This book is designed as a reference book and presents a systematic approach to analyze evolutionary and nature-inspired population-based search algorithms. Beginning with an introduction to optimization methods and algorithms and various enzymes, the book then moves on to provide a unified framework of process optimization for enzymes with various algorithms. The book presents current research on various applications of machine learning and discusses optimization techniques to solve real-life problems.
- The book compiles the different machine learning models for optimization of process parameters for production of industrially important enzymes. The production and optimization of various enzymes produced by different microorganisms are elaborated in the book
- It discusses the optimization methods that help minimize the error in developing patterns and classifications, which further helps improve prediction and decision-making
- Covers the best-performing methods and approaches for optimization sustainable enzymes production with AI integration in a real-time environment
- Featuring valuable insights, the book helps readers explore new avenues leading towards multidisciplinary research discussions
The book is aimed primarily at advanced undergraduates and graduates studying machine learning, data science and industrial biotechnology. Researchers and professionals will also find this book useful.
Author(s): J. Satya Eswari, Nisha Suryawanshi
Publisher: CRC Press/Chapman & Hall
Year: 2022
Language: English
Pages: 231
City: Boca Raton
Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Chapter 1: Industrially Important Enzymes
1.1 Introduction
1.2 Structure
1.3 Enzyme Classification
1.3.1 Microbial Enzymes
1.4 Industrial Enzyme Applications
1.4.1 Enzymes in Food Processing
1.4.2 Enzymes in Cosmetics
1.5 Commercially Important Enzymes
1.6 Typical Enzyme Production Process
1.6.1 Industrial Enzymes
1.6.2 Medium Formulation and Preparation
1.6.3 Medium Sterilization
1.6.4 Purification of Enzymes
1.7 World Market
1.8 Summary
Review Questions
Bibliography
Chapter 2: Applications of Industrially Important Enzymes
2.1 Introduction: Enzymes as Industrial Biocatalysts
2.2 The Use of Enzymes in Industrial Processes
2.2.1 Food Industry
2.2.1.1 Enzymes in Dairy Industry
2.2.1.2 Enzymes in Baking Industry
2.2.1.3 Enzymes in Other Food Industry
2.2.2 Feed Industry
2.2.3 Pharmaceutical and Analytical Industry
2.2.4 Paper and Pulp Industry
2.2.5 Leather Industry
2.2.6 Textile Industry
2.2.7 Enzymes in Cosmetics Industry
2.2.8 Enzymes in Detergent Industry
2.2.9 Organic Synthesis Industry
2.2.10 Enzymes used in Waste Treatment
2.3 Conclusion
Conflict of Interest
References
Chapter 3: Optimization of Fermentation Process: Influence on Industrial Production of Enzymes
3.1 Introduction
3.1.1 On the Production of Enzymes
3.1.2 Fermentation Technology in Enzyme Production
3.1.2.1 Submerged Fermentation
3.1.2.2 Solid-State Fermentation
3.2 Operational Issues with Fermentation Process Engineering
3.2.1 Fermentation Control Specifics
3.3 Factors Affecting Fermentation Process
3.3.1 Media Composition
3.3.2 pH
3.3.3 Temperature
3.3.4 Mechanical Forces and Aeration
3.4 Optimization of Fermentation Process Technology
3.4.1 Literature Mining
3.4.2 Nutrient Swapping
3.4.3 Biological Simulation
3.4.4 One Factor-at-a-Time
3.4.5 Factorial Design
3.4.6 Plackett and Burman’s Strategy
3.4.7 Response Surface Methodology
3.4.8 Evolutionary Operation
3.4.9 Artificial Neural Network
3.4.10 Fuzzy Logic
3.4.11 Genetic Algorithm
3.5 Conclusions
References
Chapter 4: Reforming Process Optimization of Enzyme Production Using Artificial Intelligence and Machine Learning
4.1 Introduction
4.2 Process of Enzyme Production
4.2.1 Need for the Process Optimization in Enzyme Production
4.3 Machine Learning Models
4.3.1 Types of Machine Learning Model
4.4 Role of Machine Learning in the Process Optimization of Enzyme Production
4.4.1 Artificial Neural Networks (ANN)
4.4.2 Genetic Algorithms (GA)
4.5 Advantages of Using Artificial Intelligence and Machine Learning
4.6 Disadvantages or Limitations of Machine Learning in the Process Optimization of Enzyme Production
4.7 Challenges and Prospects
4.8 Conclusion
References
Chapter 5: Scale-Up Models for Chitinase Production, Enzyme Kinetics, and Optimization
5.1 Introduction
5.2 Response Surface Methodology
5.3 Plackett–Burman Design
5.4 Box–Behnken Experimental Design
5.5 Machine Learning
5.6 Artificial Neural Networks
5.7 Multilayer Feedforward Networks
5.8 Genetic Algorithm
5.9 Particle Swarm Optimization
5.10 Enhancement of Production – Significant Studies
5.11 Advantages of Process Optimization Using Advanced Tools
5.12 Role of ANN in Scale-Up of Fermentation
5.13 Conclusion
References
Chapter 6: Genetic Algorithm for Optimization of Fermentation Processes of Various Enzyme Productions
6.1 Introduction
6.2 Industrial Production of Enzymes from Microbial Sources
6.2.1 Fermentation Methods
6.2.1.1 Solid-State Fermentation
6.2.1.2 Submerged Fermentation
6.2.2 Fermentation Parameters
6.3 Optimization Strategies for Enhanced Enzyme Production
6.3.1 Medium Optimization Methods
6.4 Genetic Algorithm as Optimization Technique for Fermentation Process
6.4.1 History of GA
6.4.2 Applications of GA to Optimize Fermentation Processes
6.5 Problems and Bottlenecks in Optimization Techniques
6.6 Overview and Conclusions
Bibliography
Chapter 7: Optimization of Process Parameters of Various Classes of Enzymes Using Artificial Neural Network
7.1 Introduction
7.2 Strategy to Solve Optimization Problems
7.3 Description and Architecture of Artificial Neural Networks
7.3.1 ANN as an Optimizer
7.3.2 Example of ANN in Optimization of Process Parameters for Various Classes of Enzymes
7.4 Description and Application Response Surface Methodology for Process Optimization
7.5 Comparison of ANN and RSM Methodology
7.6 Conclusions
References
Chapter 8: Advanced Evolutionary Differential Evolution and Central Composite Design: Comparative Study for Process Optimization of Chitinase Production
8.1 Introduction
8.2 Methods and Materials
8.2.1 Microorganism and Growth Condition
8.2.2 Substrate Preparation (Colloidal Chitin)
8.2.3 Production of Chitinase
8.2.4 Chitinase Enzyme Activity Assay
8.2.5 Statistical Optimization of Medium Components
8.2.5.1 Plackett–Burman Design
8.2.5.2 The Central Composite Design and the Response Surface Methodology
8.2.6 Machine Learning Approach: Differential Evolution
8.2.6.1 Differential Evolution in the Context
8.2.6.2 The Fundamentals of DE Algorithms
8.2.6.2.1 Initialization
8.2.6.2.2 Mutation
8.2.6.2.3 Crossover
8.2.6.2.4 Selection
8.2.7 Validation of the Experiment
8.3 Results and Discussion
8.3.1 Plackett–Burman Design
8.3.2 Central Composite Design
8.3.3 Differential Evolution (DE)
8.3.4 Experiment Model Validation
8.4 Conclusion
Acknowledgments
References
Chapter 9: Artificial Bee Colony for Optimization of Process Parameters for Various Enzyme Productions
9.1 Introduction
9.2 ABC Algorithm Motivations
9.3 Optimization of Artificial Bee Colony Algorithm
9.4 Honey Bees’ Foraging Behavior
9.5 Iteration Steps in ABC for Optimization
9.5.1 Swarm Initialization
9.5.2 Onlooker Bee
9.5.3 Scout Bee Phase
9.5.4 Termination
9.6 ABC in Process Optimization Methodology
9.7 Novel Modified ABC (MABC)
9.8 Effect of Different Parameters in ABC of Enzyme Optimization
9.9 Control Parameters in ABC for Optimization
9.10 ABC Algorithm Modifications
9.11 Summary of ABC
9.12 Application of ABC
9.13 Conclusions and Future Prospects
References
Index
