TrainSel: An R Package for Selection of Training Populations

Akdemir, Deniz; Rio, Simon; Sánchez, Julio Isidro

doi:10.3389/fgene.2021.655287

Cited by 17 publications

(26 citation statements)

References 42 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental design might need blocking structure and environmental covariates and in these cases, the order in which the individuals are positioned in the environment will be important. We refer to this kind of optimization as the "ordered" optimization as opposed to the “unordered” optimization (Akdemir et al, 2021 ).…”

Section: Populations In Gsmentioning

confidence: 99%

“…Similarly, the package TSDFGS Ou and Liao ( 2019 ) is an R package that focuses on optimization of the TRS by a genetic algorithm (GA) and can be used for TRS optimization based on three built-in design criteria [CDscore, PEVscore, and Pearson correlation (r-score)]. Recently, Akdemir et al ( 2021 ) designed a new package called TrainSel to provide many more options than previous software. For example, TrainSel can select multiple sets from multiple candidate sets, users can specify whether or not the resulting set needs to be ordered, or the power to perform multi-objective optimization.…”

Section: Software Tools For Trs Optimizationmentioning

confidence: 99%

“…Furthermore, it can be also used in combinatorial optimization problems for supervised and also unsupervised learning. The strength of TrainSel is that it combines TRS optimization with a particular experimental design, which has not been implemented in both of the above alternatives by Akdemir et al ( 2021 ).…”

Section: Software Tools For Trs Optimizationmentioning

confidence: 99%

“…For example, if your TS is highly diverse, your TRS must be built to capture that diversity, otherwise, a significant drop in accuracy might occur. That is why targeted optimization approaches are chosen when building TRS (Akdemir and Isidro-Sánchez, 2019 ; Akdemir et al, 2021 ). From Figure 5 we can observe that we get a TRS closest to the TS when we minimize the mean genetic distance (maximize the negative) of TRS to TS.…”

Section: General Guidelines For a Good Trsmentioning

confidence: 99%

See 3 more Smart Citations

Training Set Optimization for Sparse Phenotyping in Genomic Selection: A Conceptual Overview

Sánchez

Akdemir

2021

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

Genomic selection (GS) is becoming an essential tool in breeding programs due to its role in increasing genetic gain per unit time. The design of the training set (TRS) in GS is one of the key steps in the implementation of GS in plant and animal breeding programs mainly because (i) TRS optimization is critical for the efficiency and effectiveness of GS, (ii) breeders test genotypes in multi-year and multi-location trials to select the best-performing ones. In this framework, TRS optimization can help to decrease the number of genotypes to be tested and, therefore, reduce phenotyping cost and time, and (iii) we can obtain better prediction accuracies from optimally selected TRS than an arbitrary TRS. Here, we concentrate the efforts on reviewing the lessons learned from TRS optimization studies and their impact on crop breeding and discuss important features for the success of TRS optimization under different scenarios. In this article, we review the lessons learned from training population optimization in plants and the major challenges associated with the optimization of GS including population size, the relationship between training and test set (TS), update of TRS, and the use of different packages and algorithms for TRS implementation in GS. Finally, we describe general guidelines to improving the rate of genetic improvement by maximizing the use of the TRS optimization in the GS framework.

show abstract

Section: Populations In Gsmentioning

confidence: 99%

Section: Software Tools For Trs Optimizationmentioning

confidence: 99%

Section: Software Tools For Trs Optimizationmentioning

confidence: 99%

Section: General Guidelines For a Good Trsmentioning

confidence: 99%

See 2 more Smart Citations

Training Set Optimization for Sparse Phenotyping in Genomic Selection: A Conceptual Overview

Sánchez

Akdemir

2021

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Two optimization algorithms, mean of the coefficient of determination (CDmean) and mean of predictor error variance (PEVmean) proposed by Rincent et al [ 46 ] were implemented in R the package TrainSel [ 65 ] to design the training population. A randomly sampled training population was also applied and compared with these optimized training populations generated by CDmean and PEVmean.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Genomic Prediction for Fusarium Head Blight Resistance with a Multi-Parental Population

Zhang

Boyle

Brûlé‐Babel

et al. 2021

Biology

View full text Add to dashboard Cite

Fusarium head blight (FHB) resistance is quantitatively inherited, controlled by multiple minor effect genes, and highly affected by the interaction of genotype and environment. This makes genomic selection (GS) that uses genome-wide molecular marker data to predict the genetic breeding value as a promising approach to select superior lines with better resistance. However, various factors can affect accuracies of GS and better understanding how these factors affect GS accuracies could ensure the success of applying GS to improve FHB resistance in wheat. In this study, we performed a comprehensive evaluation of factors that affect GS accuracies with a multi-parental population designed for FHB resistance. We found larger sample sizes could get better accuracies. Training population designed by CDmean based optimization algorithms significantly increased accuracies than random sampling approach, while mean of predictor error variance (PEVmean) had the poorest performance. Different genomic selection models performed similarly for accuracies. Including prior known large effect quantitative trait loci (QTL) as fixed effect into the GS model considerably improved the predictability. Multi-traits models had almost no effects, while the multi-environment model outperformed the single environment model for prediction across different environments. By comparing within and across family prediction, better accuracies were obtained with the training population more closely related to the testing population. However, achieving good accuracies for GS prediction across populations is still a challenging issue for GS application.

show abstract

Building a Calibration Set for Genomic Prediction, Characteristics to Be Considered, and Optimization Approaches

Rio

Charcosset

Mary‐Huard

et al. 2022

Methods in Molecular Biology

Self Cite

View full text Add to dashboard Cite

The efficiency of genomic selection strongly depends on the prediction accuracy of the genetic merit of candidates. Numerous papers have shown that the composition of the calibration set is a key contributor to prediction accuracy. A poorly defined calibration set can result in low accuracies, whereas an optimized one can considerably increase accuracy compared to random sampling, for a same size. Alternatively, optimizing the calibration set can be a way of decreasing the costs of phenotyping by enabling similar levels of accuracy compared to random sampling but with fewer phenotypic units. We present here the different factors that have to be considered when designing a calibration set, and review the different criteria proposed in the literature. We classified these criteria into two groups: model-free criteria based on relatedness, and criteria derived from the linear mixed model. We introduce criteria targeting specific prediction objectives including the prediction of highly diverse panels, biparental families, or hybrids. We also review different ways of updating the calibration set, and different procedures for optimizing phenotyping experimental designs.

show abstract

TrainSel: An R Package for Selection of Training Populations

Cited by 17 publications

References 42 publications

Training Set Optimization for Sparse Phenotyping in Genomic Selection: A Conceptual Overview

Training Set Optimization for Sparse Phenotyping in Genomic Selection: A Conceptual Overview

Evaluation of Genomic Prediction for Fusarium Head Blight Resistance with a Multi-Parental Population

Building a Calibration Set for Genomic Prediction, Characteristics to Be Considered, and Optimization Approaches

Contact Info

Product

Resources

About