Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging

Over half the world population relies on rice for energy, but being a carbohydrate-based crop, it offers limited nutritional benefits. To achieve nutritional security targets in Asia, we must understand the genetic variation in multi-nutritional properties with therapeutic properties and deploy this...

Full description

Bibliographic Details
Main Authors: Buenafe, Reuben James, Tiozon, Rhowell N., Boyd, Lesley A., ‪Sartagoda, Kristel June, Sreenivasulu, Nese
Format: Journal Article
Language:Inglés
Published: Elsevier 2022
Subjects:
Online Access:https://hdl.handle.net/10568/126017
_version_ 1855541425347756032
author Buenafe, Reuben James
Tiozon, Rhowell N.
Boyd, Lesley A.
‪Sartagoda, Kristel June
Sreenivasulu, Nese
author_browse Boyd, Lesley A.
Buenafe, Reuben James
Sreenivasulu, Nese
Tiozon, Rhowell N.
‪Sartagoda, Kristel June
author_facet Buenafe, Reuben James
Tiozon, Rhowell N.
Boyd, Lesley A.
‪Sartagoda, Kristel June
Sreenivasulu, Nese
author_sort Buenafe, Reuben James
collection Repository of Agricultural Research Outputs (CGSpace)
description Over half the world population relies on rice for energy, but being a carbohydrate-based crop, it offers limited nutritional benefits. To achieve nutritional security targets in Asia, we must understand the genetic variation in multi-nutritional properties with therapeutic properties and deploy this knowledge to future rice breeding. High throughput, VideometerLAB spectral imaging data has been effective in estimating total anthocyanin content, particularly bound anthocyanin content, using the high prediction power of partial least square (PLS) regression models. Multi-pronged nutritional properties of phenolic compounds and minerals, together with videometerLAB features, were utilized to develop models to classify a collection of black rice varieties into three distinct nutritional quality ideotypes. These derived models for black rice diversity panels were created utilizing videometerLAB data (L, A, B parameters), selected phenolic types (total phenolics, total anthocyanins, and bound flavonoids), and minerals (Molybdenum and Phosphorous). Random forest and artificial neural network models depicted the multi-nutritional features of black rice with 85.35 and 99.9% accuracy, respectively. These prediction algorithms would help rice breeders strategically breed nutritionally valuable genotypes based on simple, high-through-put videometerLAB readings and a small number of nutritional assays.
format Journal Article
id CGSpace126017
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1260172025-11-12T05:00:00Z Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging Buenafe, Reuben James Tiozon, Rhowell N. Boyd, Lesley A. ‪Sartagoda, Kristel June Sreenivasulu, Nese rice forest conservation networks Over half the world population relies on rice for energy, but being a carbohydrate-based crop, it offers limited nutritional benefits. To achieve nutritional security targets in Asia, we must understand the genetic variation in multi-nutritional properties with therapeutic properties and deploy this knowledge to future rice breeding. High throughput, VideometerLAB spectral imaging data has been effective in estimating total anthocyanin content, particularly bound anthocyanin content, using the high prediction power of partial least square (PLS) regression models. Multi-pronged nutritional properties of phenolic compounds and minerals, together with videometerLAB features, were utilized to develop models to classify a collection of black rice varieties into three distinct nutritional quality ideotypes. These derived models for black rice diversity panels were created utilizing videometerLAB data (L, A, B parameters), selected phenolic types (total phenolics, total anthocyanins, and bound flavonoids), and minerals (Molybdenum and Phosphorous). Random forest and artificial neural network models depicted the multi-nutritional features of black rice with 85.35 and 99.9% accuracy, respectively. These prediction algorithms would help rice breeders strategically breed nutritionally valuable genotypes based on simple, high-through-put videometerLAB readings and a small number of nutritional assays. 2022-10 2022-12-15T13:34:06Z 2022-12-15T13:34:06Z Journal Article https://hdl.handle.net/10568/126017 en Open Access application/pdf Elsevier Buenafe, Reuben James, Tiozon, Rhowell Jr, Boyd, Lesley A., Sartagoda, Kristel June and Sreeni-vasulu, Nese. Mathematical modeling to predict rice's phenolic and mineral content through multi-spectral imaging. Food Chemistry Advances 1:100141.
spellingShingle rice
forest conservation
networks
Buenafe, Reuben James
Tiozon, Rhowell N.
Boyd, Lesley A.
‪Sartagoda, Kristel June
Sreenivasulu, Nese
Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging
title Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging
title_full Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging
title_fullStr Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging
title_full_unstemmed Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging
title_short Mathematical modeling to predict rice's phenolic and mineral content through multispectral imaging
title_sort mathematical modeling to predict rice s phenolic and mineral content through multispectral imaging
topic rice
forest conservation
networks
url https://hdl.handle.net/10568/126017
work_keys_str_mv AT buenafereubenjames mathematicalmodelingtopredictricesphenolicandmineralcontentthroughmultispectralimaging
AT tiozonrhowelln mathematicalmodelingtopredictricesphenolicandmineralcontentthroughmultispectralimaging
AT boydlesleya mathematicalmodelingtopredictricesphenolicandmineralcontentthroughmultispectralimaging
AT sartagodakristeljune mathematicalmodelingtopredictricesphenolicandmineralcontentthroughmultispectralimaging
AT sreenivasulunese mathematicalmodelingtopredictricesphenolicandmineralcontentthroughmultispectralimaging