Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR

Achini Herath; Rhowell Tiozon; Tobias Kretzschmar; Nese Sreenivasulu; Peter Mahon; Vito Butardo

doi:10.1016/j.foodchem.2024.140728

Back

Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR

Journal article

Open access

Peer reviewed

Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR

Achini Herath, Rhowell Tiozon, Tobias Kretzschmar, Nese Sreenivasulu, Peter Mahon and Vito Butardo

Food chemistry, Vol.460(Part 3), 140728

01/12/2024

DOI: https://doi.org/10.1016/j.foodchem.2024.140728

Appears in Recent Faculty of Science and Engineering Publications

Files and links (2)

pdf

Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR4.42 MBDownload View

Published (Version of record)CC BY V4.0, Open Access

url

Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIRView

Published (Version of record)CC BY V4.0, Open

Metrics

8 Record Views

See more details

Abstract

Anthocyanins

Chemometrics

Classification models

Flavonoids

Multivariate analysis

Pigmented rice

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.

Details

Title: Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR
Creators: Achini Herath - Swinburne University of Technology
Rhowell Tiozon - International Rice Research Institute
Tobias Kretzschmar - Southern Cross University
Nese Sreenivasulu - International Rice Research Institute
Peter Mahon - Swinburne University of Technology
Vito Butardo - Swinburne University of Technology
Publication Details: Food chemistry, Vol.460(Part 3), 140728
Publisher: Elsevier Ltd
Grant note: We acknowledge the support from the Australian Research Council (ARC) Linkage Project LP190100468. We thank Savithri Galappaththi from Swinburne University of Technology for training in the ATR-FTIR spectroscopic technique, Raymond Siong from Swinburne University of Technology for his assistance in the ATR-FTIR analyses of samples, Annaleise Kelin from the Australian Synchrotron for teaching and access to OPUS vibrational spectroscopy software, and Kaiyang Tu from the Canadian Light Source for technical discussion on mid-IR spectroscopy and training on the use of the Quasar software. R.N.T. acknowledges the Academy for International Agricultural Research (ACINAR) for fundinghis Ph.D. ACINAR, commissioned by the German Federal Ministry for Economic Cooperation and Development (BMZ) , is being carried out by ATSAF (Council for Tropical and Subtropical Agricultural Research) on behalf of the Deutsche Gesellschaft fur Internationale Zusammenarbeit (GIZ) GmbH. Lastly, we duly acknowledge Duc Truong Nguyen from the Southern Cross University for growing and providing all the BRDP rice samples.r his Ph.D. ACINAR, commissioned by the German Federal Ministry for Economic Cooperation and Development (BMZ) , is being carried out by ATSAF (Council for Tropical and Subtropical Agricultural Research) on behalf of the Deutsche Gesellschaft fur Internationale Zusammenarbeit (GIZ) GmbH. Lastly, we duly acknowledge Duc Truong Nguyen from the Southern Cross University for growing and providing all the BRDP rice samples.
Identifiers: 991013214012502368
Academic Unit: Science; Faculty of Science and Engineering
Language: English
Resource Type: Journal article

Machine learning approach for high-throughput phenolic antioxidant screening in black Rice germplasm collection based on surface FTIR

Files and links (2)

Metrics

Abstract

Details

Southern Cross University Social media