Predicting the influence of combined oxygen and glucose gradients based on scale-down and modelling approaches for the scale-up of penicillin fermentations

Janoska, Agnes; Buijs, Joran; Gulik, Walter M. van

doi:10.1016/j.procbio.2022.11.006

Cited by 5 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further research efforts could therefore focus on obtaining a higher resolution understanding of the cellular response over both a single and repeated oscillation, thereby also focusing on unraveling the regulatory mechanisms deployed under those conditions. Relevant experimental designs could be built on previous studies, i.e., by using appropriate scale-down simulators such as the STR-STR(-STR) or STR-PFR systems [18,[46][47][48]. Additionally, the development of single multicompartmental bioreactors would allow for the recreation of heterogeneities in a single vessel, thereby decreasing the experimental complexity of these studies [49,50].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Interplay between O2 Availability, Growth Rates, and the Transcriptome of Yarrowia lipolytica

et al. 2023

View full text Add to dashboard Cite

Industrial-sized fermenters differ from the laboratory environment in which bioprocess development initially took place. One of the issues that can lead to reduced productivity on a large scale or even early termination of the process is the presence of bioreactor heterogeneities. This work proposes and adopts a design–build–test–learn-type workflow that estimates the substrate, oxygen, and resulting growth heterogeneities through a compartmental modelling approach and maps Yarrowia lipolytica-specific behavior in this relevant range of conditions. The results indicate that at a growth rate of 0.1 h−1, the largest simulated volume (90 m3) reached partial oxygen limitation. Throughout the fed-batch, the cells experienced dissolved oxygen values from 0 to 75% and grew at rates of 0 to 0.2 h−1. These simulated large-scale conditions were tested in small-scale cultivations, which elucidated a transcriptome with a strong downregulation of various transporter and central carbon metabolism genes during oxygen limitation. The relation between oxygen availability and differential gene expression was dynamic and did not show a simple on–off behavior. This indicates that Y. lipolytica can differentiate between different available oxygen concentrations and adjust its transcription accordingly. The workflow presented can be used for Y. lipolytica-based strain engineering, thereby accelerating bioprocess development.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Bridging these scales has proven to be of great importance, with similar efforts focusing on different processes [18]. This study aims to aid in the development of Y. lipolytica-based bioprocesses; as such, a targeted workflow is presented and followed.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Interplay between O2 Availability, Growth Rates, and the Transcriptome of Yarrowia lipolytica

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Another countermeasure is adversarial training, which involves training the machine learning model using generated examples [35]. This helps the model learn and understand the characteristics of adversary attacks, improving its ability to resist future attacks.…”

mentioning

confidence: 99%

Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW

Villegas-Ch,

Jaramillo-Alcázar,

Luján-Mora

2024

BDCC

View full text Add to dashboard Cite

This study evaluated the generation of adversarial examples and the subsequent robustness of an image classification model. The attacks were performed using the Fast Gradient Sign method, the Projected Gradient Descent method, and the Carlini and Wagner attack to perturb the original images and analyze their impact on the model’s classification accuracy. Additionally, image manipulation techniques were investigated as defensive measures against adversarial attacks. The results highlighted the model’s vulnerability to conflicting examples: the Fast Gradient Signed Method effectively altered the original classifications, while the Carlini and Wagner method proved less effective. Promising approaches such as noise reduction, image compression, and Gaussian blurring were presented as effective countermeasures. These findings underscore the importance of addressing the vulnerability of machine learning models and the need to develop robust defenses against adversarial examples. This article emphasizes the urgency of addressing the threat posed by harmful standards in machine learning models, highlighting the relevance of implementing effective countermeasures and image manipulation techniques to mitigate the effects of adversarial attacks. These efforts are crucial to safeguarding model integrity and trust in an environment marked by constantly evolving hostile threats. An average 25% decrease in accuracy was observed for the VGG16 model when exposed to the Fast Gradient Signed Method and Projected Gradient Descent attacks, and an even more significant 35% decrease with the Carlini and Wagner method.

show abstract

Towards Digital Twin for Biopharmaceutical Processes: Concept and Progress

Ding,

Yang,

Ierapetritou

2023

Cell Engineering

View full text Add to dashboard Cite

Predicting the influence of combined oxygen and glucose gradients based on scale-down and modelling approaches for the scale-up of penicillin fermentations

Cited by 5 publications

References 48 publications

Dynamic Interplay between O2 Availability, Growth Rates, and the Transcriptome of Yarrowia lipolytica

Dynamic Interplay between O2 Availability, Growth Rates, and the Transcriptome of Yarrowia lipolytica

Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW

Towards Digital Twin for Biopharmaceutical Processes: Concept and Progress

Contact Info

Product

Resources

About