Artificial intelligence technologies in bioprocess: Opportunities and challenges

Cheng, Yang; Bi, Xinyu; Xu, Yameng; Liu, Yanfeng; Li, Jianghua; Du, Guocheng; Liu, Long

doi:10.1016/j.biortech.2022.128451

Cited by 27 publications

(8 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Resultsmentioning

confidence: 99%

“…Through the establishment of large databases and the prediction of deep learning, it is possible to identify more efficient activators and target genes that can significantly enhance the yield of L-serine production, thereby facilitating a substantial breakthrough in metabolic engineering of C. glutamicum. 52 The implementation of the CRISPR/dCpf1based bifunctional regulation system in C. glutamicum has greatly facilitated the streamlined and efficient regulation of metabolic pathways. With the rapid development of synthetic biology and related fields, the CRISPR/dCpf1-based bifunctional regulation system has broad application prospects as an important metabolic tool.…”

Section: Metabolic Pathwaymentioning

confidence: 99%

See 1 more Smart Citation

Rewiring Metabolic Flux in Corynebacterium glutamicum Using a CRISPR/dCpf1-Based Bifunctional Regulation System

Yin,

Xi,

Shen

et al. 2024

J. Agric. Food Chem.

View full text Add to dashboard Cite

Corynebacterium glutamicum, a microorganism classified as generally recognized as safe for use in the industrial production of food raw materials and additives, has encountered challenges in achieving widespread adoption and popularization as microbial cell factories. These obstacles arise from the intricate nature of manipulating metabolic flux through conventional methods, such as gene knockout and enzyme overexpression. To address this challenge, we developed a CRISPR/dCpf1-based bifunctional regulation system to bidirectionally regulate the expression of multiple genes in C. glutamicum. Specifically, through fusing various transcription factors to the C-terminus of dCpf1, the resulting dCpf1-SoxS exhibited both CRISPR interference (CRISPRi) and CRISPR activation (CRISPRa) capabilities in C. glutamicum by altering the binding sites of crRNAs. The bifunctional regulation system was used to fine-tune metabolic flux from shikimic acid (SA) and L-serine biosynthesis, resulting in 27-fold and 10-fold increases in SA and L-serine production, respectively, compared to the original strain. These findings highlight the potential of the CRISPR/dCpf1-based bifunctional regulation system in effectively enhancing the yield of target products in C. glutamicum.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Metabolic Pathwaymentioning

confidence: 99%

Rewiring Metabolic Flux in Corynebacterium glutamicum Using a CRISPR/dCpf1-Based Bifunctional Regulation System

Yin,

Xi,

Shen

et al. 2024

J. Agric. Food Chem.

View full text Add to dashboard Cite

show abstract

“…ANN-ML model provided better predictability of parameters in enhancing CFD processes (Cantarero-Rivera et al, 2024). AI and ML algorithms can be employed to analyse data from previous bioreactor runs and identify patterns and trends for improvement of bioreactor design and operation (Cheng et al, 2023;Walsh et al, 2022). AI and ML can also be used to develop and optimise control algorithms for bioreactors.…”

Section: Bioreactorsmentioning

confidence: 99%

“…AI and ML strategies are being utilised by Innocent Meat, Germany and Renaissance Farms, UK, for developing fully automated plug-and-play CM manufacturing facilities (Table 2) (Ho, 2021;Innocent Meat, 2023). AI and ML algorithms can be used to analyse data from sensors and other sources within the manufacturing process to identify trends, predict potential problems, and optimise production (Cheng et al, 2023;Walsh et al, 2022). IoT can also be used to facilitate the industrial manufacturing of CM by enabling real-time monitoring and control of the production process (Parks et al, 2022).…”

Section: Industrial Manufacturingmentioning

confidence: 99%

Industry 4.0 technologies for cultivated meat manufacturing

Kamalapuram,

Choudhury

2024

Food Bioengineering

View full text Add to dashboard Cite

Industry 4.0 integrates the physical, digital, and biological realms by applying digital automation in systems, processes, and manufacturing facilities. Industry 4.0 is actively shaping the development of intelligent food processing industries in cultivated meat (CM) sector. This integration plays a crucial role in accelerating progress within the global CM sector, facilitating the achievement of its objectives related to food sustainability, security, human health, environmental concerns, and hygiene. Incorporating Industry 4.0 into CM manufacturing systems empowers upstream and downstream production processes to become more intelligent and capable of self‐optimisation. However, enabling rapid adoption of Industry 4.0 by emerging startups and small to medium‐sized enterprises in the CM industry necessitates a thorough understanding of prerequisites and evaluation of technological and biological limitations. Challenges include the substantial initial costs associated with establishing Industry 4.0 infrastructure, robust cybersecurity measures to ensure effective risk management, and acquiring skilled professionals proficient in both operational and maintenance roles. Integrating Industry 4.0 with the evolving CM sector presents an exciting opportunity to foster business‐to‐business investments across various domains, including local markets, export opportunities, and the broader global consumer ecosystem.

show abstract

“…On the other hand, hybrid modeling of bioprocess incorporates a data‐driven approach to map the specific rates in mechanistic models, without advocating any explicit functional relationship with process variables. Artificial intelligence has been introduced as a facilitating approach to build a data‐driven model by learning the relationship between input and output using a training data set, creating a rule on trained structure for future predictions (Cheng et al, 2023).…”

Section: Machine Learning Tools In Hybrid Modelingmentioning

confidence: 99%

Hybrid modeling in bioprocess dynamics: Structural variabilities, implementation strategies, and practical challenges

Mahanty

2023

Biotech & Bioengineering

View full text Add to dashboard Cite

Hybrid modeling, with an appropriate blend of the mechanistic and data‐driven framework, is increasingly being adopted in bioprocess modeling, model‐based experimental design (digital‐twin), identification of critical process parameters, and optimization. However, the development of a hybrid model from experimental data is an inherently complex workflow, involving designed experiments, selection of the data‐driven process, identification of model parameters, assessment fitness, and generalization capability. Depending on the complexity of the process system and purpose, each piece of these modules can flexibly be incorporated into the puzzle. However, this extra flexibility can be a cause of concern to trace an “optimal” model structure. In this paper, the development of hybrid models in a common bioprocess system, selection of data‐driven components and their mapping to states, choice of parameter identification techniques, and model quality assurance are revisited. The challenges associated with hybrid‐model development, and corrective actions have also been reviewed. The review also suggests the lack of data, and code sharing in communal repositories can be a hurdle in the exploration, and expansion of those tools in a bioprocess system.

show abstract

Artificial intelligence technologies in bioprocess: Opportunities and challenges

Cited by 27 publications

References 91 publications

Rewiring Metabolic Flux in Corynebacterium glutamicum Using a CRISPR/dCpf1-Based Bifunctional Regulation System

Rewiring Metabolic Flux in Corynebacterium glutamicum Using a CRISPR/dCpf1-Based Bifunctional Regulation System

Industry 4.0 technologies for cultivated meat manufacturing

Hybrid modeling in bioprocess dynamics: Structural variabilities, implementation strategies, and practical challenges

Contact Info

Product

Resources

About