What question did this study set out to answer?

To evaluate digital phenotyping for seed characterization and its potential applications in breeding castor bean.

April 18, 2026Euphytica0 citationsOpen Access

Image-Based Phenotyping for Morphological Traits and Genetic Diversity in Castor Bean Seeds

Image-based phenotyping of castor bean seeds for morphological traits, seed weight prediction, and assessment of genetic diversity

View Full Paper

Ask AI

Bookmark

Authors

Digital phenotyping predicts seed weight and assesses genetic diversity in castor beans, suggesting improved breeding efficiency.

To evaluate digital phenotyping for seed characterization and its potential applications in breeding castor bean.
Photographed seeds from 65 and 51 accessions in 2023 and 2024, respectively, using an RGB camera.
Extracted morphological traits using ImageJ® with correlation and Bland–Altman analysis for measurement agreement.
Trained machine learning models, including Ridge Regression, to predict hundred-seed weight (HSW).
Explored genetic diversity using principal component analysis (PCA) and clustering.
Estimated variance components and heritability with mixed linear models.
Achieved strong agreement between digital and manual measurements (r = 0.95–0.97).
Ridge Regression exhibited the best performance in predicting HSW with R2 = 0.88; RMSE = 3.83; MAE = 3.19.
PCA explained 85.7% of the variance and identified three phenotypic clusters.
High heritability observed for traits like seed length (H2 = 0.88) and aspect ratio (H2 = 0.87).
Moderate heritability found for roundness (H2 = 0.79), perimeter (H2 = 0.72), and area (H2 = 0.67).

Santos et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

April 18, 2026Euphytica0 citationsOpen Access

Image-based phenotyping of castor bean seeds for morphological traits, seed weight prediction, and assessment of genetic diversity

View Full Paper

Ask AI

Bookmark

Authors

Digital phenotyping predicts seed weight and assesses genetic diversity in castor beans, suggesting improved breeding efficiency.

To evaluate digital phenotyping for seed characterization and its potential applications in breeding castor bean.
Photographed seeds from 65 and 51 accessions in 2023 and 2024, respectively, using an RGB camera.
Extracted morphological traits using ImageJ® with correlation and Bland–Altman analysis for measurement agreement.
Trained machine learning models, including Ridge Regression, to predict hundred-seed weight (HSW).
Explored genetic diversity using principal component analysis (PCA) and clustering.
Estimated variance components and heritability with mixed linear models.
Achieved strong agreement between digital and manual measurements (r = 0.95–0.97).
Ridge Regression exhibited the best performance in predicting HSW with R2 = 0.88; RMSE = 3.83; MAE = 3.19.
PCA explained 85.7% of the variance and identified three phenotypic clusters.
High heritability observed for traits like seed length (H2 = 0.88) and aspect ratio (H2 = 0.87).
Moderate heritability found for roundness (H2 = 0.79), perimeter (H2 = 0.72), and area (H2 = 0.67).

Santos et al. (2026) studied this question.

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark