EUVIMEDEUVIMED entdecken
Crossref

Predictive Modeling of Cordycepin Content in Cordyceps militaris Using Machine Learning Based on Cultivation Conditions

Si Young Ha iD, Hyeon Cheol Kim iD, Jae-Kyung Yang iD

Journal of Basic Microbiology · 2026

DOI: 10.1002/jobm.70148 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Basic Microbiology, 2026. Verfasst von Si Young Ha und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Environmental Materials Science, Institute of Agriculture & Life Science, Gyeongsang National University, Jinju, Republic of Korea. Hauptthemen laut MEDLINE: Deoxyadenosines, Cordyceps, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 63 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cordycepin, a nucleoside analog derived from Cordyceps militaris , is a bioactive compound with potent pharmacological properties and growing relevance in functional food and pharmaceutical industries. However, its production is highly variable depending on cultivation conditions, making real‐time and scalable prediction essential for efficient process control. This study aimed to develop a machine learning‐based predictive model to estimate cordycepin content based on measurable cultivation parameters. Three machine learning algorithms—XGBoost, Random Forest, and Support Vector Machine—were trained using experimental data encompassing environmental and nutritional factors. Model validation was conducted using Tropsha's statistical criteria, and model explainability was achieved through SHAP analysis. A user‐friendly GUI was also developed for real‐time prediction and application. Among the models, XGBoost demonstrated the highest performance with a cross‐validated Q² of 0.9087 and an R² of 0.9544, satisfying all statistical requirements for reliability. SHAP analysis identified light wavelength and carbon/nitrogen ratio as the most influential factors in cordycepin biosynthesis. The developed GUI enables end‐users to input cultivation conditions and receive immediate predictions, facilitating data‐driven decision‐making. This approach offers a scalable and interpretable framework for optimizing bioactive compound production in edible fungi, with potential application in smart bioprocessing and precision fermentation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DeoxyadenosinesCordycepsMachine LearningBoosting Machine Learning AlgorithmsPredictive Learning ModelsRandom ForestPrediction AlgorithmsSupport Vector MachineCulture MediaNitrogenCarbonFermentationReproducibility of Results

Stichwörter der Autor:innen

Cordyceps militarisGUIXGBoostbioprocessingcordycepinmachine learning

Substanzen

cordycepinDeoxyadenosinesCulture MediaNitrogenCarbon

Autor:innen und Institutionen

  • Department of Environmental Materials Science, Institute of Agriculture & Life Science, Gyeongsang National University, Jinju, Republic of Korea.

ORCID-Profile: Si Young Ha, Hyeon Cheol Kim, Jae-Kyung Yang

Zitieren

APA

Ha, S. Y., Kim, H. C., & Yang, J. K. (2026). Predictive Modeling of Cordycepin Content in Cordyceps militaris Using Machine Learning Based on Cultivation Conditions. Journal of Basic Microbiology. https://doi.org/10.1002/jobm.70148

Vancouver

Ha SY, Kim HC, Yang JK. Predictive Modeling of Cordycepin Content in Cordyceps militaris Using Machine Learning Based on Cultivation Conditions. Journal of Basic Microbiology. 2026. doi:10.1002/jobm.70148

BibTeX
@article{Ha2026,
  author = {Ha, Si Young and Kim, Hyeon Cheol and Yang, Jae-Kyung},
  title = {Predictive Modeling of Cordycepin Content in Cordyceps militaris Using Machine Learning Based on Cultivation Conditions},
  journal = {Journal of Basic Microbiology},
  year = {2026},
  doi = {10.1002/jobm.70148}
}
Kostenlos starten →