Feature engineering of environmental covariates improves plant genomic-enabled prediction

Introduction: Because Genomic selection (GS) is a predictive methodology, it needs to guarantee high-prediction accuracies for practical implementations. However, since many factors affect the prediction performance of this methodology, its practical implementation still needs to be improved in many...

Descripción completa

Detalles Bibliográficos
Autores principales: Montesinos-Lopez, Osval A., Crespo-Herrera, Leonardo A., Saint Pierre, Carolina, Cano-Paez, Bernabe, Huerta Prado, Gloria Isabel, Mosqueda-Gonzalez, Brandon Alejandro, Ramos-Pulido, Sofia, Gerard, Guillermo S., Khalid Alnowibet, Fritsche-Neto, Roberto, Montesinos-Lopez, Abelardo, Crossa, José
Formato: Journal Article
Lenguaje:Inglés
Publicado: Frontiers Media 2024
Materias:
Acceso en línea:https://hdl.handle.net/10568/149160
_version_ 1855534945584283648
author Montesinos-Lopez, Osval A.
Crespo-Herrera, Leonardo A.
Saint Pierre, Carolina
Cano-Paez, Bernabe
Huerta Prado, Gloria Isabel
Mosqueda-Gonzalez, Brandon Alejandro
Ramos-Pulido, Sofia
Gerard, Guillermo S.
Khalid Alnowibet
Fritsche-Neto, Roberto
Montesinos-Lopez, Abelardo
Crossa, José
author_browse Cano-Paez, Bernabe
Crespo-Herrera, Leonardo A.
Crossa, José
Fritsche-Neto, Roberto
Gerard, Guillermo S.
Huerta Prado, Gloria Isabel
Khalid Alnowibet
Montesinos-Lopez, Abelardo
Montesinos-Lopez, Osval A.
Mosqueda-Gonzalez, Brandon Alejandro
Ramos-Pulido, Sofia
Saint Pierre, Carolina
author_facet Montesinos-Lopez, Osval A.
Crespo-Herrera, Leonardo A.
Saint Pierre, Carolina
Cano-Paez, Bernabe
Huerta Prado, Gloria Isabel
Mosqueda-Gonzalez, Brandon Alejandro
Ramos-Pulido, Sofia
Gerard, Guillermo S.
Khalid Alnowibet
Fritsche-Neto, Roberto
Montesinos-Lopez, Abelardo
Crossa, José
author_sort Montesinos-Lopez, Osval A.
collection Repository of Agricultural Research Outputs (CGSpace)
description Introduction: Because Genomic selection (GS) is a predictive methodology, it needs to guarantee high-prediction accuracies for practical implementations. However, since many factors affect the prediction performance of this methodology, its practical implementation still needs to be improved in many breeding programs. For this reason, many strategies have been explored to improve the prediction performance of this methodology. Methods: When environmental covariates are incorporated as inputs in the genomic prediction models, this information only sometimes helps increase prediction performance. For this reason, this investigation explores the use of feature engineering on the environmental covariates to enhance the prediction performance of genomic prediction models. Results and discussion: We found that across data sets, feature engineering helps reduce prediction error regarding only the inclusion of the environmental covariates without feature engineering by 761.625% across predictors. These results are very promising regarding the potential of feature engineering to enhance prediction accuracy. However, since a significant gain in prediction accuracy was observed in only some data sets, further research is required to guarantee a robust feature engineering strategy to incorporate the environmental covariates.
format Journal Article
id CGSpace149160
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Frontiers Media
publisherStr Frontiers Media
record_format dspace
spelling CGSpace1491602025-12-08T10:29:22Z Feature engineering of environmental covariates improves plant genomic-enabled prediction Montesinos-Lopez, Osval A. Crespo-Herrera, Leonardo A. Saint Pierre, Carolina Cano-Paez, Bernabe Huerta Prado, Gloria Isabel Mosqueda-Gonzalez, Brandon Alejandro Ramos-Pulido, Sofia Gerard, Guillermo S. Khalid Alnowibet Fritsche-Neto, Roberto Montesinos-Lopez, Abelardo Crossa, José engineering selection marker-assisted selection plant breeding Introduction: Because Genomic selection (GS) is a predictive methodology, it needs to guarantee high-prediction accuracies for practical implementations. However, since many factors affect the prediction performance of this methodology, its practical implementation still needs to be improved in many breeding programs. For this reason, many strategies have been explored to improve the prediction performance of this methodology. Methods: When environmental covariates are incorporated as inputs in the genomic prediction models, this information only sometimes helps increase prediction performance. For this reason, this investigation explores the use of feature engineering on the environmental covariates to enhance the prediction performance of genomic prediction models. Results and discussion: We found that across data sets, feature engineering helps reduce prediction error regarding only the inclusion of the environmental covariates without feature engineering by 761.625% across predictors. These results are very promising regarding the potential of feature engineering to enhance prediction accuracy. However, since a significant gain in prediction accuracy was observed in only some data sets, further research is required to guarantee a robust feature engineering strategy to incorporate the environmental covariates. 2024-05 2024-07-19T15:19:42Z 2024-07-19T15:19:42Z Journal Article https://hdl.handle.net/10568/149160 en Open Access application/pdf Frontiers Media Montesinos-López, O. A., Crespo-Herrera, L., Pierre, C. S., Cano-Paez, B., Huerta-Prado, G. I., Mosqueda-González, B. A., Ramos-Pulido, S., Gerard, G., Alnowibet, K., Fritsche-Neto, R., Montesinos-López, A., & Crossa, J. (2024). Feature engineering of environmental covariates improves plant genomic-enabled prediction. Frontiers in Plant Science, 15, 1349569. https://doi.org/10.3389/fpls.2024.1349569
spellingShingle engineering
selection
marker-assisted selection
plant breeding
Montesinos-Lopez, Osval A.
Crespo-Herrera, Leonardo A.
Saint Pierre, Carolina
Cano-Paez, Bernabe
Huerta Prado, Gloria Isabel
Mosqueda-Gonzalez, Brandon Alejandro
Ramos-Pulido, Sofia
Gerard, Guillermo S.
Khalid Alnowibet
Fritsche-Neto, Roberto
Montesinos-Lopez, Abelardo
Crossa, José
Feature engineering of environmental covariates improves plant genomic-enabled prediction
title Feature engineering of environmental covariates improves plant genomic-enabled prediction
title_full Feature engineering of environmental covariates improves plant genomic-enabled prediction
title_fullStr Feature engineering of environmental covariates improves plant genomic-enabled prediction
title_full_unstemmed Feature engineering of environmental covariates improves plant genomic-enabled prediction
title_short Feature engineering of environmental covariates improves plant genomic-enabled prediction
title_sort feature engineering of environmental covariates improves plant genomic enabled prediction
topic engineering
selection
marker-assisted selection
plant breeding
url https://hdl.handle.net/10568/149160
work_keys_str_mv AT montesinoslopezosvala featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT crespoherreraleonardoa featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT saintpierrecarolina featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT canopaezbernabe featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT huertapradogloriaisabel featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT mosquedagonzalezbrandonalejandro featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT ramospulidosofia featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT gerardguillermos featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT khalidalnowibet featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT fritschenetoroberto featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT montesinoslopezabelardo featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction
AT crossajose featureengineeringofenvironmentalcovariatesimprovesplantgenomicenabledprediction