Rapid analysis of hydrogen cyanide in fresh cassava roots using NIRSand machine learning algorithms: Meeting end user demand for low cyanogenic cassava.

IF 3.9 2区 生物学 Q1 GENETICS & HEREDITY Plant Genome Pub Date : 2024-06-01 Epub Date: 2023-11-08 DOI:10.1002/tpg2.20403
Michael Kanaabi, Fatumah B Namakula, Ephraim Nuwamanya, Ismail S Kayondo, Nicholas Muhumuza, Enoch Wembabazi, Paula Iragaba, Leah Nandudu, Ann Ritah Nanyonjo, Julius Baguma, Williams Esuma, Alfred Ozimati, Mukasa Settumba, Titus Alicai, Angele Ibanda, Robert S Kawuki
{"title":"Rapid analysis of hydrogen cyanide in fresh cassava roots using NIRSand machine learning algorithms: Meeting end user demand for low cyanogenic cassava.","authors":"Michael Kanaabi, Fatumah B Namakula, Ephraim Nuwamanya, Ismail S Kayondo, Nicholas Muhumuza, Enoch Wembabazi, Paula Iragaba, Leah Nandudu, Ann Ritah Nanyonjo, Julius Baguma, Williams Esuma, Alfred Ozimati, Mukasa Settumba, Titus Alicai, Angele Ibanda, Robert S Kawuki","doi":"10.1002/tpg2.20403","DOIUrl":null,"url":null,"abstract":"<p><p>This study focuses on meeting end-users' demand for cassava (Manihot esculenta Crantz) varieties with low cyanogenic potential (hydrogen cyanide potential [HCN]) by using near-infrared spectrometry (NIRS). This technology provides a fast, accurate, and reliable way to determine sample constituents with minimal sample preparation. The study aims to evaluate the effectiveness of machine learning (ML) algorithms such as logistic regression (LR), support vector machine (SVM), and partial least squares discriminant analysis (PLS-DA) in distinguishing between low and high HCN accessions. Low HCN accessions averagely scored 1-5.9, while high HCN accessions scored 6-9 on a 1-9 categorical scale. The researchers used 1164 root samples to test different NIRS prediction models and six spectral pretreatments. The wavelengths 961, 1165, 1403-1505, 1913-1981, and 2491 nm were influential in discrimination of low and high HCN accessions. Using selected wavelengths, LR achieved 100% classification accuracy and PLS-DA achieved 99% classification accuracy. Using the full spectrum, the best model for discriminating low and high HCN accessions was the PLS-DA combined with standard normal variate with second derivative, which produced an accuracy of 99.6%. The SVM and LR had moderate classification accuracies of 75% and 74%, respectively. This study demonstrates that NIRS coupled with ML algorithms can be used to identify low and high HCN accessions, which can help cassava breeding programs to select for low HCN accessions.</p>","PeriodicalId":49002,"journal":{"name":"Plant Genome","volume":" ","pages":"e20403"},"PeriodicalIF":3.9000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Plant Genome","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1002/tpg2.20403","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/11/8 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}
引用次数: 0

Abstract

This study focuses on meeting end-users' demand for cassava (Manihot esculenta Crantz) varieties with low cyanogenic potential (hydrogen cyanide potential [HCN]) by using near-infrared spectrometry (NIRS). This technology provides a fast, accurate, and reliable way to determine sample constituents with minimal sample preparation. The study aims to evaluate the effectiveness of machine learning (ML) algorithms such as logistic regression (LR), support vector machine (SVM), and partial least squares discriminant analysis (PLS-DA) in distinguishing between low and high HCN accessions. Low HCN accessions averagely scored 1-5.9, while high HCN accessions scored 6-9 on a 1-9 categorical scale. The researchers used 1164 root samples to test different NIRS prediction models and six spectral pretreatments. The wavelengths 961, 1165, 1403-1505, 1913-1981, and 2491 nm were influential in discrimination of low and high HCN accessions. Using selected wavelengths, LR achieved 100% classification accuracy and PLS-DA achieved 99% classification accuracy. Using the full spectrum, the best model for discriminating low and high HCN accessions was the PLS-DA combined with standard normal variate with second derivative, which produced an accuracy of 99.6%. The SVM and LR had moderate classification accuracies of 75% and 74%, respectively. This study demonstrates that NIRS coupled with ML algorithms can be used to identify low and high HCN accessions, which can help cassava breeding programs to select for low HCN accessions.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
使用NIRSand机器学习算法快速分析新鲜木薯根中的氰化氢:满足终端用户对低氰木薯的需求。
本研究的重点是通过使用近红外光谱法(NIRS)满足终端用户对具有低氰潜能(氰化氢潜能[HCN])的木薯(Manihot esculenta Crantz)品种的需求。这项技术提供了一种快速、准确和可靠的方法,可以用最少的样品制备来确定样品成分。本研究旨在评估机器学习(ML)算法,如逻辑回归(LR)、支持向量机(SVM)和偏最小二乘判别分析(PLS-DA)在区分低和高HCN材料方面的有效性。低HCN材料的平均得分为1-5.9,而高HCN材料在1-9分类量表上的得分为6-9。研究人员使用1164个根样本来测试不同的近红外预测模型和六种光谱预处理。961、1165、1403-1505、1913-1981和2491nm的波长对区分低和高HCN材料有影响。使用选定的波长,LR实现了100%的分类精度,PLS-DA实现了99%的分类精度。利用全谱分析,PLS-DA与二阶导数标准正态变量相结合是鉴别低、高HCN材料的最佳模型,其准确率为99.6%。SVM和LR的分类准确率分别为75%和74%。这项研究表明,NIRS与ML算法相结合可以用于识别低HCN和高HCN材料,这可以帮助木薯育种计划选择低HCN材料。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Plant Genome
Plant Genome PLANT SCIENCES-GENETICS & HEREDITY
CiteScore
6.00
自引率
4.80%
发文量
93
审稿时长
>12 weeks
期刊介绍: The Plant Genome publishes original research investigating all aspects of plant genomics. Technical breakthroughs reporting improvements in the efficiency and speed of acquiring and interpreting plant genomics data are welcome. The editorial board gives preference to novel reports that use innovative genomic applications that advance our understanding of plant biology that may have applications to crop improvement. The journal also publishes invited review articles and perspectives that offer insight and commentary on recent advances in genomics and their potential for agronomic improvement.
期刊最新文献
Identification of resistance sources and genomic regions regulating Septoria tritici blotch resistance in South Asian bread wheat germplasm. Soybean genomics research community strategic plan: A vision for 2024-2028. Enhancing prediction accuracy of grain yield in wheat lines adapted to the southeastern United States through multivariate and multi-environment genomic prediction models incorporating spectral and thermal information. Genome-wide association of an organic naked barley diversity panel identified quantitative trait loci for disease resistance. Association mapping and genomic prediction for processing and end-use quality traits in wheat (Triticum aestivum L.).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1