Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids

Machine learning methods such as multilayer perceptrons (MLP) and Convolutional Neural Networks (CNN) have emerged as promising methods for genomic prediction (GP). In this context, we assess the performance of MLP and CNN on regression and classification tasks in a case study with maize hybrids. Th...

Descripción completa

Detalles Bibliográficos
Autores principales: Galli, Giovanni, Sabadin, Felipe, Yassue, Rafael Massahiro, Galves, Cassia, Carvalho, Humberto Fanelli, Crossa, José, Montesinos-López, Osval Antonio, Fritsche-Neto, Roberto
Formato: Journal Article
Lenguaje:Inglés
Publicado: Frontiers Media 2022
Materias:
Acceso en línea:https://hdl.handle.net/10568/164102
_version_ 1855527147023630336
author Galli, Giovanni
Sabadin, Felipe
Yassue, Rafael Massahiro
Galves, Cassia
Carvalho, Humberto Fanelli
Crossa, José
Montesinos-López, Osval Antonio
Fritsche-Neto, Roberto
author_browse Carvalho, Humberto Fanelli
Crossa, José
Fritsche-Neto, Roberto
Galli, Giovanni
Galves, Cassia
Montesinos-López, Osval Antonio
Sabadin, Felipe
Yassue, Rafael Massahiro
author_facet Galli, Giovanni
Sabadin, Felipe
Yassue, Rafael Massahiro
Galves, Cassia
Carvalho, Humberto Fanelli
Crossa, José
Montesinos-López, Osval Antonio
Fritsche-Neto, Roberto
author_sort Galli, Giovanni
collection Repository of Agricultural Research Outputs (CGSpace)
description Machine learning methods such as multilayer perceptrons (MLP) and Convolutional Neural Networks (CNN) have emerged as promising methods for genomic prediction (GP). In this context, we assess the performance of MLP and CNN on regression and classification tasks in a case study with maize hybrids. The genomic information was provided to the MLP as a relationship matrix and to the CNN as “genomic images.” In the regression task, the machine learning models were compared along with GBLUP. Under the classification task, MLP and CNN were compared. In this case, the traits (plant height and grain yield) were discretized in such a way to create balanced (moderate selection intensity) and unbalanced (extreme selection intensity) datasets for further evaluations. An automatic hyperparameter search for MLP and CNN was performed, and the best models were reported. For both task types, several metrics were calculated under a validation scheme to assess the effect of the prediction method and other variables. Overall, MLP and CNN presented competitive results to GBLUP. Also, we bring new insights on automated machine learning for genomic prediction and its implications to plant breeding.
format Journal Article
id CGSpace164102
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Frontiers Media
publisherStr Frontiers Media
record_format dspace
spelling CGSpace1641022025-12-08T10:29:22Z Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids Galli, Giovanni Sabadin, Felipe Yassue, Rafael Massahiro Galves, Cassia Carvalho, Humberto Fanelli Crossa, José Montesinos-López, Osval Antonio Fritsche-Neto, Roberto plant science Machine learning methods such as multilayer perceptrons (MLP) and Convolutional Neural Networks (CNN) have emerged as promising methods for genomic prediction (GP). In this context, we assess the performance of MLP and CNN on regression and classification tasks in a case study with maize hybrids. The genomic information was provided to the MLP as a relationship matrix and to the CNN as “genomic images.” In the regression task, the machine learning models were compared along with GBLUP. Under the classification task, MLP and CNN were compared. In this case, the traits (plant height and grain yield) were discretized in such a way to create balanced (moderate selection intensity) and unbalanced (extreme selection intensity) datasets for further evaluations. An automatic hyperparameter search for MLP and CNN was performed, and the best models were reported. For both task types, several metrics were calculated under a validation scheme to assess the effect of the prediction method and other variables. Overall, MLP and CNN presented competitive results to GBLUP. Also, we bring new insights on automated machine learning for genomic prediction and its implications to plant breeding. 2022-03-07 2024-12-19T12:53:28Z 2024-12-19T12:53:28Z Journal Article https://hdl.handle.net/10568/164102 en Open Access Frontiers Media Galli, Giovanni; Sabadin, Felipe; Yassue, Rafael Massahiro; Galves, Cassia; Carvalho, Humberto Fanelli; Crossa, Jose; Montesinos-López, Osval Antonio and Fritsche-Neto, Roberto. 2022. "Automated machine learning: A case study of genomic ""image-based"" prediction in maize hybrids". Front. Plant Sci., Volume 13
spellingShingle plant science
Galli, Giovanni
Sabadin, Felipe
Yassue, Rafael Massahiro
Galves, Cassia
Carvalho, Humberto Fanelli
Crossa, José
Montesinos-López, Osval Antonio
Fritsche-Neto, Roberto
Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids
title Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids
title_full Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids
title_fullStr Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids
title_full_unstemmed Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids
title_short Automated machine learning: A case study of genomic "image-based" prediction in maize hybrids
title_sort automated machine learning a case study of genomic image based prediction in maize hybrids
topic plant science
url https://hdl.handle.net/10568/164102
work_keys_str_mv AT galligiovanni automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids
AT sabadinfelipe automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids
AT yassuerafaelmassahiro automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids
AT galvescassia automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids
AT carvalhohumbertofanelli automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids
AT crossajose automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids
AT montesinoslopezosvalantonio automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids
AT fritschenetoroberto automatedmachinelearningacasestudyofgenomicimagebasedpredictioninmaizehybrids