Machine learning in computational biology to accelerate high-throughput protein expression

Advances in mRNA LNP-Based Cancer Vaccines: Mechanisms, Formulation Aspects, Challenges, and Future Directions

After the COVID-19 pandemic, mRNA-based vaccines have emerged as a revolutionary technology in immunization and vaccination. These vaccines have shown remarkable efficacy against the virus and opened up avenues for their possible application in other diseases. This has renewed interest and investment in mRNA vaccine research and development, attracting the scientific community to explore all its other applications beyond infectious diseases. Recently, researchers have focused on the possibility of adapting this vaccination approach to cancer immunotherapy. While there is a huge potential, challenges still remain in the design and optimization of the synthetic mRNA molecules and the lipid nanoparticle delivery system required to ensure the adequate elicitation of the immune response and the successful eradication of tumors. This review points out the basic mechanisms of mRNA-LNP vaccines in cancer immunotherapy and recent approaches in mRNA vaccine design. This review displays the current mRNA modifications and lipid nanoparticle components and how these factors affect vaccine efficacy. Furthermore, this review discusses the future directions and clinical applications of mRNA-LNP vaccines in cancer treatment.

Optimizing recombinant antibody fragment production: A comparison of artificial intelligence and statistical modeling

Maximizing the recombinant protein yield necessitates optimizing the production medium. This can be done using a variety of methods, including the conventional "one-factor-at-a-time" approach and more recent statistical and mathematical methods such as artificial neural network (ANN), genetic algorithm, etc. Every approach has advantages and disadvantages of its own, yet even when a technique has flaws, it is nevertheless used to get the best results. Here, one categorical variable and four numerical parameters, including post-induction time, inducer concentration, post-induction temperature, and pre-induction cell density, were optimized using the 232 experimental assays of the central composite design. The direct and indirect effects of factors on the yield of anti-epithelial cell adhesion molecule extracellular domain fragment antibody were examined using statistical methods. The analysis of variance results indicate that the response surface methodology (RSM) model is effective in predicting the amount of produced single-chain fragment variable (p-value = 0.0001 and R2 = 0.905). For ANN modeling, the evaluation using normalized root mean square error (NRMSE) and R2 values shows a good fit (R2 = 0.942) and accurate predictions (NRMSE = 0.145). The analysis of error parameters and R2 of a dataset, which contained 30 data points randomly selected from the complete dataset, showed that the ANN model had a higher R2 value (0.968) compared to the RSM model (0.932). Furthermore, the ANN model demonstrated stronger predictive ability with a lower NRMSE (0.048 vs. 0.064). Induction at the cell density of 0.7 and an isopropyl β-D-1-thiogalactopyranoside concentration of 0.6 mM for 32 h at 30°C in BW25113 was the ideal culture condition leading to the protein yield of 259.51 mg/L. Under the optimum conditions, the output values predicted by the ANN model (259.83 mg/L) were more in line with the experimental data (259.51 mg/L) than the RSM (276.13 mg/L) expected value. This outcome demonstrated that the ANN model outperforms the RSM in terms of prediction accuracy.

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.

Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains

The solubility of proteins is usually a necessity for their functioning. Recently an emergence of machine learning approaches as trained alternatives to statistical models has been evidenced for empirical modeling and optimization. Here, soluble production of anti-EpCAM extracellular domain (EpEx) single chain variable fragment (scFv) antibody was modeled and optimized as a function of four literature based numerical factors (post-induction temperature, post-induction time, cell density of induction time, and inducer concentration) and one categorical variable using artificial neural network (ANN) and response surface methodology (RSM). Models were established by the CCD experimental data derived from 232 separate experiments. The concentration of soluble scFv reached 112.4 mg/L at the optimum condition and strain (induction at cell density 0.6 with 0.4 mM IPTG for 24 h at 23 °C in Origami). The predicted value obtained by ANN for the response (106.1 mg/L) was closer to the experimental result than that obtained by RSM (97.9 mg/L), which again confirmed a higher accuracy of ANN model. To the author's knowledge this is the first report on comparison of ANN and RSM in statistical optimization of fermentation conditions of E.coli for the soluble production of recombinant scFv.

Machine and Deep Learning for Prediction of Subcellular Localization

Protein subcellular localization prediction (PSLP), which plays an important role in the field of computational biology, identifies the position and function of proteins in cells without expensive cost and laborious effort. In the past few decades, various methods with different algorithms have been proposed in solving the problem of subcellular localization prediction; machine learning and deep learning constitute a large portion among those proposed methods. In order to provide an overview about those methods, the first part of this article will be a brief review of several state-of-the-art machine learning methods on subcellular localization prediction; then the materials used by subcellular localization prediction is described and a simple prediction method, that takes protein sequences as input and utilizes a convolutional neural network as the classifier, is introduced. At last, a list of notes is provided to indicate the major problems that may occur with this method.

Independent component analysis of E. coli's transcriptome reveals the cellular processes that respond to heterologous gene expression

Achieving the predictable expression of heterologous genes in a production host has proven difficult. Each heterologous gene expressed in the same host seems to elicit a different host response governed by unknown mechanisms. Historically, most studies have approached this challenge by manipulating the properties of the heterologous gene through methods like codon optimization. Here we approach this challenge from the host side. We express a set of 45 heterologous genes in the same Escherichia coli strain, using the same expression system and culture conditions. We collect a comprehensive RNAseq set to characterize the host's transcriptional response. Independent Component Analysis of the RNAseq data set reveals independently modulated gene sets (iModulons) that characterize the host response to heterologous gene expression. We relate 55% of variation of the host response to: Fear vs Greed (16.5%), Metal Homeostasis (19.0%), Respiration (6.0%), Protein folding (4.5%), and Amino acid and nucleotide biosynthesis (9.0%). If these responses can be controlled, then the success rate with predicting heterologous gene expression should increase.

Affinity purification of Car9-tagged proteins on silica-derivatized spin columns and 96-well plates

The Car9 affinity tag is a dodecameric silica-binding peptide that can be fused to the N- and C-termini of proteins of interest to enable their rapid and inexpensive purification on underivatized silica in a process that typically relies on l-lysine as an eluent. Here, we show that silica paper spin columns and borosilicate multi-well plates used for plasmid DNA purification are suitable for recovering Car9-tagged proteins with high purity in a workflow compatible with high-throughput experiments. Spin columns typically yield 100 μg of biologically active material that can be recovered in minutes with low concentrations of lysine. Because of their short bed length, spin columns also offer unique advantages, as evidenced by the selective recovery of functional Car9-tagged tobacco etch virus (TEV) protease from a fused and auto-cleaved maltose binding protein (MBP) folding partner that nonspecifically binds to silica in the presence of NaCl. These additional purification modalities should increase the versatility and appeal of the Car9 tag for affinity protein purification.

Metabolite-Induced Protein Expression Guided by Metabolomics and Systems Biology

Metabolomics combined with systems biology can be used to identify endogenous metabolites that modulate protein expression. Recent examples include the 2-fold enhancements of pertussis toxin protein in vaccine production and myelin basic protein expression in oligodendrocyte maturation; both applied a metabolomics-systems strategy to identify active metabolites.