EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Michael Kanaabi iD, Fatumah B Namakula, Ephraim Nuwamanya, Ismail S Kayondo iD, Nicholas Muhumuza, Enoch Wembabazi, Paula Iragaba, Leah Nandudu, Ann Ritah Nanyonjo, Julius Baguma, Williams Esuma, Alfred Ozimati und 4 weitere

The Plant Genome · 2024-06 · 17 (2)

DOI: 10.1002/tpg2.20403 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Plant Genome, online erschienen am 08.11.2023. Verfasst von Michael Kanaabi und 15 weiteren Autor:innen. Beteiligte Einrichtung: School of Agricultural Sciences, Makerere University, Kampala, Uganda. Hauptthemen laut MEDLINE: Manihot, Hydrogen Cyanide, Spectroscopy, Near-Infrared, Plant Roots. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gates Foundation, Nextgen cassava breeding project, UK's Foreign Common Wealth and Development Office.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ManihotHydrogen CyanideSpectroscopy, Near-InfraredPlant RootsMachine LearningAlgorithmsSupport Vector MachineLeast-Squares Analysis

Substanzen

Hydrogen Cyanide

Autor:innen und Institutionen

  • School of Agricultural Sciences, Makerere University, Kampala, Uganda.
  • National Crops Resources Research Institute (NaCRRI), Kampala, Uganda.
  • International Institute for Tropical Agriculture (IITA), Ibadan, Nigeria.
  • Plant Breeding and Genetics section, Cornell University, Ithaca, New York, USA.

ORCID-Profile: Michael Kanaabi, Ismail S Kayondo

Förderung

  • Gates Foundation
  • Nextgen cassava breeding project
  • UK's Foreign Common Wealth and Development Office
  • CGIAR Roots, Tubers and Banana Research Program
  • CGIAR Fund council
  • Breeding RTB products for End User Preferences
  • French Agricultural Research Center for International Development
  • Regional Universities Forum for Capacity Building in Agriculture

Zitieren

APA

Kanaabi, M., Namakula, F. B., Nuwamanya, E., Kayondo, I. S., Muhumuza, N., Wembabazi, E., Iragaba, P., Nandudu, L., Nanyonjo, A. R., Baguma, J., Esuma, W., Ozimati, A., Settumba, M., Alicai, T., Ibanda, A., & Kawuki, R. S. (2024). Rapid analysis of hydrogen cyanide in fresh cassava roots using NIRSand machine learning algorithms: Meeting end user demand for low cyanogenic cassava. The Plant Genome, 17(2). https://doi.org/10.1002/tpg2.20403

Vancouver

Kanaabi M, Namakula FB, Nuwamanya E, Kayondo IS, Muhumuza N, Wembabazi E, et al. Rapid analysis of hydrogen cyanide in fresh cassava roots using NIRSand machine learning algorithms: Meeting end user demand for low cyanogenic cassava. The Plant Genome. 2024;17(2). doi:10.1002/tpg2.20403

BibTeX
@article{Kanaabi2024,
  author = {Kanaabi, Michael and Namakula, Fatumah B and Nuwamanya, Ephraim and Kayondo, Ismail S and Muhumuza, Nicholas and Wembabazi, Enoch and Iragaba, Paula and Nandudu, Leah and Nanyonjo, Ann Ritah and Baguma, Julius and Esuma, Williams and Ozimati, Alfred and Settumba, Mukasa and Alicai, Titus and Ibanda, Angele and Kawuki, Robert S},
  title = {Rapid analysis of hydrogen cyanide in fresh cassava roots using NIRSand machine learning algorithms: Meeting end user demand for low cyanogenic cassava},
  journal = {The Plant Genome},
  year = {2024},
  volume = {17},
  number = {2},
  doi = {10.1002/tpg2.20403}
}
Kostenlos starten →