Recent advances in machine learning applications in metabolic engineering

Patra, Pradipta; Disha, B.R.; Kundu, Pritam; Das, Manali; Ghosh, Amit

doi:10.1016/j.biotechadv.2022.108069

Cited by 39 publications

(15 citation statements)

References 200 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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. 142 This vast amount of biological data should be standardized through knowledge engineering to train different ML models for providing accurate predictions in the dose−effect relationship between gene expression and function of key enzymes in triterpenoids synthesis and screening of hyperproducing robust cell factories. However, the lack of high throughput methods makes the application of machine learning to the synthesis of triterpenoids inefficient.…”

Section: Discussion and Perspectivementioning

confidence: 99%

Efficient Plant Triterpenoids Synthesis in Saccharomyces cerevisiae: from Mechanisms to Engineering Strategies

Wang,

Meng,

Feng

et al. 2024

ACS Synth. Biol.

View full text Add to dashboard Cite

Triterpenoids possess a range of biological activities and are extensively utilized in the pharmaceutical, food, cosmetic, and chemical industries. Traditionally, they are acquired through chemical synthesis and plant extraction. However, these methods have drawbacks, including high energy consumption, environmental pollution, and being time-consuming. Recently, the de novo synthesis of triterpenoids in microbial cell factories has been achieved. This represents a promising and environmentally friendly alternative to traditional supply methods. Saccharomyces cerevisiae, known for its robustness, safety, and ample precursor supply, stands out as an ideal candidate for triterpenoid biosynthesis. However, challenges persist in industrial production and economic feasibility of triterpenoid biosynthesis. Consequently, metabolic engineering approaches have been applied to improve the triterpenoid yield, leading to substantial progress. This review explores triterpenoids biosynthesis mechanisms in S. cerevisiae and strategies for efficient production. Finally, the review also discusses current challenges and proposes potential solutions, offering insights for future engineering.

show abstract

Section: Discussion and Perspectivementioning

confidence: 99%

Efficient Plant Triterpenoids Synthesis in Saccharomyces cerevisiae: from Mechanisms to Engineering Strategies

Wang,

Meng,

Feng

et al. 2024

ACS Synth. Biol.

View full text Add to dashboard Cite

show abstract

“…In the field of protein function, the incorporation of machine learning into analytical models can improve the accuracy of prediction and in-depth analysis of protein function [ 20 ]. In the field of metabolic engineering, machine learning has improved data analysis methods, saving time and improving the accuracy of predicting metabolic results [ 21 ]. Generalized Linear Models (GLM) is a regression model for non-normal dependent variables [ 22 ]; Random Forest (RF) can evaluate the importance of variables and model predictions [ 23 ]; Support Vector Machine (SVM) is a two-class classification model that assigns labels to objects through instance learning [ 24 ]; and Extreme Gradient Boosting (XGB) is to integrate the prediction results of multiple classifiers as the most do that prediction [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Identification and validation of cuproptosis related genes and signature markers in bronchopulmonary dysplasia disease using bioinformatics analysis and machine learning

Jia

Zhang

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Bronchopulmonary Dysplasia (BPD) has a high incidence and affects the health of preterm infants. Cuproptosis is a novel form of cell death, but its mechanism of action in the disease is not yet clear. Machine learning, the latest tool for the analysis of biological samples, is still relatively rarely used for in-depth analysis and prediction of diseases. Methods and results First, the differential expression of cuproptosis-related genes (CRGs) in the GSE108754 dataset was extracted and the heat map showed that the expression of NFE2L2 gene was significantly higher in the control group whereas the expression of GLS gene was significantly higher in the treatment group. Chromosome location analysis showed that both the genes were positively correlated and associated with chromosome 2. The results of immune infiltration and immune cell differential analysis showed differences in the four immune cells, significantly in Monocytes cells. Five new pathways were analyzed through two subgroups based on consistent clustering of CRG expression. Weighted correlation network analysis (WGCNA) set the screening condition to the top 25% to obtain the disease signature genes. Four machine learning algorithms: Generalized Linear Models (GLM), Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB) were used to screen the disease signature genes, and the final five marker genes for disease prediction. The models constructed by GLM method were proved to be more accurate in the validation of two datasets, GSE190215 and GSE188944. Conclusion We eventually identified two copper death-associated genes, NFE2L2 and GLS. A machine learning model-GLM was constructed to predict the prevalence of BPD disease, and five disease signature genes NFATC3, ERMN, PLA2G4A, MTMR9LP and LOC440700 were identified. These genes that were bioinformatics analyzed could be potential targets for identifying BPD disease and treatment.

show abstract

“…Although numerous qualitative aging experiments exist on the antioxidation mechanism of antioxidant molecules, quantitative studies involving molecular insights into the antioxidant efficiency of natural antioxidant molecules are still inadequate. Computational tools predict materials’ dynamic and quantum mechanical (QM) properties on multiple scales. − Molecular theories have made the utmost advancement in the field of polymer nanocomposites for calculating equilibrium phase and macroscopic properties. − Thus, QM and MD simulations were meant to be carried out to investigate the relationship between the molecular structure and the chemical nature of the antioxidant molecules. The present study thus aims to examine the influence of the interfacial interactions among the antioxidants, polymer, and fillers on the interfacial bonding and the interphase antioxidant properties of the model nanocomposites, which are difficult to access experimentally.…”

Section: Introductionmentioning

confidence: 99%

Molecular Insights into Antioxidant Efficiency of Melanin: A Sustainable Antioxidant for Natural Rubber Formulations

Abdul Sattar,

Patnaik

2023

J. Phys. Chem. B

View full text Add to dashboard Cite

N-(1,3-Dimethyl butyl)-N′-phenyl-p-phenylenediamine (6-PPD) is a worldwide antioxidant commonly added to delay the thermo-oxidative degradation of tire rubbers. Unfortunately, 6PPD and its transformation product 6PPD-quinone are toxic to aquatic organisms (e.g., coho salmon). Herein, we explore the free radical scavenging activity and protective mechanism of melanin (MLN) on natural rubber's (NR's) oxidative resistance using molecular dynamics (MD) and quantum mechanical (QM) calculations. The relationship between the molecular structure and the chemical nature of the antioxidant molecules via transition state calculations is explored to unravel the reaction mechanisms of antioxidants interacting with peroxy radicals (ROO • ) of NR with the estimation of reaction barriers. Following this, the radical scavenging activity of antioxidants was quantified via a hydrogen atom transfer mechanism and bond dissociation energy calculations. Parallel MD simulations were considered to study the interfacial interactions of antioxidant molecules with polymer chains and fillers with a quantifiable structure−property correlation. Given these results, the nanocomposite (NR-MLN-SiO 2 ) with natural antioxidant melanin manifested outstanding antioxidant properties by preferentially bagging the ROO • radicals, thus improving NR's thermal-oxidative aging relative to 6-PPD. The MD results revealed that the intermolecular interactions at the NR/antioxidant interface benefited the antioxidant MLN to bind tightly to the NR in NR-MLN-SiO 2 composite, thus exhibiting improved dispersion, O 2 barrier properties, and thermo-oxidative stability, which could extend the service life of NR products (e.g., tires). In addition, as a sustainable antioxidant, MLN could replace toxic antioxidants like 6-PPD. More importantly, the QM/MD simulations provided a fundamental understanding of the mechanistic pathways of antioxidant molecules in NR composites, which are conducive to designing highperformance and sustainable green elastomers.

show abstract

Recent advances in machine learning applications in metabolic engineering

Cited by 39 publications

References 200 publications

Efficient Plant Triterpenoids Synthesis in Saccharomyces cerevisiae: from Mechanisms to Engineering Strategies

Efficient Plant Triterpenoids Synthesis in Saccharomyces cerevisiae: from Mechanisms to Engineering Strategies

Identification and validation of cuproptosis related genes and signature markers in bronchopulmonary dysplasia disease using bioinformatics analysis and machine learning

Molecular Insights into Antioxidant Efficiency of Melanin: A Sustainable Antioxidant for Natural Rubber Formulations

Contact Info

Product

Resources

About