Academic Journal
Προβολή σε EDS

Multi-metric evaluation and parametric optimization of stochastic gradient boosting machines for genomic prediction and selection in wheat (Triticum aestivum) breeding.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Multi-metric evaluation and parametric optimization of stochastic gradient boosting machines for genomic prediction and selection in wheat (Triticum aestivum) breeding.
Συγγραφείς: Munroe HN; Division of Plant Breeding Methodology, Department of Crop Sciences, University of Göttingen, Carl-Sprengel-Weg 1, Göttingen 37075, Lower Saxony, Germany., Osatohanmwen BE; Division of Plant Breeding Methodology, Department of Crop Sciences, University of Göttingen, Carl-Sprengel-Weg 1, Göttingen 37075, Lower Saxony, Germany.; Center for Integrated Breeding Research, University of Göttingen, Albrecht-Thaer-Weg 3, Göttingen 37075, Lower Saxony, Germany., Reza Sharifi A; Center for Integrated Breeding Research, University of Göttingen, Albrecht-Thaer-Weg 3, Göttingen 37075, Lower Saxony, Germany.; Division of Animal Breeding and Genetics, Department of Animal Sciences, University of Göttingen, Albrecht-Thaer-Weg 3, Göttingen 37075, Lower Saxony, Germany.
Πηγή: G3 (Bethesda, Md.) [G3 (Bethesda)] 2026 Jul 06; Vol. 16 (7).
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Oxford University Press Country of Publication: England NLM ID: 101566598 Publication Model: Print Cited Medium: Internet ISSN: 2160-1836 (Electronic) Linking ISSN: 21601836 NLM ISO Abbreviation: G3 (Bethesda) Subsets: MEDLINE
Imprint Name(s): Publication: 2021- : [Oxford] : Oxford University Press
Original Publication: Bethesda, MD : Genetics Society of America, 2011-
Ιατρικοί όροι (MeSH): Triticum*/genetics , Genomics*/methods , Selection, Genetic* , Plant Breeding* , Boosting Machine Learning Algorithms*, Genome, Plant ; Hybridization, Genetic
Περίληψη: Machine learning (ML) models with stochastic and nondeterministic characteristics are increasingly used for genomic prediction in plant breeding, but evaluation often neglects important aspects like prediction stability and ranking performance. This study addresses this gap by evaluating how 2 hyperparameters of a Gradient Boosting Machine (GBM), learning rate (v) and boosting rounds (ntrees), impact stability and multimetric predictive performance for cross-season, cross-environment prediction in a MAGIC wheat population. Using a grid search of 36 parameter combinations, we evaluated 4 agronomic traits with 5 metrics: Pearson's r, area under the curve (AUC), normalized discounted cumulative gain (NDCG), and the intraclass correlation coefficient (ICC), and Fleiss' κ for stability. Our findings show that a low learning rate combined with a high number of boosting rounds substantially improves prediction stability (ICC > 0.98) and selection stability (Fleiss' κ > 0.80), while reducing train-test performance gaps. This combination produced concurrent improvements for predictive accuracy (r), classification accuracy (AUC), and ranking efficiency (NDCG), though optimal settings were trait-dependent. Despite moderate Pearson's r in this challenging cross-season, cross-environment prediction scenario, NDCG remained high (>0.85), indicating a strong ability to rank top-performing entries. In benchmark comparisons conducted within this stump-based additive GBM setting, selected GBM configurations were broadly comparable to rrBLUP, with modest trait-dependent differences across metrics. Ultimately, prioritizing stability when tuning GBMs effectively yields reproducible cross-environment predictions with improved accuracy and top-end ranking performance.
(© The Author(s) 2026. Published by Oxford University Press on behalf of The Genetics Society of America.)
Contributed Indexing: Keywords: cross-environment prediction; genomic prediction; gradient boosting machine; hyperparameter optimization; model stochasticity; wheat (Triticum aestivum) MAGIC population
Entry Date(s): Date Created: 20260523 Date Completed: 20260723 Latest Revision: 20260726
Update Code: 20260726
PubMed Central ID: PMC13334169
DOI: 10.1093/g3journal/jkag127
PMID: 42175721
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=21601836&ISBN=&volume=16&issue=7&date=20260706&spage=&pages=&title=G3 (Bethesda, Md.)&atitle=Multi-metric%20evaluation%20and%20parametric%20optimization%20of%20stochastic%20gradient%20boosting%20machines%20for%20genomic%20prediction%20and%20selection%20in%20wheat%20%28Triticum%E2%80%AFaestivum%29%20breeding.&aulast=Munroe%20HN&id=DOI:10.1093/g3journal/jkag127
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42175721
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Multi-metric evaluation and parametric optimization of stochastic gradient boosting machines for genomic prediction and selection in wheat (Triticum aestivum) breeding.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Munroe+HN%22">Munroe HN</searchLink>; Division of Plant Breeding Methodology, Department of Crop Sciences, University of Göttingen, Carl-Sprengel-Weg 1, Göttingen 37075, Lower Saxony, Germany.<br /><searchLink fieldCode="AU" term="%22Osatohanmwen+BE%22">Osatohanmwen BE</searchLink>; Division of Plant Breeding Methodology, Department of Crop Sciences, University of Göttingen, Carl-Sprengel-Weg 1, Göttingen 37075, Lower Saxony, Germany.; Center for Integrated Breeding Research, University of Göttingen, Albrecht-Thaer-Weg 3, Göttingen 37075, Lower Saxony, Germany.<br /><searchLink fieldCode="AU" term="%22Reza+Sharifi+A%22">Reza Sharifi A</searchLink>; Center for Integrated Breeding Research, University of Göttingen, Albrecht-Thaer-Weg 3, Göttingen 37075, Lower Saxony, Germany.; Division of Animal Breeding and Genetics, Department of Animal Sciences, University of Göttingen, Albrecht-Thaer-Weg 3, Göttingen 37075, Lower Saxony, Germany.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101566598%22">G3 (Bethesda, Md.)</searchLink> [G3 (Bethesda)] 2026 Jul 06; Vol. 16 (7).
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Oxford+University+Press%22">Oxford University Press </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>101566598 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>2160-1836 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2221601836%22">21601836 </searchLink><i>NLM ISO Abbreviation: </i>G3 (Bethesda) <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: 2021- : [Oxford] : Oxford University Press<br /><i>Original Publication</i>: Bethesda, MD : Genetics Society of America, 2011-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Triticum%22">Triticum*</searchLink>/<searchLink fieldCode="MM" term="%22Triticum+genetics%22">genetics</searchLink> <br /><searchLink fieldCode="MM" term="%22Genomics%22">Genomics*</searchLink>/<searchLink fieldCode="MM" term="%22Genomics+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Selection%2C+Genetic%22">Selection, Genetic*</searchLink> <br /><searchLink fieldCode="MM" term="%22Plant+Breeding%22">Plant Breeding*</searchLink> <br /><searchLink fieldCode="MM" term="%22Boosting+Machine+Learning+Algorithms%22">Boosting Machine Learning Algorithms*</searchLink><br /><searchLink fieldCode="MH" term="%22Genome%2C+Plant%22">Genome, Plant</searchLink> ; <searchLink fieldCode="MH" term="%22Hybridization%2C+Genetic%22">Hybridization, Genetic</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Machine learning (ML) models with stochastic and nondeterministic characteristics are increasingly used for genomic prediction in plant breeding, but evaluation often neglects important aspects like prediction stability and ranking performance. This study addresses this gap by evaluating how 2 hyperparameters of a Gradient Boosting Machine (GBM), learning rate (v) and boosting rounds (ntrees), impact stability and multimetric predictive performance for cross-season, cross-environment prediction in a MAGIC wheat population. Using a grid search of 36 parameter combinations, we evaluated 4 agronomic traits with 5 metrics: Pearson's r, area under the curve (AUC), normalized discounted cumulative gain (NDCG), and the intraclass correlation coefficient (ICC), and Fleiss' κ for stability. Our findings show that a low learning rate combined with a high number of boosting rounds substantially improves prediction stability (ICC > 0.98) and selection stability (Fleiss' κ > 0.80), while reducing train-test performance gaps. This combination produced concurrent improvements for predictive accuracy (r), classification accuracy (AUC), and ranking efficiency (NDCG), though optimal settings were trait-dependent. Despite moderate Pearson's r in this challenging cross-season, cross-environment prediction scenario, NDCG remained high (>0.85), indicating a strong ability to rank top-performing entries. In benchmark comparisons conducted within this stump-based additive GBM setting, selected GBM configurations were broadly comparable to rrBLUP, with modest trait-dependent differences across metrics. Ultimately, prioritizing stability when tuning GBMs effectively yields reproducible cross-environment predictions with improved accuracy and top-end ranking performance.<br /> (© The Author(s) 2026. Published by Oxford University Press on behalf of The Genetics Society of America.)
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>cross-environment prediction; genomic prediction; gradient boosting machine; hyperparameter optimization; model stochasticity; wheat (Triticum aestivum) MAGIC population
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260523 <i>Date Completed: </i>20260723 <i>Latest Revision: </i>20260726
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260726
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13334169
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1093/g3journal/jkag127
– Name: AN
  Label: PMID
  Group: ID
  Data: 42175721
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42175721
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1093/g3journal/jkag127
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Genome, Plant
        Type: general
      – SubjectFull: Hybridization, Genetic
        Type: general
      – SubjectFull: Triticum genetics
        Type: general
      – SubjectFull: Genomics methods
        Type: general
      – SubjectFull: Selection, Genetic
        Type: general
      – SubjectFull: Plant Breeding
        Type: general
      – SubjectFull: Boosting Machine Learning Algorithms
        Type: general
    Titles:
      – TitleFull: Multi-metric evaluation and parametric optimization of stochastic gradient boosting machines for genomic prediction and selection in wheat (Triticum aestivum) breeding.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Munroe HN
      – PersonEntity:
          Name:
            NameFull: Osatohanmwen BE
      – PersonEntity:
          Name:
            NameFull: Reza Sharifi A
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 06
              M: 07
              Text: 2026 Jul 06
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 2160-1836
          Numbering:
            – Type: volume
              Value: 16
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: G3 (Bethesda, Md.)
              Type: main
ResultId 1