Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Microbial Fermentation01:23

Microbial Fermentation

422
Fermentation is a crucial anaerobic metabolic process that enables microbes to derive energy from sugar without relying on oxygen or an electron transport chain. This process is fundamental to various biological and industrial applications and is classified based on the metabolic products generated.Role of Pyruvate in FermentationPyruvate and its derivatives serve as key electron acceptors in fermentative pathways. The oxidation of NADH to regenerate NAD+ is essential for the continuation of...
422

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Energy-translation coupling limits anaerobic yeast growth.

Nature communications·2026
Same author

Metabolic Reprogramming and Proteome Reallocation Accompany Loss of Respiratory Oscillations in Yeast Accelerostat.

Biotechnology and bioengineering·2026
Same author

EnzymeTuning improves enzyme-constrained metabolic modeling and proteome abundance prediction through deep learning.

Nature communications·2026
Same author

Physiological Response of Penicillium chrysogenum to Mimicked Local and Global Perturbations of Substrate and Dissolved Oxygen Gradients at Industrial-Scale.

Biotechnology and bioengineering·2025
Same author

Toward Efficient Utilization of Photogenerated Charge Carriers in Photoelectrochemical Systems: Engineering Strategies from the Atomic Level to Configuration.

Chemical reviews·2024
Same author

Exploring Pathogenic Genes in Frozen Shoulder through weighted gene co-expression network analysis and Mendelian Randomization.

International journal of medical sciences·2024

Related Experiment Video

Updated: Sep 19, 2025

Techniques for the Evolution of Robust Pentose-fermenting Yeast for Bioconversion of Lignocellulose to Ethanol
14:53

Techniques for the Evolution of Robust Pentose-fermenting Yeast for Bioconversion of Lignocellulose to Ethanol

Published on: October 24, 2016

11.4K

Data-Augmented Deep Learning Algorithm for Accurate Control of Bioethanol Fermentation Using an Online Raman

Kaidi Ji1, Xiaofei Yu2, Lifan Chen2

  • 1School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, P.R. China.

Biotechnology and Bioengineering
|June 9, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a Raman spectroscopy and deep learning system for optimizing fed-batch fermentation. The new method enhances bioethanol production by precisely controlling glucose feeding, leading to higher yields and reduced byproducts.

Keywords:
data augmentationdeep learningfeedback controlfermentationraman analyzer

More Related Videos

Workflow Based on the Combination of Isotopic Tracer Experiments to Investigate Microbial Metabolism of Multiple Nutrient Sources
12:47

Workflow Based on the Combination of Isotopic Tracer Experiments to Investigate Microbial Metabolism of Multiple Nutrient Sources

Published on: January 22, 2018

9.5K
Methanol Independent Expression by Pichia Pastoris Employing De-repression Technologies
05:30

Methanol Independent Expression by Pichia Pastoris Employing De-repression Technologies

Published on: January 23, 2019

13.9K

Related Experiment Videos

Last Updated: Sep 19, 2025

Techniques for the Evolution of Robust Pentose-fermenting Yeast for Bioconversion of Lignocellulose to Ethanol
14:53

Techniques for the Evolution of Robust Pentose-fermenting Yeast for Bioconversion of Lignocellulose to Ethanol

Published on: October 24, 2016

11.4K
Workflow Based on the Combination of Isotopic Tracer Experiments to Investigate Microbial Metabolism of Multiple Nutrient Sources
12:47

Workflow Based on the Combination of Isotopic Tracer Experiments to Investigate Microbial Metabolism of Multiple Nutrient Sources

Published on: January 22, 2018

9.5K
Methanol Independent Expression by Pichia Pastoris Employing De-repression Technologies
05:30

Methanol Independent Expression by Pichia Pastoris Employing De-repression Technologies

Published on: January 23, 2019

13.9K

Area of Science:

  • Biotechnology
  • Chemical Engineering
  • Spectroscopy

Background:

  • Fed-batch fermentation is crucial for industrial biomanufacturing but optimizing feeding strategies for maximum yield remains challenging.
  • Accurate real-time monitoring of key metabolites like glucose is essential for effective process control.
  • Limited labeled data often hinders the development of advanced machine learning models for bioprocesses.

Purpose of the Study:

  • To develop and validate an online Raman spectroscopy-based monitoring and control system for optimizing fed-batch fermentation.
  • To improve glucose prediction accuracy using semi-supervised learning and a novel deep learning architecture.
  • To demonstrate enhanced bioethanol production and reduced glycerol formation through automated glucose feeding.

Main Methods:

  • Implementation of an online Raman spectroscopy system for real-time bioprocess monitoring.
  • Application of a pseudo-labeling approach to expand limited labeled data for semi-supervised learning.
  • Development of a spectral-temporal concatenation convolutional neural network (STC-CNN) for analyzing sequential spectral features.
  • Automated glucose feeding control based on real-time glucose predictions.

Main Results:

  • The STC-CNN model achieved a low root mean square error (RMSE) of 3.63 g/L for glucose prediction, outperforming other machine learning algorithms.
  • The developed system enabled rapid and automated glucose feeding to maintain target concentrations.
  • A glucose setpoint of 30 g/L resulted in the highest ethanol concentration (140.68 g/L), a 3.85% increase over traditional methods.
  • Glycerol production was reduced by 6.67% under the optimized feeding strategy.

Conclusions:

  • Raman spectroscopy combined with deep learning offers a powerful approach for automated bioprocess monitoring and control.
  • The developed STC-CNN model and pseudo-labeling strategy effectively address data limitations in bioprocess optimization.
  • This integrated system significantly enhances bioethanol production efficiency and sustainability in Saccharomyces cerevisiae fermentation.