Artificial neural network‐genetic algorithm (ANN‐GA) based medium optimization for the production of human interferon gamma (hIFN‐γ) inKluyveromyces lactiscell factory

Molecular insights fast-tracked: AI in biosynthetic pathway research

Covering: 2000 to 2025This review explores the potential of artificial intelligence (AI) in addressing challenges and accelerating molecular insights in biosynthetic pathway research, which is crucial for developing bioactive natural products with applications in pharmacology, agriculture, and biotechnology. It provides an overview of various AI techniques relevant to this research field, including machine learning (ML), deep learning (DL), natural language processing, network analysis, and data mining. AI-powered applications across three main areas, namely, pathway discovery and mining, pathway design, and pathway optimization, are discussed, and the benefits and challenges of integrating omics data and AI for enhanced pathway research are also elucidated. This review also addresses the current limitations, future directions, and the importance of synergy between AI and experimental approaches in unlocking rapid advancements in biosynthetic pathway research. The review concludes with an evaluation of AI's current capabilities and future outlook, emphasizing the transformative impact of AI on biosynthetic pathway research and the potential for new opportunities in the discovery and optimization of bioactive natural products.

Modeling and Optimization of Recombinant Tocilizumab Production From Pichia pastoris Using Response Surface Methodology and Artificial Neural Network

This study has demonstrated the optimization of the defined medium that significantly enhanced the production of recombinant monoclonal antibody (mAb) Tocilizumab (TCZ) as full-length and Fab fragment from Pichia pastoris. Out of the four tested defined media, FM22 was found to be suitable for the growth of recombinant strains and antibody yield. Among the various carbon and nitrogen sources tested, mannitol and glycine, respectively, were found to be suitable for the enhanced production of full-length TCZ. Similarly, sorbitol and ammonium sulfate were found to be suitable carbon and nitrogen sources, respectively, for enhanced production of Fab. The medium components that significantly influenced the production of TCZ were found to be mannitol, glycine, histidine, and K2SO4 and sorbitol, ammonium sulfate, KH2PO4, and CaSO4.2H2O for full-length and Fab, respectively, using a two-level factorial Plackett-Burman design. The screened medium components were optimized using response surface methodology (Box-Behnken Design). Artificial neural network (ANN) models combined with genetic algorithms (GA) further improved predictions and showed a remarkable impact on mAb production in P. pastoris. Under the optimal levels of medium components, the full-length TCZ and Fab were determined to be 0.35 mg/L and 0.42 g/L, respectively, in the shake-flask culture. The yield of full-length TCZ and Fab in batch reactor (2-L culture) was found to be 0.44 mg/L and 0.45 g/L, respectively, at the optimal levels of the medium components. The overall increased yields were observed to be 3.8 and 2.9-folds of full-length TCZ and Fab, respectively.

Machine learning assisted media optimization for enhanced insulin production in Pseudomonas fluorescens cell factory and scale-up studies

Diabetes mellitus, a chronic metabolic disorder, is characterized by high blood glucose levels. External insulin administration, along with diet and exercise, is recommended to the patients. The increase in the number of diabetics and the adoption of oral insulin uptake (higher dosage) has led to an enhancement in insulin demand. Although insulin has been expressed in Pseudomonas fluorescens-based expression system, medium optimization, a crucial step in bioprocess for product titer and yield improvement, has not been reported. In this study, medium components were screened using the Placket-Burman design (PBD) approach, which showed that glucose, sodium chloride, ammonium chloride, and magnesium sulphate have a significant effect on GST-proinsulin (GPI) fusion protein expression. The Box-Behnken design (BBD) and the Artificial Neural Network-Genetic Algorithm (ANN-GA) were implemented to determine the optimized level of the screened significant medium components. The optimized medium was used to validate the result in the shake flask, and the scale-up potential was studied in the batch reactor. The kinetic parameters estimated from the batch study were used to perform the fed-batch and continuous bioreactor experiments. The fed-batch reactor led to a maximum expression of 1145 mg/L proinsulin fusion protein, a 19-fold higher titer in the optimized medium. This study establishes the P. fluorescens expression system for high titer production of recombinant proteins and the importance of machine learning-assisted optimization over traditional statistical optimization techniques.

A comprehensive review of recombinant technology in the food industry: Exploring expression systems, application, and future challenges

Biotechnology has significantly advanced the production of recombinant proteins (RPs). This review examines the latest advancements in protein production technologies, including CRISPR, genetic engineering, vector integration, and fermentation, and their implications for the food industry. This review delineates the merits and shortcomings of prevailing host systems for RP production, underscoring molecular and process strategies pivotal for amplifying yields and purity. It traverses the spectrum of RP applications, challenges, and burgeoning trends, highlighting the imperative of employing robust hosts and cutting-edge genetic engineering to secure high-quality, high-yield outputs while circumventing protein aggregation and ensuring correct folding for enhanced activity. Recombinant technology has paved the way for the food industry to produce alternative proteins like leghemoglobin and cytokines, along with enzyme preparations such as proteases and lipases, and to modify microbial pathways for synthesizing beneficial compounds, including pigments, terpenes, flavonoids, and functional sugars. However, scaling microbial production to industrial scales presents economic, efficiency, and environmental challenges that demand innovative solutions, including high-throughput screening and CRISPR/Cas9 systems, to bolster protein yield and quality. Although recombinant technology holds much promise, it must navigate high costs and scalability to satisfy the escalating global demand for RPs in therapeutics and food. The variability in ethical and regulatory hurdles across regions further complicates market acceptance, underscoring an urgent need for robust regulatory frameworks for genetically modified organisms. These frameworks are essential for safeguarding the production process, ensuring product safety, and upholding the efficacy of RPs in industrial applications.

Therapeutic proteins: developments, progress, challenges, and future perspectives

Proteins are considered magic molecules due to their enormous applications in the health sector. Over the past few decades, therapeutic proteins have emerged as a promising treatment option for various diseases, particularly cancer, cardiovascular disease, diabetes, and others. The formulation of protein-based therapies is a major area of research, however, a few factors still hinder the large-scale production of these therapeutic products, such as stability, heterogenicity, immunogenicity, high cost of production, etc. This review provides comprehensive information on various sources and production of therapeutic proteins. The review also summarizes the challenges currently faced by scientists while developing protein-based therapeutics, along with possible solutions. It can be concluded that these proteins can be used in combination with small molecular drugs to give synergistic benefits in the future.

Challenges in developing cell culture media using machine learning

Microbial and mammalian cells are widely used in the food, pharmaceutical, and medical industries. Developing or optimizing culture media is essential to improve cell culture performance as a critical technology in cell culture engineering. Methodologies for media optimization have been developed to a great extent, such as the approaches of one-factor-at-a-time (OFAT) and response surface methodology (RSM). The present review introduces the emerging machine learning (ML) technology in cell culture engineering by combining high-throughput experimental technologies to develop highly efficient and effective culture media. The commonly used ML algorithms and the successful applications of employing ML in medium optimization are summarized. This review highlights the benefits of ML-assisted medium development and guides the selection of the media optimization method appropriate for various cell culture purposes.

Machine learning in bioprocess development: from promise to practice

Fostered by novel analytical techniques, digitalization, and automation, modern bioprocess development provides large amounts of heterogeneous experimental data, containing valuable process information. In this context, data-driven methods like machine learning (ML) approaches have great potential to rationally explore large design spaces while exploiting experimental facilities most efficiently. Herein we demonstrate how ML methods have been applied so far in bioprocess development, especially in strain engineering and selection, bioprocess optimization, scale-up, monitoring, and control of bioprocesses. For each topic, we will highlight successful application cases, current challenges, and point out domains that can potentially benefit from technology transfer and further progress in the field of ML.

Precision cellular agriculture: The future role of recombinantly expressed protein as food

Cellular agriculture is a rapidly emerging field, within which cultured meat has attracted the majority of media attention in recent years. An equally promising area of cellular agriculture, and one that has produced far more actual food ingredients that have been incorporated into commercially available products, is the use of cellular hosts to produce soluble proteins, herein referred to as precision cellular agriculture (PCAg). In PCAg, specific animal- or plant-sourced proteins are expressed recombinantly in unicellular hosts-the majority of which are yeast-and harvested for food use. The numerous advantages of PCAg over traditional agriculture, including a smaller carbon footprint and more consistent products, have led to extensive research on its utility. This review is the first to survey proteins currently being expressed using PCAg for food purposes. A growing number of viable expression hosts and recent advances for increased protein yields and process optimization have led to its application for producing milk, egg, and muscle proteins; plant hemoglobin; sweet-tasting plant proteins; and ice-binding proteins. Current knowledge gaps present research opportunities for optimizing expression hosts, tailoring posttranslational modifications, and expanding the scope of proteins produced. Considerations for the expansion of PCAg and its implications on food regulation, society, ethics, and the environment are also discussed. Considering the current trajectory of PCAg, food proteins from any biological source can likely be expressed recombinantly and used as purified food ingredients to create novel and tailored food products.

Recent advances in machine learning applications in metabolic engineering

Metabolic engineering encompasses several widely-used strategies, which currently hold a high seat in the field of biotechnology when its potential is manifesting through a plethora of research and commercial products with a strong societal impact. The genomic revolution that occurred almost three decades ago has initiated the generation of large omics-datasets which has helped in gaining a better understanding of cellular behavior. The itinerary of metabolic engineering that has occurred based on these large datasets has allowed researchers to gain detailed insights and a reasonable understanding of the intricacies of biosystems. However, the existing trail-and-error approaches for metabolic engineering are laborious and time-intensive when it comes to the production of target compounds with high yields through genetic manipulations in host organisms. Machine learning (ML) coupled with the available metabolic engineering test instances and omics data brings a comprehensive and multidisciplinary approach that enables scientists to evaluate various parameters for effective strain design. This vast amount of biological data should be standardized through knowledge engineering to train different ML models for providing accurate predictions in gene circuits designing, modification of proteins, optimization of bioprocess parameters for scaling up, and screening of hyper-producing robust cell factories. This review briefs on the premise of ML, followed by mentioning various ML methods and algorithms alongside the numerous omics datasets available to train ML models for predicting metabolic outcomes with high-accuracy. The combinative interplay between the ML algorithms and biological datasets through knowledge engineering have guided the recent advancements in applications such as CRISPR/Cas systems, gene circuits, protein engineering, metabolic pathway reconstruction, and bioprocess engineering. Finally, this review addresses the probable challenges of applying ML in metabolic engineering which will guide the researchers toward novel techniques to overcome the limitations.

Isolation of a bacterial strain from the gut of the fish, Systomus sarana, identification of the isolated strain, optimized production of its protease, the enzyme purification, and partial structural characterization

BACKGROUND

The present study focuses on the isolation of Bacillus thuringiensis bacterium from the gut of fresh water fish, Systomus sarana, the innovative optimization of culture parameters to produce maximum protease enzyme, by the isolated bacterium, and the elucidation of peptide profile of the protease. And the experimental data and results were authenticated through the response surface method (RSM) and Box-Behnken design (BBD) model.

RESULTS

During the RSM optimization, the interaction of the highest concentrations (%) of 2.2 maltose, 2.2 beef extract, and 7.0 pH, at 37 °C incubation, yielded a maximum protease enzyme of 245 U/ml by the fish gut-isolated, B. thuringiensis. The spectral analysis of the obtained enzyme revealed the presence of major functional groups at the range of 610-3852 cm^-1 viz., alkynes (-C≡C-H: C-H stretch), misc (P-H phosphine sharp), α, β-unsaturated aldehydes, and through PAGE analysis, its molecular weight was determined as 27 kDa. The enzyme's MALDI-TOF/MS analysis revealed the presence of 15 peptides from which the R.YHTVCDPR.L peptide has been found to be a major one.

CONCLUSIONS

The fish gut-isolated bacterium, B. thuringiensis, SS4 exhibited the potential for high protease production under the innovatively optimized culture conditions, and the obtained result provides scope for applications in food and pharmaceutical industries.

Synergisms of machine learning and constraint-based modeling of metabolism for analysis and optimization of fermentation parameters

Recent noteworthy advances in the development of high-performing microbial and mammalian strains have enabled the sustainable production of bio-economically valuable substances such as bio-compounds, biofuels, and biopharmaceuticals. However, to obtain an industrially viable mass-production scheme, much time and effort are required. The robust and rational design of fermentation processes requires analysis and optimization of different extracellular conditions and medium components, which have a massive effect on growth and productivity. In this regard, knowledge- and data-driven modeling methods have received much attention. Constraint-based modeling (CBM) is a knowledge-driven mathematical approach that has been widely used in fermentation analysis and optimization due to its capabilities of predicting the cellular phenotype from genotype through high-throughput means. On the other hand, machine learning (ML) is a data-driven statistical method that identifies the data patterns within sophisticated biological systems and processes, where there is inadequate knowledge to represent underlying mechanisms. Furthermore, ML models are becoming a viable complement to constraint-based models in a reciprocal manner when one is used as a pre-step of another. As a result, more predictable model is produced. This review highlights the applications of CBM and ML independently and the combination of these two approaches for analyzing and optimizing fermentation parameters. This article is protected by copyright. All rights reserved.

Biovalorisation of crude glycerol and xylose into xylitol by oleaginous yeast Yarrowia lipolytica

Background

Xylitol is a commercially important chemical with multiple applications in the food and pharmaceutical industries. According to the US Department of Energy, xylitol is one of the top twelve platform chemicals that can be produced from biomass. The chemical method for xylitol synthesis is however, expensive and energy intensive. In contrast, the biological route using microbial cell factories offers a potential cost-effective alternative process. The bioprocess occurs under ambient conditions and makes use of biocatalysts and biomass which can be sourced from renewable carbon originating from a variety of cheap waste feedstocks.

Result

In this study, biotransformation of xylose to xylitol was investigated using Yarrowia lipolytica, an oleaginous yeast which was firstly grown on a glycerol/glucose for screening of co-substrate, followed by media optimisation in shake flask, scale up in bioreactor and downstream processing of xylitol. A two-step medium optimization was employed using central composite design and artificial neural network coupled with genetic algorithm. The yeast amassed a concentration of 53.2 g/L xylitol using pure glycerol (PG) and xylose with a bioconversion yield of 0.97 g/g. Similar results were obtained when PG was substituted with crude glycerol (CG) from the biodiesel industry (titer: 50.5 g/L; yield: 0.92 g/g). Even when xylose from sugarcane bagasse hydrolysate was used as opposed to pure xylose, a xylitol yield of 0.54 g/g was achieved. Xylitol was successfully crystallized from PG/xylose and CG/xylose fermentation broths with a recovery of 39.5 and 35.3%, respectively.

Conclusion

To the best of the author’s knowledge, this study demonstrates for the first time the potential of using Y. lipolytica as a microbial cell factory for xylitol synthesis from inexpensive feedstocks. The results obtained are competitive with other xylitol producing organisms.

Recent Developments in Bioprocessing of Recombinant Proteins: Expression Hosts and Process Development

Infectious diseases, along with cancers, are among the main causes of death among humans worldwide. The production of therapeutic proteins for treating diseases at large scale for millions of individuals is one of the essential needs of mankind. Recent progress in the area of recombinant DNA technologies has paved the way to producing recombinant proteins that can be used as therapeutics, vaccines, and diagnostic reagents. Recombinant proteins for these applications are mainly produced using prokaryotic and eukaryotic expression host systems such as mammalian cells, bacteria, yeast, insect cells, and transgenic plants at laboratory scale as well as in large-scale settings. The development of efficient bioprocessing strategies is crucial for industrial production of recombinant proteins of therapeutic and prophylactic importance. Recently, advances have been made in the various areas of bioprocessing and are being utilized to develop effective processes for producing recombinant proteins. These include the use of high-throughput devices for effective bioprocess optimization and of disposable systems, continuous upstream processing, continuous chromatography, integrated continuous bioprocessing, Quality by Design, and process analytical technologies to achieve quality product with higher yield. This review summarizes recent developments in the bioprocessing of recombinant proteins, including in various expression systems, bioprocess development, and the upstream and downstream processing of recombinant proteins.

Accurate and cost-effective prediction of HBsAg titer in industrial scale fermentation process of recombinant Pichia pastoris by using neural network based soft sensor

In the current work, the attempt was made to apply best-fitted artificial neural network (ANN) architecture and the respective training process for predicting final titer of hepatitis B surface antigen (HBsAg), produced intracellularly by recombinant Pichia pastoris Mut⁺ in the commercial scale. For this purpose, in large-scale fed-batch fermentation, using methanol for HBsAg induction and cell growth, three parameters of average specific growth rate, biomass yield, and dry biomass concentration-in the definite integral form with respect to fermentation time-were selected as input vectors; the final concentration of HBsAg was selected for the ANN output. Used dataset consists of 38 runs from previous batches; feed-forward ANN 3:5:1 with training algorithm of backpropagation based on a Bayesian regularization was trained and tested with a high degree of accuracy. Implementing the verified ANN for predicting the HBsAg titer of the five new fermentation runs, excluded from the dataset, in the full-scale production, the coefficient of regression and root-mean-square error were found to be 0.969299 and 2.716774, respectively. These results suggest that this verified soft sensor could be an excellent alternative for the current relatively expensive and time-intensive analytical techniques such as enzyme-linked immunosorbent assay in the biopharmaceutical industry.

Soluble expression of IGF1 fused to DsbA in SHuffle™ T7 strain: optimization of expression and purification by Box-Behnken design

Production of insulin-like growth factor 1 (IGF1) in Escherichia coli mostly results in the formation of inclusion bodies. In the present study, IGF1 was fused to disulfide bond oxidoreductase A (DsbA) and expressed in SHuffle™ T7 strain, in order to obtain correctly folded protein. Soluble expression and IMAC purification of DsbA-IGF1 were optimized by applying the Box-Behnken design of response surface methodology. The optimization greatly increased concentration of soluble protein from 317 to 2600 mg/L, and IMAC yield from 400 to 1900 mg/L. Results of ANOVA showed induction OD600 and temperature had significant effects on the soluble protein expression while isopropyl-β-d thiogalactoside, in the concentrations tested, displayed no significant effect. Moreover, the three parameters of the binding buffer including, pH, concentration of NaCl, and imidazole displayed significant effects on the IMAC yield. Then, purified DsbA-IGF1 was cleaved by human rhinovirus 3C protease, and authentic IGF1 was obtained in flow through of a subtractive IMAC. Final polishing of the protein by reversed-phase HPLC yielded IGF1 with purity of 96%. The quality attributes of purified IGF1 such as purity, identity, molecular size, molecular weight, secondary structure, and biological activity were assessed and showed to be comparable to the standard IGF1. The final yield of purified IGF1 was estimated to be 120 ± 18 mg from 1 L of the culture. Our results demonstrated a simple and easily scalable strategy for production of large amounts of bioactive IGF1 by rational designing soluble protein expression, and further optimization of expression and purification methods.