Dataset Information

Differentiation of Geographical Origin of White and Brown Rice Samples Using NMR Spectroscopy Coupled with Machine Learning Techniques.

ABSTRACT: Rice (Oryza sativa L.) is a widely consumed food source, and its geographical origin has long been a subject of discussion. In our study, we collected 44 and 20 rice samples from different regions of the Republic of Korea and China, respectively, of which 35 and 29 samples were of white and brown rice, respectively. These samples were analyzed using nuclear magnetic resonance (NMR) spectroscopy, followed by analyses with various data normalization and scaling methods. Then, leave-one-out cross-validation (LOOCV) and external validation were employed to evaluate various machine learning algorithms. Total area normalization, with unit variance and Pareto scaling for white and brown rice samples, respectively, was determined as the best pre-processing method in orthogonal partial least squares-discriminant analysis. Among the various tested algorithms, support vector machine (SVM) was the best algorithm for predicting the geographical origin of white and brown rice, with an accuracy of 0.99 and 0.96, respectively. In external validation, the SVM-based prediction model for white and brown rice showed good performance, with an accuracy of 1.0. The results of this study suggest the potential application of machine learning techniques based on NMR data for the differentiation and prediction of diverse geographical origins of white and brown rice.

SUBMITTER: Saeed M

PROVIDER: S-EPMC9693418 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Differentiation of Geographical Origin of White and Brown Rice Samples Using NMR Spectroscopy Coupled with Machine Learning Techniques.

Saeed Maham M Kim Jung-Seop JS Kim Seok-Young SY Ryu Ji Eun JE Ko JuHee J Zaidi Syed Farhan Alam SFA Seo Jeong-Ah JA Kim Young-Suk YS Lee Do Yup DY Choi Hyung-Kyoon HK

Metabolites 20221024 11

Rice (<i>Oryza sativa</i> L.) is a widely consumed food source, and its geographical origin has long been a subject of discussion. In our study, we collected 44 and 20 rice samples from different regions of the Republic of Korea and China, respectively, of which 35 and 29 samples were of white and brown rice, respectively. These samples were analyzed using nuclear magnetic resonance (NMR) spectroscopy, followed by analyses with various data normalization and scaling methods. Then, leave-one-out ...[more]

PMID: 36355095

Similar Datasets

Project description:Reconstructing the history-such as the place of birth and death-of an individual sample is a fundamental goal in ancient DNA (aDNA) studies. However, knowing the place of death can be particularly challenging when samples come from museum collections with incomplete or erroneous archives. While analyses of human DNA and isotope data can inform us about the ancestry of an individual and provide clues about where the person lived, they cannot specifically trace the place of death. Moreover, while ancient human DNA can be retrieved, a large fraction of the sequenced molecules in ancient DNA studies derive from exogenous DNA. This DNA-which is usually discarded in aDNA analyses-is constituted mostly by microbial DNA from soil-dwelling microorganisms that have colonized the buried remains post-mortem. In this study, we hypothesize that remains of individuals buried in the same or close geographic areas, exposed to similar microbial communities, could harbor more similar metagenomes. We propose to use metagenomic data from ancient samples' shotgun sequencing to locate the place of death of a given individual which can also help to solve cases of sample mislabeling. We used a k-mer-based approach to compute similarity scores between metagenomic samples from different locations and propose a method based on dimensionality reduction and logistic regression to assign a geographical origin to target samples. We apply our method to several public datasets and observe that individual samples from closer geographic locations tend to show higher similarities in their metagenomes compared to those of different origin, allowing good geographical predictions of test samples. Moreover, we observe that the genus Streptomyces commonly infiltrates ancient remains and represents a valuable biomarker to trace the samples' geographic origin. Our results provide a proof of concept and show how metagenomic data can also be used to shed light on the place of origin of ancient samples.

Dataset Information

Differentiation of Geographical Origin of White and Brown Rice Samples Using NMR Spectroscopy Coupled with Machine Learning Techniques.

Publications

Differentiation of Geographical Origin of White and Brown Rice Samples Using NMR Spectroscopy Coupled with Machine Learning Techniques.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets