Development and assessment of a lysophospholipid-based deep learning model to discriminate geographical origins of white rice

Nguyen Phuoc Long, Dong Kyu Lim, Changyeun Mo, Giyoung Kim, Sung Won Kwon

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Geographical origin determination of white rice has become the major issue of food industry. However, there is still lack of a high-throughput method for rapidly and reproducibly differentiating the geographical origins of commercial white rice. In this study, we developed a method that employed lipidomics and deep learning to discriminate white rice from Korea to China. A total of 126 white rice of 30 cultivars from different regions were utilized for the method development and validation. By using direct infusion-mass spectrometry-based targeted lipidomics, 17 lysoglycerophospholipids were simultaneously characterized within minutes per sample. Unsupervised data exploration showed a noticeable overlap of white rice between two countries. In addition, lysophosphatidylcholines (lysoPCs) were prominent in white rice from Korea while lysophosphatidylethanolamines (lysoPEs) were enriched in white rice from China. A deep learning prediction model was built using 2014 white rice and validated using two different batches of 2015 white rice. The model accurately discriminated white rice from two countries. Among 10 selected predictors, lysoPC(18:2), lysoPC(14:0), and lysoPE(16:0) were the three most important features. Random forest and gradient boosting machine models also worked well in this circumstance. In conclusion, this study provides an architecture for high-throughput classification of white rice from different geographical origins.

Original languageEnglish (US)
Article number8552
JournalScientific Reports
Volume7
Issue number1
DOIs
StatePublished - Dec 1 2017

Fingerprint

Lysophospholipids
Learning
Korea
China
Oryza
Lysophosphatidylcholines
Food Industry
Mass Spectrometry

ASJC Scopus subject areas

  • General

Cite this

Development and assessment of a lysophospholipid-based deep learning model to discriminate geographical origins of white rice. / Long, Nguyen Phuoc; Lim, Dong Kyu; Mo, Changyeun; Kim, Giyoung; Kwon, Sung Won.

In: Scientific Reports, Vol. 7, No. 1, 8552, 01.12.2017.

Research output: Contribution to journalArticle

Long, Nguyen Phuoc ; Lim, Dong Kyu ; Mo, Changyeun ; Kim, Giyoung ; Kwon, Sung Won. / Development and assessment of a lysophospholipid-based deep learning model to discriminate geographical origins of white rice. In: Scientific Reports. 2017 ; Vol. 7, No. 1.
@article{3ec16ffaded3470dbdb05426e7d03669,
title = "Development and assessment of a lysophospholipid-based deep learning model to discriminate geographical origins of white rice",
abstract = "Geographical origin determination of white rice has become the major issue of food industry. However, there is still lack of a high-throughput method for rapidly and reproducibly differentiating the geographical origins of commercial white rice. In this study, we developed a method that employed lipidomics and deep learning to discriminate white rice from Korea to China. A total of 126 white rice of 30 cultivars from different regions were utilized for the method development and validation. By using direct infusion-mass spectrometry-based targeted lipidomics, 17 lysoglycerophospholipids were simultaneously characterized within minutes per sample. Unsupervised data exploration showed a noticeable overlap of white rice between two countries. In addition, lysophosphatidylcholines (lysoPCs) were prominent in white rice from Korea while lysophosphatidylethanolamines (lysoPEs) were enriched in white rice from China. A deep learning prediction model was built using 2014 white rice and validated using two different batches of 2015 white rice. The model accurately discriminated white rice from two countries. Among 10 selected predictors, lysoPC(18:2), lysoPC(14:0), and lysoPE(16:0) were the three most important features. Random forest and gradient boosting machine models also worked well in this circumstance. In conclusion, this study provides an architecture for high-throughput classification of white rice from different geographical origins.",
author = "Long, {Nguyen Phuoc} and Lim, {Dong Kyu} and Changyeun Mo and Giyoung Kim and Kwon, {Sung Won}",
year = "2017",
month = "12",
day = "1",
doi = "10.1038/s41598-017-08892-0",
language = "English (US)",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Development and assessment of a lysophospholipid-based deep learning model to discriminate geographical origins of white rice

AU - Long, Nguyen Phuoc

AU - Lim, Dong Kyu

AU - Mo, Changyeun

AU - Kim, Giyoung

AU - Kwon, Sung Won

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Geographical origin determination of white rice has become the major issue of food industry. However, there is still lack of a high-throughput method for rapidly and reproducibly differentiating the geographical origins of commercial white rice. In this study, we developed a method that employed lipidomics and deep learning to discriminate white rice from Korea to China. A total of 126 white rice of 30 cultivars from different regions were utilized for the method development and validation. By using direct infusion-mass spectrometry-based targeted lipidomics, 17 lysoglycerophospholipids were simultaneously characterized within minutes per sample. Unsupervised data exploration showed a noticeable overlap of white rice between two countries. In addition, lysophosphatidylcholines (lysoPCs) were prominent in white rice from Korea while lysophosphatidylethanolamines (lysoPEs) were enriched in white rice from China. A deep learning prediction model was built using 2014 white rice and validated using two different batches of 2015 white rice. The model accurately discriminated white rice from two countries. Among 10 selected predictors, lysoPC(18:2), lysoPC(14:0), and lysoPE(16:0) were the three most important features. Random forest and gradient boosting machine models also worked well in this circumstance. In conclusion, this study provides an architecture for high-throughput classification of white rice from different geographical origins.

AB - Geographical origin determination of white rice has become the major issue of food industry. However, there is still lack of a high-throughput method for rapidly and reproducibly differentiating the geographical origins of commercial white rice. In this study, we developed a method that employed lipidomics and deep learning to discriminate white rice from Korea to China. A total of 126 white rice of 30 cultivars from different regions were utilized for the method development and validation. By using direct infusion-mass spectrometry-based targeted lipidomics, 17 lysoglycerophospholipids were simultaneously characterized within minutes per sample. Unsupervised data exploration showed a noticeable overlap of white rice between two countries. In addition, lysophosphatidylcholines (lysoPCs) were prominent in white rice from Korea while lysophosphatidylethanolamines (lysoPEs) were enriched in white rice from China. A deep learning prediction model was built using 2014 white rice and validated using two different batches of 2015 white rice. The model accurately discriminated white rice from two countries. Among 10 selected predictors, lysoPC(18:2), lysoPC(14:0), and lysoPE(16:0) were the three most important features. Random forest and gradient boosting machine models also worked well in this circumstance. In conclusion, this study provides an architecture for high-throughput classification of white rice from different geographical origins.

UR - http://www.scopus.com/inward/record.url?scp=85027866872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027866872&partnerID=8YFLogxK

U2 - 10.1038/s41598-017-08892-0

DO - 10.1038/s41598-017-08892-0

M3 - Article

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 8552

ER -