This book reviews the advances in data gathering and processing in the biotech laboratory environment, and it sheds new lights on the various aspects that are necessary for the implementation of intelligent laboratory architecture and infrastructure. Smart technologies are increasingly dominating our everyday lives and have become an indispensable part of the industrial environment. The laboratory environment, which has long been rather conservative, has also set out to adapt smart technologies with regards to Industry 4.0 and the Internet of Things (IoT) for the laboratory. Due to the heterogeneity of the existing infrastructure and the often complex work processes, standardization is slow, e.g. to implement device interfaces or standardized driver protocols, which are urgently needed to generate standardized data streams that would be immanent for post-processing of data.
Divided into 9 chapters, this book offers an authoritative overview of the diverse aspects in the generation and recording of uniform data sets in the laboratory, and in the processing of the data and enabling seamless processing towards machine learning and artificial intelligence. In the first part of the book, readers will find more about high throughout systems, automation, robotics, and the evolution of technology in the laboratory. The second part of the book is devoted to standardization in lab automation, in which readers will learn more about some regulatory aspects, the SiLA2 standards, the OPC LADS (Laboratory and Analytical Device Standard), and FAIR Data infrastructure
Author(s): Sascha Beutel, Felix Lenk
Series: Advances in Biochemical Engineering/Biotechnology, 182
Publisher: Springer
Year: 2022
Language: English
Pages: 212
City: Cham
Preface
Contents
Part I: Data Gathering Part
Automation for Life Science Laboratories
1 Introduction
1.1 Definition Automation
1.2 Automation in Life Sciences
2 Robots in Life Sciences
2.1 Introduction
2.2 Stationary Robots
2.3 Mobile Robots
3 Innovative Automation Devices
3.1 Introduction
3.2 Devices for Labware Handling
3.3 Devices for Sample Processing
4 Automation Strategies
5 Summary and Outlook
References
Evolution of Artificial Intelligence-Powered Technologies in Biomedical Research and Healthcare
1 Prologue
2 Introduction
2.1 Brief Historical Overview of AI
2.2 Understanding AI
2.3 AI Inception
2.4 AI Training Workflow
3 Machine Learning
3.1 Supervised Learning
3.2 Semi-Supervised Learning
3.3 Self-Supervised Learning
3.4 A Note on Reinforcement Learning
4 Deep Learning
4.1 Artificial Neural Networks (ANN)
4.2 Brief Overview of DL Models
4.2.1 Feed Forward Neural Networks (FFNNs)
4.2.2 Recurrent Neural Networks (RNN)
4.2.3 Convolutional Neural Network (CNN)
4.2.4 Autoencoders (AEs)
5 AI-Derived Applications in Biology and Biomedical Research
5.1 AI in Structural Biology
5.2 AI in Clinical Genomics
5.3 AI in Image Analysis
5.4 AI in Multiomics Analysis
5.5 AI in Documentation and Data Management
5.6 Deep Learning in Drug Discovery
5.6.1 Phenotypic Drug Discovery
5.6.2 Virtual Screening
5.6.3 Target-Based Drug Discovery
6 AI as a Powerful Tool for Precision Medicine
7 Limitations of AI
8 Conclusions
References
A Comprehensive IT Infrastructure for an Enzymatic Product Development in a Digitalized Biotechnological Laboratory
1 Introduction
2 Solutions for Laboratory Digitalization and Digitization
2.1 Process Overview
2.2 Software in the Laboratory Infrastructure
2.2.1 Electronic Lab Notebook
2.2.2 Laboratory Information and Management System
2.2.3 Laboratory Execution Software
2.2.4 Manufacturing and Execution System
2.2.5 Supervisory Control and Data Acquisition and Distributed Control System
2.2.6 Overview Software
2.3 Data Exchange Between Laboratory Software
2.4 Device Integration
3 Discussion
4 Conclusion and Outlook
References
Human-Device Interaction in the Life Science Laboratory
1 Introduction
2 The Evolution of Laboratory Devices
3 The Rise and Evolution of Software in the Lab
4 Natural User Interfaces in the Laboratory
4.1 Touch-Based User Interfaces
4.1.1 Smartphone and Tablet Applications in the (Bio)chemical Laboratory
4.1.2 Assistance Applications for Smartphones and Tablets in the Laboratory
4.1.3 Smartphones and Tablets as Equipment Replacement
4.2 Touchless User Interfaces
4.2.1 Gesture and Motion-Based Interfaces in the Laboratory
4.2.2 Voice User Interfaces in the Laboratory
4.2.3 AI in Natural Language Processing
4.2.4 Voice Assistants
4.3 Smartglasses and Their Applications in the Life Science Laboratory
5 Concluding Remarks and Outlook
References
Flexible Digitization of Highly Individualized Workflows Demonstrated Through the Quality Control of Patient-Specific Cytostat...
1 Introduction
2 The Use Case
3 The Analogue Application Bag Workflow
4 The Digitization Processes
4.1 Digital Transformation of the Workflow
4.2 Device Integration
4.3 Data Processing and Reporting
5 Conclusion and Outlook
References
Part II: Data Processing Part
Comparison of Laboratory Standards
1 Definition of Standards
2 Need for Standards and Norms
3 Standardization in the Laboratory
3.1 Need for Standards
3.2 Classification
3.3 Summary
4 Standardization Through Modularization
4.1 Current State of Digitization
4.2 Modular Lab
5 Conclusion
References
SiLA 2: The Next Generation Lab Automation Standard
1 The Need for SiLA
1.1 Cornerstones for Successful Digitalization
1.2 Standardization as a Necessary Precondition
1.3 SiLA Connector for Non-SiLA and Legacy Instruments
2 How Does SiLA Work?
2.1 Client Server Infrastructure
2.2 Discovery of SiLA Servers and Service in the Network
2.3 Service Capabilities: Features
2.4 SiLA Client and Server Interaction in a Nutshell
3 Example Use Cases
3.1 Balances
3.2 Chromatography Data Systems
3.3 Laboratory Information Management Systems
4 Cloud Connectivity Support
4.1 SiLA Edge Gateway
5 Lab Digitalization
5.1 The FAIR Data Principles
5.2 Findable, Accessible, Interoperable, and Reusable
5.3 Standard Data Formats
6 Instrument Integration
6.1 Instrument Vendor Perspective
6.1.1 Integration Through Standards
6.1.2 Scheduling
6.1.3 Protect Investments
6.2 The SiLA Connector for Legacy Instruments
7 A Community Effort
7.1 Great Ecosystem
8 Data Integrity
8.1 Reduce Time and Cost
8.2 Single Standard
8.3 Key Principles for Data Integrity
8.4 Paper-Based Vulnerabilities
8.5 Physical Files
8.6 File-Less Communication
8.7 Modular Validation Strategy
8.8 Benefits of SiLA
9 Future Proof
9.1 Effortless Digitalization
9.2 The Last Mile to the Instrument
9.3 SiLA: Key for Digitalization
10 SiLA: Free and Open
11 About SiLA
11.1 Mission
11.2 A Community Effort
11.3 Membership
11.4 Technical Details
11.5 The SiLA Specification
11.6 Key Design Principles
11.7 Conclusion
12 Further Readings
12.1 Official Documentation
12.2 SiLA 2 Tools
12.3 SiLA 2 Community
12.4 The Digital Lab in a Nutshell
12.5 Articles/Media/Publications
Reference
Laboratory and Analytical Device Standard (LADS): A Communication Standard Based on OPC UA for Networked Laboratories
1 Overview
2 Introduction
3 Increased Efficiency with a Digital, Networked Laboratory
3.1 The Status Quo: A Heterogeneous Environment and a Lack of Standards
3.2 The Requirements for Digital, Networked Laboratories
4 Industry 4.0 as a Blueprint: Best of Breed and OPC UA
4.1 Best of Breed
4.2 OPC UA
5 Laboratory and Analytical Device Standard (LADS)
5.1 Reasons for OPC UA as a Technological Basis for LADS
5.2 Implementation of LADS
6 What LADS Means to the Laboratory Environment and the Lab of the Future
6.1 Laboratory Devices
6.2 Ambient Data and Sensors
6.3 Process Analysis
6.3.1 Automated Data Transfers
6.3.2 Measurement Islands
6.3.3 Reproducible Production Conditions
6.4 Digital Device Records and Services
6.5 Networking
6.6 Management
7 Conclusion
References
FAIR Data Infrastructure
1 Introduction
2 Research Data and Research Data Management
3 Metadata
4 FAIR Data Principles
5 (FAIR) Data Infrastructure
6 Summary and Outlook
References
