola

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Notably, report that the performance of multi-trait and multi-environment deep learning (MTDL) is commensurate with that of the Bayesian multi-trait and multi-environment approach. Ersoz et al (2020) and Washburn et al (2020) review machine-learning approaches in crop improvement.…”

Section: Explaining and Simulating G × E × M Interactionsmentioning

confidence: 99%

CGIAR modeling approaches for resource‐constrained scenarios: I. Accelerating crop breeding for a changing climate

et al. 2020

View full text Add to dashboard Cite

Crop improvement efforts aiming at increasing crop production (quantity, quality) and adapting to climate change have been subject of active research over the past years. But, the question remains 'to what extent can breeding gains be achieved under a changing climate, at a pace sufficient to usefully contribute to climate adaptation, mitigation and food security?'. Here, we address this question by critically reviewing how model-based approaches can be used to assist breeding activities, with

show abstract

“…Prediction of phenotypes from a combination of environmental (E), genetic (G), and humanimposed (often referred to as management(M)) conditions has been a long standing challenge in biology and related fields (Messina et al 2009(Messina et al , 2018Technow et al 2015;Cooper et al 2016Cooper et al , 2021Varshney et al 2017;Washburn et al 2020;Jarquin et al 2021;Li et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Predicting phenotypes from genetic, environment, management, and historical data using CNNs

Washburn

Çimen

Ramstein

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Predicting phenotypes from genetic (G), environmental (E), and management (M) conditions is a long-standing challenge with implications to agriculture, medicine, and conservation. Most methods reduce the factors in a dataset (feature engineering) in a subjective and potentially oversimplified manner. Convolutional Neural Networks (CNN) can overcome this by allowing the data itself to determine which factors are most important. CNN models were developed for predicting agronomic yield from a combination of replicated trials and historical yield survey data. The results were more accurate than standard methods when tested on heldout G, E, and M data (r=0.5 vs r=0.4), and performed slightly worse than standard methods when only G was held out (r=0.74 vs r=0.78). Pre-training on historical data increased accuracy by 1-36% compared to trial data alone. Saliency map analysis indicated the CNN has "learned" to prioritize many factors of known agricultural importance.

show abstract

Predictive breeding for maize: Making use of molecular phenotypes, machine learning, and physiological crop models

Cited by 37 publications

References 138 publications

Multi-omics-based prediction of hybrid performance in canola

Multi-omics-based prediction of hybrid performance in canola

CGIAR modeling approaches for resource‐constrained scenarios: I. Accelerating crop breeding for a changing climate

Predicting phenotypes from genetic, environment, management, and historical data using CNNs

Contact Info

Product

Resources

About