Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR
Pigmented rice contains beneficial phenolic antioxidants but analysing them across germplasm collections is laborious and time-consuming. Here we utilised rapid surface Fourier transform infrared (FTIR) spectroscopy and machine learning algorithms (ML) to predict and classify polyphenolic antioxidan...
| Main Authors: | , , , , , |
|---|---|
| Format: | Journal Article |
| Language: | Inglés |
| Published: |
Elsevier
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/168152 |
| _version_ | 1855541357668466688 |
|---|---|
| author | Herath, Achini Tiozon, Rhowell Jr. Kretzschmar, Tobias Sreenivasulu, Nese Mahon, Peter Butardo, Vito |
| author_browse | Butardo, Vito Herath, Achini Kretzschmar, Tobias Mahon, Peter Sreenivasulu, Nese Tiozon, Rhowell Jr. |
| author_facet | Herath, Achini Tiozon, Rhowell Jr. Kretzschmar, Tobias Sreenivasulu, Nese Mahon, Peter Butardo, Vito |
| author_sort | Herath, Achini |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Pigmented rice contains beneficial phenolic antioxidants but analysing them across germplasm collections is laborious and time-consuming. Here we utilised rapid surface Fourier transform infrared (FTIR) spectroscopy and machine learning algorithms (ML) to predict and classify polyphenolic antioxidants. Total phenolics, flavonoids, anthocyanins, and proanthocyanidins were quantified biochemically from 270 diverse global coloured rice collection and attenuated total reflectance (ATR) FTIR spectra were obtained by scanning whole grain surfaces at 800–4000 cm−1. Five ML classification models were optimised using the biochemical and spectral data which performed predictions with 93.5%–100% accuracy. Random Forest and Support Vector Machine models identified key FTIR peaks linked to flavonols, flavones and anthocyanins as important model predictors. This research successfully established direct and non-destructive surface chemistry spectroscopy of the aleurone layer of pigmented rice integrated with ML models as a viable high-throughput platform to accelerate the analysis and profiling of nutritionally valuable coloured rice varieties. |
| format | Journal Article |
| id | CGSpace168152 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| record_format | dspace |
| spelling | CGSpace1681522025-12-08T10:11:39Z Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR Herath, Achini Tiozon, Rhowell Jr. Kretzschmar, Tobias Sreenivasulu, Nese Mahon, Peter Butardo, Vito anthocyanins machine learning high-throughput phenotyping screening pigments rice multivariate analysis flavonoids Pigmented rice contains beneficial phenolic antioxidants but analysing them across germplasm collections is laborious and time-consuming. Here we utilised rapid surface Fourier transform infrared (FTIR) spectroscopy and machine learning algorithms (ML) to predict and classify polyphenolic antioxidants. Total phenolics, flavonoids, anthocyanins, and proanthocyanidins were quantified biochemically from 270 diverse global coloured rice collection and attenuated total reflectance (ATR) FTIR spectra were obtained by scanning whole grain surfaces at 800–4000 cm−1. Five ML classification models were optimised using the biochemical and spectral data which performed predictions with 93.5%–100% accuracy. Random Forest and Support Vector Machine models identified key FTIR peaks linked to flavonols, flavones and anthocyanins as important model predictors. This research successfully established direct and non-destructive surface chemistry spectroscopy of the aleurone layer of pigmented rice integrated with ML models as a viable high-throughput platform to accelerate the analysis and profiling of nutritionally valuable coloured rice varieties. 2024-12 2024-12-20T16:03:58Z 2024-12-20T16:03:58Z Journal Article https://hdl.handle.net/10568/168152 en Open Access application/pdf Elsevier Herath, Achini, Tobias Kretzschmar, Nese Sreenivasulu, Peter Mahon, and Vito Butardo Jr. "Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR." Food chemistry 460 (2024): 140728. |
| spellingShingle | anthocyanins machine learning high-throughput phenotyping screening pigments rice multivariate analysis flavonoids Herath, Achini Tiozon, Rhowell Jr. Kretzschmar, Tobias Sreenivasulu, Nese Mahon, Peter Butardo, Vito Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR |
| title | Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR |
| title_full | Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR |
| title_fullStr | Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR |
| title_full_unstemmed | Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR |
| title_short | Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR |
| title_sort | machine learning approach for high throughput phenolic antioxidant screening in black rice germplasm collection based on surface ftir |
| topic | anthocyanins machine learning high-throughput phenotyping screening pigments rice multivariate analysis flavonoids |
| url | https://hdl.handle.net/10568/168152 |
| work_keys_str_mv | AT herathachini machinelearningapproachforhighthroughputphenolicantioxidantscreeninginblackricegermplasmcollectionbasedonsurfaceftir AT tiozonrhowelljr machinelearningapproachforhighthroughputphenolicantioxidantscreeninginblackricegermplasmcollectionbasedonsurfaceftir AT kretzschmartobias machinelearningapproachforhighthroughputphenolicantioxidantscreeninginblackricegermplasmcollectionbasedonsurfaceftir AT sreenivasulunese machinelearningapproachforhighthroughputphenolicantioxidantscreeninginblackricegermplasmcollectionbasedonsurfaceftir AT mahonpeter machinelearningapproachforhighthroughputphenolicantioxidantscreeninginblackricegermplasmcollectionbasedonsurfaceftir AT butardovito machinelearningapproachforhighthroughputphenolicantioxidantscreeninginblackricegermplasmcollectionbasedonsurfaceftir |