Prediction of count phenotypes using high-resolution images and genomic data
Genomic selection (GS) is revolutionizing plant breeding since the selection process is done with the help of statistical machine learning methods. A model is trained with a reference population and then it is used for predicting the candidate individuals available in the testing set. However, given that breeding phenotypic values are very noisy, new models must be able to integrate not only genotypic and environmental data but also high-resolution images that have been collected by breeders with advanced image technology. For this reason, this paper explores the use of generalized Poisson regression (GPR) for genome-enabled prediction of count phenotypes using genomic and hyperspectral images. The GPR model allows integrating input information of many sources like environments, genomic data, high resolution data, and interaction terms between these three sources. We found that the best prediction performance was obtained when the three sources of information were taken into account in the predictor, and those measures of high-resolution images close to the harvest day provided the best prediction performance.
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article biblioteca |
| Language: | English |
| Published: |
Genetics Society of America
2021
|
| Subjects: | AGRICULTURAL SCIENCES AND BIOTECHNOLOGY, High-Resolution Images, Genomic Data, Generalized Poisson Regression, Genomic Selection, Count Data, IMAGE ANALYSIS, GENOMICS, DATA, PLANT BREEDING, MARKER-ASSISTED SELECTION, |
| Online Access: | https://hdl.handle.net/10883/21353 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
dig-cimmyt-10883-21353 |
|---|---|
| record_format |
koha |
| spelling |
dig-cimmyt-10883-213532021-05-07T16:35:31Z Prediction of count phenotypes using high-resolution images and genomic data Kismiantini Montesinos-Lopez, O.A. Crossa, J. Setiawan, E.P. Wutsqa, D.U. AGRICULTURAL SCIENCES AND BIOTECHNOLOGY High-Resolution Images Genomic Data Generalized Poisson Regression Genomic Selection Count Data IMAGE ANALYSIS GENOMICS DATA PLANT BREEDING MARKER-ASSISTED SELECTION Genomic selection (GS) is revolutionizing plant breeding since the selection process is done with the help of statistical machine learning methods. A model is trained with a reference population and then it is used for predicting the candidate individuals available in the testing set. However, given that breeding phenotypic values are very noisy, new models must be able to integrate not only genotypic and environmental data but also high-resolution images that have been collected by breeders with advanced image technology. For this reason, this paper explores the use of generalized Poisson regression (GPR) for genome-enabled prediction of count phenotypes using genomic and hyperspectral images. The GPR model allows integrating input information of many sources like environments, genomic data, high resolution data, and interaction terms between these three sources. We found that the best prediction performance was obtained when the three sources of information were taken into account in the predictor, and those measures of high-resolution images close to the harvest day provided the best prediction performance. 2021-04-13T16:25:35Z 2021-04-13T16:25:35Z 2021 Article Published Version https://hdl.handle.net/10883/21353 10.1093/G3JOURNAL/JKAB035 English https://doi.org/10.5281/zenodo.4478247 Open Access CIMMYT manages Intellectual Assets as International Public Goods. The user is free to download, print, store and share this work. In case you want to translate or create any other derivative work and share or distribute such translation/derivative work, please contact CIMMYT-Knowledge-Center@cgiar.org indicating the work you want to use and the kind of use you intend; CIMMYT will contact you with the suitable license for that purpose. pdf Bethesda, MD (USA) Genetics Society of America 2 11 2160-1836 G3: Genes, Genomes, Genetics jkab035 |
| 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 |
AGRICULTURAL SCIENCES AND BIOTECHNOLOGY High-Resolution Images Genomic Data Generalized Poisson Regression Genomic Selection Count Data IMAGE ANALYSIS GENOMICS DATA PLANT BREEDING MARKER-ASSISTED SELECTION AGRICULTURAL SCIENCES AND BIOTECHNOLOGY High-Resolution Images Genomic Data Generalized Poisson Regression Genomic Selection Count Data IMAGE ANALYSIS GENOMICS DATA PLANT BREEDING MARKER-ASSISTED SELECTION |
| spellingShingle |
AGRICULTURAL SCIENCES AND BIOTECHNOLOGY High-Resolution Images Genomic Data Generalized Poisson Regression Genomic Selection Count Data IMAGE ANALYSIS GENOMICS DATA PLANT BREEDING MARKER-ASSISTED SELECTION AGRICULTURAL SCIENCES AND BIOTECHNOLOGY High-Resolution Images Genomic Data Generalized Poisson Regression Genomic Selection Count Data IMAGE ANALYSIS GENOMICS DATA PLANT BREEDING MARKER-ASSISTED SELECTION Kismiantini Montesinos-Lopez, O.A. Crossa, J. Setiawan, E.P. Wutsqa, D.U. Prediction of count phenotypes using high-resolution images and genomic data |
| description |
Genomic selection (GS) is revolutionizing plant breeding since the selection process is done with the help of statistical machine learning methods. A model is trained with a reference population and then it is used for predicting the candidate individuals available in the testing set. However, given that breeding phenotypic values are very noisy, new models must be able to integrate not only genotypic and environmental data but also high-resolution images that have been collected by breeders with advanced image technology. For this reason, this paper explores the use of generalized Poisson regression (GPR) for genome-enabled prediction of count phenotypes using genomic and hyperspectral images. The GPR model allows integrating input information of many sources like environments, genomic data, high resolution data, and interaction terms between these three sources. We found that the best prediction performance was obtained when the three sources of information were taken into account in the predictor, and those measures of high-resolution images close to the harvest day provided the best prediction performance. |
| format |
Article |
| topic_facet |
AGRICULTURAL SCIENCES AND BIOTECHNOLOGY High-Resolution Images Genomic Data Generalized Poisson Regression Genomic Selection Count Data IMAGE ANALYSIS GENOMICS DATA PLANT BREEDING MARKER-ASSISTED SELECTION |
| author |
Kismiantini Montesinos-Lopez, O.A. Crossa, J. Setiawan, E.P. Wutsqa, D.U. |
| author_facet |
Kismiantini Montesinos-Lopez, O.A. Crossa, J. Setiawan, E.P. Wutsqa, D.U. |
| author_sort |
Kismiantini |
| title |
Prediction of count phenotypes using high-resolution images and genomic data |
| title_short |
Prediction of count phenotypes using high-resolution images and genomic data |
| title_full |
Prediction of count phenotypes using high-resolution images and genomic data |
| title_fullStr |
Prediction of count phenotypes using high-resolution images and genomic data |
| title_full_unstemmed |
Prediction of count phenotypes using high-resolution images and genomic data |
| title_sort |
prediction of count phenotypes using high-resolution images and genomic data |
| publisher |
Genetics Society of America |
| publishDate |
2021 |
| url |
https://hdl.handle.net/10883/21353 |
| work_keys_str_mv |
AT kismiantini predictionofcountphenotypesusinghighresolutionimagesandgenomicdata AT montesinoslopezoa predictionofcountphenotypesusinghighresolutionimagesandgenomicdata AT crossaj predictionofcountphenotypesusinghighresolutionimagesandgenomicdata AT setiawanep predictionofcountphenotypesusinghighresolutionimagesandgenomicdata AT wutsqadu predictionofcountphenotypesusinghighresolutionimagesandgenomicdata |
| _version_ |
1756086973916774400 |