Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods
Although durum wheat (Triticum turgidum var. durum Desf.) is a minor cereal crop representing just 5-7% of the world's total wheat crop, it is a staple food in Mediterranean countries, where it is used to produce pasta, couscous, bulgur and bread. In this paper, we cover multi-trait prediction of grain yield (GY), days to heading (DH) and plant height (PH) of 270 durum wheat lines that were evaluated in 43 environments (country-location-year combinations) across a broad range of water regimes in the Mediterranean Basin and other locations. Multi-trait prediction analyses were performed by implementing a multi-trait deep learning model (MTDL) with a feed-forward network topology and a rectified linear unit activation function with a grid search approach for the selection of hyper-parameters. The results of the multi-trait deep learning method were also compared with univariate predictions of the genomic best linear unbiased predictor (GBLUP) method and the univariate counterpart of the multi-trait deep learning method (UDL). All models were implemented with and without the genotype x environment interaction term. We found that the best predictions were observed without the genotype x environment interaction term in the UDL and MTDL methods. However, under the GBLUP method, the best predictions were observed when the genotype x environment interaction term was taken into account. We also found that in general the best predictions were observed under the GBLUP model; however, the predictions of the MTDL were very similar to those of the GBLUP model. This result provides more evidence that the GBLUP model is a powerful approach for genomic prediction, but also that the deep learning method is a practical approach for predicting univariate and multivariate traits in the context of genomic selection.
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article biblioteca |
| Language: | English |
| Published: |
Frontiers
2019
|
| Subjects: | HARD WHEAT, MARKER-ASSISTED SELECTION, AGRONOMIC CHARACTERS, |
| Online Access: | https://hdl.handle.net/10883/20598 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
dig-cimmyt-10883-20598 |
|---|---|
| record_format |
koha |
| spelling |
dig-cimmyt-10883-205982021-07-22T15:07:26Z Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods Montesinos-Lopez, O.A. Montesinos-Lopez, A. Tuberosa, R. Maccaferri, M. Sciara, G. Ammar, K. Crossa, J. HARD WHEAT MARKER-ASSISTED SELECTION AGRONOMIC CHARACTERS Although durum wheat (Triticum turgidum var. durum Desf.) is a minor cereal crop representing just 5-7% of the world's total wheat crop, it is a staple food in Mediterranean countries, where it is used to produce pasta, couscous, bulgur and bread. In this paper, we cover multi-trait prediction of grain yield (GY), days to heading (DH) and plant height (PH) of 270 durum wheat lines that were evaluated in 43 environments (country-location-year combinations) across a broad range of water regimes in the Mediterranean Basin and other locations. Multi-trait prediction analyses were performed by implementing a multi-trait deep learning model (MTDL) with a feed-forward network topology and a rectified linear unit activation function with a grid search approach for the selection of hyper-parameters. The results of the multi-trait deep learning method were also compared with univariate predictions of the genomic best linear unbiased predictor (GBLUP) method and the univariate counterpart of the multi-trait deep learning method (UDL). All models were implemented with and without the genotype x environment interaction term. We found that the best predictions were observed without the genotype x environment interaction term in the UDL and MTDL methods. However, under the GBLUP method, the best predictions were observed when the genotype x environment interaction term was taken into account. We also found that in general the best predictions were observed under the GBLUP model; however, the predictions of the MTDL were very similar to those of the GBLUP model. This result provides more evidence that the GBLUP model is a powerful approach for genomic prediction, but also that the deep learning method is a practical approach for predicting univariate and multivariate traits in the context of genomic selection. 2019-12-19T01:10:18Z 2019-12-19T01:10:18Z 2019 Article Published Version 1664-462X (Print) https://hdl.handle.net/10883/20598 10.3389/fpls.2019.01311 English http://hdl.handle.net/11529/10548262 Open Access PDF Switzerland Frontiers art. 1311 10 Frontiers in Plant Science |
| institution |
CIMMYT |
| collection |
DSpace |
| country |
México |
| countrycode |
MX |
| component |
Bibliográfico |
| access |
En linea |
| databasecode |
dig-cimmyt |
| tag |
biblioteca |
| region |
America del Norte |
| libraryname |
CIMMYT Library |
| language |
English |
| topic |
HARD WHEAT MARKER-ASSISTED SELECTION AGRONOMIC CHARACTERS HARD WHEAT MARKER-ASSISTED SELECTION AGRONOMIC CHARACTERS |
| spellingShingle |
HARD WHEAT MARKER-ASSISTED SELECTION AGRONOMIC CHARACTERS HARD WHEAT MARKER-ASSISTED SELECTION AGRONOMIC CHARACTERS Montesinos-Lopez, O.A. Montesinos-Lopez, A. Tuberosa, R. Maccaferri, M. Sciara, G. Ammar, K. Crossa, J. Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods |
| description |
Although durum wheat (Triticum turgidum var. durum Desf.) is a minor cereal crop representing just 5-7% of the world's total wheat crop, it is a staple food in Mediterranean countries, where it is used to produce pasta, couscous, bulgur and bread. In this paper, we cover multi-trait prediction of grain yield (GY), days to heading (DH) and plant height (PH) of 270 durum wheat lines that were evaluated in 43 environments (country-location-year combinations) across a broad range of water regimes in the Mediterranean Basin and other locations. Multi-trait prediction analyses were performed by implementing a multi-trait deep learning model (MTDL) with a feed-forward network topology and a rectified linear unit activation function with a grid search approach for the selection of hyper-parameters. The results of the multi-trait deep learning method were also compared with univariate predictions of the genomic best linear unbiased predictor (GBLUP) method and the univariate counterpart of the multi-trait deep learning method (UDL). All models were implemented with and without the genotype x environment interaction term. We found that the best predictions were observed without the genotype x environment interaction term in the UDL and MTDL methods. However, under the GBLUP method, the best predictions were observed when the genotype x environment interaction term was taken into account. We also found that in general the best predictions were observed under the GBLUP model; however, the predictions of the MTDL were very similar to those of the GBLUP model. This result provides more evidence that the GBLUP model is a powerful approach for genomic prediction, but also that the deep learning method is a practical approach for predicting univariate and multivariate traits in the context of genomic selection. |
| format |
Article |
| topic_facet |
HARD WHEAT MARKER-ASSISTED SELECTION AGRONOMIC CHARACTERS |
| author |
Montesinos-Lopez, O.A. Montesinos-Lopez, A. Tuberosa, R. Maccaferri, M. Sciara, G. Ammar, K. Crossa, J. |
| author_facet |
Montesinos-Lopez, O.A. Montesinos-Lopez, A. Tuberosa, R. Maccaferri, M. Sciara, G. Ammar, K. Crossa, J. |
| author_sort |
Montesinos-Lopez, O.A. |
| title |
Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods |
| title_short |
Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods |
| title_full |
Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods |
| title_fullStr |
Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods |
| title_full_unstemmed |
Multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods |
| title_sort |
multi-trait, multi-environment genomic prediction of durum wheat with genomic best linear unbiased predictor and deep learning methods |
| publisher |
Frontiers |
| publishDate |
2019 |
| url |
https://hdl.handle.net/10883/20598 |
| work_keys_str_mv |
AT montesinoslopezoa multitraitmultienvironmentgenomicpredictionofdurumwheatwithgenomicbestlinearunbiasedpredictoranddeeplearningmethods AT montesinoslopeza multitraitmultienvironmentgenomicpredictionofdurumwheatwithgenomicbestlinearunbiasedpredictoranddeeplearningmethods AT tuberosar multitraitmultienvironmentgenomicpredictionofdurumwheatwithgenomicbestlinearunbiasedpredictoranddeeplearningmethods AT maccaferrim multitraitmultienvironmentgenomicpredictionofdurumwheatwithgenomicbestlinearunbiasedpredictoranddeeplearningmethods AT sciarag multitraitmultienvironmentgenomicpredictionofdurumwheatwithgenomicbestlinearunbiasedpredictoranddeeplearningmethods AT ammark multitraitmultienvironmentgenomicpredictionofdurumwheatwithgenomicbestlinearunbiasedpredictoranddeeplearningmethods AT crossaj multitraitmultienvironmentgenomicpredictionofdurumwheatwithgenomicbestlinearunbiasedpredictoranddeeplearningmethods |
| _version_ |
1756086875970338816 |