Automated Machine Learning: A Case Study of Genomic "Image-Based" Prediction in Maize Hybrids

Simple item page
dc.contributor.authorGalli, Giovannien
dc.contributor.authorSabadin, Felipeen
dc.contributor.authorYassue, Rafael Massahiroen
dc.contributor.authorGalves, Cassiaen
dc.contributor.authorCarvalho, Humberto Fanellien
dc.contributor.authorCrossa, Joseen
dc.contributor.authorMontesinos-Lopez, Osval Antonioen
dc.contributor.authorFritsche-Neto, Robertoen
dc.date.accessioned2022-07-15T12:58:00Zen
dc.date.available2022-07-15T12:58:00Zen
dc.date.issued2022-03-07en
dc.description.abstractMachine 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.en
dc.description.notesThis work was financially supported by Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior Brasil (CAPES) - Finance Code 001 and Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPq). Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP) and the Bill and Melinda Gates Foundation (BMGF): Grant Number INV-003439 BMGF/FCDO for the financial support. Accelerating Genetic Gains in Maize and Wheat for Improved Livelihoods (AG2MW).en
dc.description.sponsorshipCoordenacao de Aperfeicoamento de Pessoal de Nivel Superior Brasil (CAPES) [001]; Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPq); Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP); Bill and Melinda Gates Foundation (BMGF) [INV-003439 BMGF/FCDO]en
dc.description.versionPublished versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.3389/fpls.2022.845524en
dc.identifier.issn1664-462Xen
dc.identifier.other845524en
dc.identifier.pmid35321444en
dc.identifier.urihttp://hdl.handle.net/10919/111260en
dc.identifier.volume13en
dc.language.isoenen
dc.publisherFrontiersen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectnon-image to imageen
dc.subjectmultilayer perceptronsen
dc.subjectconvolutional neural networksen
dc.subjectAutoMLen
dc.subjectaccuracyen
dc.titleAutomated Machine Learning: A Case Study of Genomic "Image-Based" Prediction in Maize Hybridsen
dc.title.serialFrontiers in Plant Scienceen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
fpls-13-845524.pdf
Size:
1.32 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Scholarly Works, School of Plant and Environmental Sciences