Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUP
Testcross factorials in newly established hybrid breeding programs are often highly unbalanced, incomplete, and characterized by predominance of special combining ability (SCA) over general combining ability (GCA). This results in a low efficiency of GCA-based selection. Machine learning algorithms...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1178902/full |
| _version_ | 1797774998133276672 |
|---|---|
| author | Philipp Georg Heilmann Matthias Frisch Amine Abbadi Tobias Kox Eva Herzog |
| author_facet | Philipp Georg Heilmann Matthias Frisch Amine Abbadi Tobias Kox Eva Herzog |
| author_sort | Philipp Georg Heilmann |
| collection | DOAJ |
| description | Testcross factorials in newly established hybrid breeding programs are often highly unbalanced, incomplete, and characterized by predominance of special combining ability (SCA) over general combining ability (GCA). This results in a low efficiency of GCA-based selection. Machine learning algorithms might improve prediction of hybrid performance in such testcross factorials, as they have been successfully applied to find complex underlying patterns in sparse data. Our objective was to compare the prediction accuracy of machine learning algorithms to that of GCA-based prediction and genomic best linear unbiased prediction (GBLUP) in six unbalanced incomplete factorials from hybrid breeding programs of rapeseed, wheat, and corn. We investigated a range of machine learning algorithms with three different types of predictor variables: (a) information on parentage of hybrids, (b) in addition hybrid performance of crosses of the parental lines with other crossing partners, and (c) genotypic marker data. In two highly incomplete and unbalanced factorials from rapeseed, in which the SCA variance contributed considerably to the genetic variance, stacked ensembles of gradient boosting machines based on parentage information outperformed GCA prediction. The stacked ensembles increased prediction accuracy from 0.39 to 0.45, and from 0.48 to 0.54 compared to GCA prediction. The prediction accuracy reached by stacked ensembles without marker data reached values comparable to those of GBLUP that requires marker data. We conclude that hybrid prediction with stacked ensembles of gradient boosting machines based on parentage information is a promising approach that is worth further investigations with other data sets in which SCA variance is high. |
| first_indexed | 2024-03-12T22:29:16Z |
| format | Article |
| id | doaj.art-139ab7f2df304487a5705e3b68dc8e02 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-12T22:29:16Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-139ab7f2df304487a5705e3b68dc8e022023-07-21T15:38:58ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-07-011410.3389/fpls.2023.11789021178902Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUPPhilipp Georg Heilmann0Matthias Frisch1Amine Abbadi2Tobias Kox3Eva Herzog4Institute of Agronomy and Plant Breeding II, Justus Liebig University, Gießen, GermanyInstitute of Agronomy and Plant Breeding II, Justus Liebig University, Gießen, GermanyNPZ Innovation GmbH, Holtsee, GermanyNPZ Innovation GmbH, Holtsee, GermanyInstitute of Agronomy and Plant Breeding II, Justus Liebig University, Gießen, GermanyTestcross factorials in newly established hybrid breeding programs are often highly unbalanced, incomplete, and characterized by predominance of special combining ability (SCA) over general combining ability (GCA). This results in a low efficiency of GCA-based selection. Machine learning algorithms might improve prediction of hybrid performance in such testcross factorials, as they have been successfully applied to find complex underlying patterns in sparse data. Our objective was to compare the prediction accuracy of machine learning algorithms to that of GCA-based prediction and genomic best linear unbiased prediction (GBLUP) in six unbalanced incomplete factorials from hybrid breeding programs of rapeseed, wheat, and corn. We investigated a range of machine learning algorithms with three different types of predictor variables: (a) information on parentage of hybrids, (b) in addition hybrid performance of crosses of the parental lines with other crossing partners, and (c) genotypic marker data. In two highly incomplete and unbalanced factorials from rapeseed, in which the SCA variance contributed considerably to the genetic variance, stacked ensembles of gradient boosting machines based on parentage information outperformed GCA prediction. The stacked ensembles increased prediction accuracy from 0.39 to 0.45, and from 0.48 to 0.54 compared to GCA prediction. The prediction accuracy reached by stacked ensembles without marker data reached values comparable to those of GBLUP that requires marker data. We conclude that hybrid prediction with stacked ensembles of gradient boosting machines based on parentage information is a promising approach that is worth further investigations with other data sets in which SCA variance is high.https://www.frontiersin.org/articles/10.3389/fpls.2023.1178902/fullmachine learningstacked ensemblesgradient boostinggenomic predictiongeneral combining abilityspecific combining ability |
| spellingShingle | Philipp Georg Heilmann Matthias Frisch Amine Abbadi Tobias Kox Eva Herzog Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUP Frontiers in Plant Science machine learning stacked ensembles gradient boosting genomic prediction general combining ability specific combining ability |
| title | Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUP |
| title_full | Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUP |
| title_fullStr | Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUP |
| title_full_unstemmed | Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUP |
| title_short | Stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker-based GBLUP |
| title_sort | stacked ensembles on basis of parentage information can predict hybrid performance with an accuracy comparable to marker based gblup |
| topic | machine learning stacked ensembles gradient boosting genomic prediction general combining ability specific combining ability |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1178902/full |
| work_keys_str_mv | AT philippgeorgheilmann stackedensemblesonbasisofparentageinformationcanpredicthybridperformancewithanaccuracycomparabletomarkerbasedgblup AT matthiasfrisch stackedensemblesonbasisofparentageinformationcanpredicthybridperformancewithanaccuracycomparabletomarkerbasedgblup AT amineabbadi stackedensemblesonbasisofparentageinformationcanpredicthybridperformancewithanaccuracycomparabletomarkerbasedgblup AT tobiaskox stackedensemblesonbasisofparentageinformationcanpredicthybridperformancewithanaccuracycomparabletomarkerbasedgblup AT evaherzog stackedensemblesonbasisofparentageinformationcanpredicthybridperformancewithanaccuracycomparabletomarkerbasedgblup |