Biopharmaceutical Informatics: Learning to Discover Developable Biotherapeutics

Cover
Half Title
Biopharmaceutical Informatics: Learning to Discover Developable Biotherapeutics
Copyright
Dedication
Contents
Foreword
Preface
About the Editors
Contributors
1. Biopharmaceutical Informatics: An Introduction
	References
2. Digital Transformation in the Biopharmaceutical Industry: Rebuilding the Way We Discover Complex Therapeutics
	2.1 Introduction
	2.2 Current State of Digitalisation in Pre-Clinical R&D
	2.3 Challenges in Digital Transformation of Pre-Clinical R&D
		2.3.1 Operational Challenges
		2.3.2 Cultural Challenges
		2.3.3 Data Management, Data Analytics, and Integrity Concerns
		2.3.4 Barriers to Automation Adoption
	2.4 Core Ingredients for Successful Digital Transformation
		2.4.1 New Data-Generation Methods and Laboratory Automation
		2.4.2 Cloud Computing
		2.4.3 Machine Learning and MLOps to Support the Machine Learning Life Cycle
		2.4.4 Company Culture That Drives a Data-Driven Approach
	2.5 Case Studies of Successful Digital Transformation
	2.6 Conclusion
	References
3. Computational Protein Design Strategies for Optimization of Antigen Generation to Drive Antibody Discovery
	3.1 Introduction
	3.2 Target Protein (Antigen) Considerations for Antibody Discovery
	3.3 Antigen Generation Strategies
	3.4 Computational Methods
		3.4.1 Impact of AI/ML on Target Protein Expression, Construct Design, and Protein Production
		3.4.2 Computational Protein Structure Prediction
	3.5 Case Study Examples of Antigen Design Strategies to Drive Drug Discovery and Immunogen Performance
	3.6 Conclusions: Computational Antigen Design and Future Developments
	References
4. Bioinformatic Analyses of Antibody Repertoires and Their Roles in Modern Antibody Drug Discovery
	4.1 Introduction
	4.2 NGS Technologies, Tools, and Data Analysis for Modern Antibody Discovery
	4.3 NGS-Enabled In Vivo Antibody Discovery from Immunized Animals
	4.4 NGS-Enabled In Vitro Antibody Discovery from Display Libraries
	4.5 NGS-Enabled In Silico Antibody Discovery via Artificial Intelligence Methods
	4.6 Summary and Future Directions
	Acknowledgments
	References
5. Applications of Artificial Intelligence and Machine Learning toward Antibody Discovery and Development
	5.1 Introduction
	5.2 Databases
		5.2.1 Databases in Machine Learning Approaches
		5.2.2 Database Types
	5.3 Applications of Machine Learning in Antibody Discovery and Development
		5.3.1 Structure Prediction with Deep Learning
		5.3.2 Antibody-Binding Prediction by Deep Learning (Paratope Prediction)
		5.3.3 Developability
	5.4 Antibody Generation and Design by Language Models
		5.4.1 Antibody Representations
		5.4.2 Representation Learning
		5.4.3 Language Models
	5.5 Conclusions and Future Perspectives in AI for Antibody Discovery
	References
6. From Deep Generative Models to Structure-Based Simulations: Computational Approaches for Antibody Design
	6.1 Introduction
	6.2 Antibody Generation through Deep Generative Models
		6.2.1 B-Cell Repertoires in the Era of Artificial Intelligence
		6.2.2 Deep Generative Models and Large Language Models in Protein Science
		6.2.3 Antibody Sequence Generation through Deep Generative Models
	6.3 Antibody Optimization through Structure-Based Simulations and Machine Learning
		6.3.1 Sampling and Scoring
		6.3.2 Machine Learning in the Context of Protein Sequence Design
		6.3.3 Computational Strategy to Improve Stability of Antibodies
		6.3.4 Computational Strategy to Improve Functionality of Antibodies through Structure-Based Simulations
		6.3.5 Computational Strategy to Improve Functionality of Antibodies through Machine Learning
		6.3.6 Computer-Aided Antibody Repositioning
	6.4 Geometric and Computational Considerations in the Design of Multispecific Biologics
		6.4.1 Antibody Formats in Multispecific Biologics
		6.4.2 Computational Multistate Design of Bispecific IgG Antibodies
	6.5 Conclusions and Perspectives
	Acknowledgments
	References
7. Computational Biophysical Analyses of Antibody Structure-Function Relationships with Emphasis on Therapeutic Antibody-Based Biologics
	7.1 Introduction
	7.2 Computational Resources for Antibody Structure and Function
		7.2.1 Antibody-Related Online Resources and Databases
		7.2.2 Computational Methods for Investigating Structure-Function Relationship
		7.2.3 Computational Approaches to Predict Antibody–Antigen Interaction
		7.2.4 In Silico Prediction of Binding Affinity
		7.2.5 Biophysical Parameters Affecting Antibody Design
		7.2.6 Role of Mutational Scanning in Antibody–Antigen Interaction Prediction
		7.2.7 Language Models for Antibody Structure and Function Prediction
		7.2.8 Role of MD Simulations in Antibody Structure-Function Prediction
	7.3 Conclusion
	Competing Interests
	Acknowledgments
	References
8. Use of Molecular Simulations to Understand Structural Dynamics of Antibodies
	8.1 Why Run Molecular Simulations on Antibodies?
	8.2 Common Types of Molecular Simulations for Biomolecules
		8.2.1 Molecular Dynamics (MD) Simulations
		8.2.2 Monte Carlo (MC) Simulations
		8.2.3 Challenges of Molecular Simulations
	8.3 Modeling Perspective: Why We Cannot Simulate Everything in the Real System
		8.3.1 Periodic Boundary Conditions
		8.3.2 Inclusion versus Exclusion of Constant Domains
		8.3.3 All-Atom versus Coarse-Grain (CG) Simulations
	8.4 Uses of Molecular Simulation in Antibody Drug Development
		8.4.1 Predicting and Understanding Protein-Protein Interactions in mAb Solutions
		8.4.2 Predicting and Understanding Binding Mechanisms, Energetics, and Aggregation
	8.5 Conclusion
	References
9. Considerations of Developability During the Early Stages of Antibody Drug Discovery and Design
	9.1 Introduction
	9.2 Historical Perspective
	9.3 Clinical Antibody Data Set
	9.4 Human B-Cell-Derived Antibodies
	9.5 Control Antibodies
	9.6 Assays Results for Human Antibodies from De Novo Discovery Campaigns
	9.7 Assessment of Chemical Liabilities
	9.8 Conclusions and Future Perspectives
	Acknowledgments
	References
10. In Silico Approaches to Deliver Better Antibodies by Design: The Past, the Present, and the Future
	Abbreviations
	10.1 Introduction
	10.2 The Classical Approach – Design of Specific Sequence-Optimization Variants
	10.3 The Contemporary Approach – Engineered Libraries toward Improved Developability an Alternative
		10.3.1 Design of Specific Hit Optimization Display Libraries in Combination with AI/ML Approaches
		10.3.2 Design of Diverse Hit Identification Libraries
	10.4 The Emerging Approach - De Novo Design of Developable Antibody Therapeutics
		10.4.1 Conclusions and Outlook
	Acknowledgments
	References
11. Use of Systems Biology Approaches toward Target Discovery, Validation, and Drug Development
	11.1 Introduction (Introduction to Systems Biology and Its Scope in Drug Discovery and Development)
	11.2 Experimental Methods for Systems Approach in Biopharmaceutical Drug Discovery and Development
	11.3 Computational Methods for Systems Approach in Biopharmaceutical Drug Discovery and Development
	11.4 Applications of Systems Approaches to Target Identification and Validation in Drug Discovery
	11.5 Application of Systems Biology in Biopharmaceutical Development – Optimizing Growth and Productivity
	11.6 Application of Systems Biology in Biopharmaceutical Development – Controlling Product Quality Attributes
	11.7 Big Data Approach in Biologics Drug Development
	11.8 Conclusions and Future Directions
	References
12. Recent Advances in PK/PD and Quantitative Systems Pharmacology (QSP) Models for Biopharmaceuticals
	12.1 Introduction to PK/PD and QSP Modeling
		12.1.1 PK/PD Modeling
		12.1.2 QSP Modeling
		12.1.3 Why Are PK/PD Modeling and QSP Modeling Important for Biotherapeutics?
	12.2 PK/PD Characteristics and Considerations for Biotherapeutics
		12.2.1 Monoclonal Antibodies (mAbs)
		12.2.2 Antibody-Drug Conjugates (ADCs)
		12.2.3 Cell Therapies
		12.2.4 Gene Therapies
		12.2.5 Vaccines
		12.2.6 mRNA/siRNA/Oligonucleotide Therapeutics
	12.3 Use of M&S Approaches in the Discovery and Development of Biotherapeutics and Novel Modalities
	12.4 Case Studies
		12.4.1 Application of Mechanistic PK/PD Models to Inform Early Drug Discovery Decisions for Biotherapeutics
		12.4.2 QSP Modeling of ADCs for Preclinical to Clinical Translation and Optimization of Doses for Different Oncology Indications
		12.4.3 A Translational Platform PBPK Model for Antibody Disposition in the Brain
		12.4.4 Empirical Model-Based Cellular Kinetic Analysis of CAR-Ts in Clinical Studies, Investigation of Dose-Exposure-Response Relationship, and Covariate Modeling
		12.4.5 Mechanistic, Multiscale PK/PD and PBPK Modeling for In Vitro to In Vivo Correlation (IVIVC) and Preclinical to Clinical Translation for CAR-T Therapy
		12.4.6 QSP Model for Preclinical to Clinical Translation of CD3 Bispecific Antibodies
		12.4.7 QSP Model for mRNA Therapeutic Lipid Nanoparticle for Preclinical to Clinical Translation
		12.4.8 QSP Model to Gather Mechanistic Insights for Gene Delivery in Sickle Cell Disease
	12.5 Conclusions and Future Perspectives
	References
13.The Artificial Intelligence Revolution: Transforming the Design and Optimization of Multispecific Antibodies
	13.1 Introduction
	13.2 AI/ML: A Game Changer for Antibody Design
	13.3 Multispecific Antibody Design
	13.4 Adapting AI to the Design of Multispecific Antibodies
		13.4.1 Structure Prediction and Modeling
		13.4.2 Developability Prediction and Optimization
		13.4.3 Virtual Screening and Lead Identification
		13.4.4 In Silico Modeling and Simulation
	13.5 The Future: Beyond Optimization
		13.5.1 Market Trends and Commercialization
		13.5.2 Logic Gates, Biosensors, and De Novo Design
		13.5.3 Challenges and Opportunities
	13.6 Conclusion
	Acknowledgments
	References
Index