Добавил:
Sekretar
kiopkiopkiop18@yandex.ru
t.me/Prokururor I Вовсе не секретарь, но почту проверяю
Опубликованный материал нарушает ваши авторские права? Сообщите нам.
Вуз:
Предмет:
Файл:Ординатура / Хирургия / Библиотека им академика М.И. Перельмана / Книга_5387_Библиотеки_им_академика_М_И_Перельмана.pdf
Biopharmaceutical Informatics
Despite the phenomenal clinical success of antibody‑based biopharmaceuticals in recent
years, discovery and development of these novel biomedicines remains a costly, time‑
consuming, and risky endeavor with low probability of success. To bring better biomed‑
icines to patients faster, we have come up with a strategic vision of Biopharmaceutical
Informatics which calls for syncretic use of computation and experiment at all stages of
biologic drug discovery and pre‑clinical development cycles to improve probability of
successful clinical outcomes. Biopharmaceutical Informatics also encourages industry
and academic scientists supporting various aspects of biotherapeutic drug discovery
and development cycles to learn from our collective experiences of successes and, more
importantly, failures. The insights gained from such learnings shall help us improve the
rate of successful translation of drug discoveries into drug products available to clini‑
cians and patients, reduce costs, and increase the speed of biologic drug discovery and
development. Hopefully, the efciencies gained from implementing such insights shall
make novel biomedicines more affordable for patients.
This unique volume describes ways to invent and commercialize biomedicines
more efciently:
• Calls for digital transformation of biopharmaceutical industry by appropri‑
ately collecting, curating, and making available discovery and pre‑clinical
development project data using FAIR principles.
• Describes applications of articial intelligence and machine learning (AIML)
in discovery of antibodies in silico (DAbI) starting with antigen design, con‑
structing inherently developable antibody libraries, nding hits, identifying
lead candidates, and optimizing them.
• Details applications of AIML, physics‑based computational design methods,
and other bioinformatics tools in elds such as developability assessments,
formulation and excipient design, analytical and bioprocess development, and
phar macology.
• Presents pharmacokinetics/pharmacodynamics (PK/PD) and Quantitative
Systems Pharmacology (QSP) models for biopharmaceuticals.
• Describes uses of AIML in bispecic and multi‑specic formats.
DrSandeep Kumar has also edited a collection of articles dedicated to this topic which
can be found in the Taylor and Francis journal mAbs.
Biopharmaceutical
Informatics
Learning to Discover Developable
Biotherapeutics
Edited by
Sandeep Kumar and Andrew E. Nixon
Designed cover image: Sandeep Kumar
First edition published 2025
by CRC Press
2385 NW Executive Center Drive, Suite 320, Boca Raton FL 33431
and by CRC Press
4 Park Square, Milton Park, Abingdon, Oxon, OX14 4RN
CRC Press is an imprint of Taylor & Francis Group, LLC
© 2025 selection and editorial matter, Sandeep Kumar and Andrew E. Nixon; individual chapters,
the contributors
Reasonable eorts have been made to publish reliable data and information, but the author and
publisher cannot assume responsibility for the validity of all materials or the consequences of
their use. e authors and publishers have attempted to trace the copyright holders of all material
reproduced in this publication and apologize to copyright holders if permission to publish in this
form has not been obtained. If any copyright material has not been acknowledged please write and
let us know so we may rectify in any future reprint.
Except as permitted under U.S. Copyright Law, no part of this book may be reprinted, reproduced,
transmitted, or utilized in any form by any electronic, mechanical, or other means, now known or
hereafter invented, including photocopying, microlming, and recording, or in any information
storage or retrieval system, without written permission from the publishers.
For permission to photocopy or use material electronically from this work, access www.copyright.
com or contact the Copyright Clearance Center, Inc. (CCC), 222 Rosewood Drive, Danvers, MA
01923, 978‑750‑84 00. For works t hat are not ava ilable on CCC plea se contact mpkbookspermissions@
tandf.co.uk
Trademark notice: Product or corporate names may be trademarks or registered trademarks and a re
used only for identication and explanation without intent to infringe.
ISBN: 978‑1‑032‑29167‑3 (hbk)
ISBN: 978‑1‑032‑29168‑0 (pbk)
IS BN: 9 78‑1‑ 0 0 3 ‑30031‑1 (ebk)
DOI: 10.1201/9781003300311
Typeset in Times
by codeMantra
Dedications
To the cause of globally equitable access to medicines and healthcare
Sandeep Kumar dedicates this book to memories of his mother.
Andrew E. Nixon dedicates this book to his wife and children for their on‑going
support.
Contents
Foreword xiv
Preface xvi
About the Editors xviii
List of Contributors xix
1 Biopharmaceutical Informatics: An Introduction 1
Andrew E. Nixon and Sandeep Kumar
References 9
2 Digital Transformation in the Biopharmaceutical Industry:
Rebuilding the Way We Discover Complex Therapeutics 11
Tonya Frolov, Leonard Wossnig, and Alexander Jung
2.1 Introduction 11
2.2 Current State of Digitalisation in Pre‑clinical R&D 14
2.3 Challenges in Digital Transformation of Pre‑clinical R&D 15
2.3.1 Operational Challenges 15
2.3.2 Cultural Challenges 16
2.3.3 Data Management, Data Analytics, and Integrity Concerns 17
2.3.4 Barriers to Automation Adoption 18
2.4 Core Ingredients for Successful Digital Transformation 19
2.4.1 New Data‑Generation Methods and
Laboratory Automation 19
2.4.2 Cloud Computing 25
2.4.3 Machine Learning and MLOps to Support the Machine
Learning Life Cycle 27
2.4.4 Company Culture That Drives a Data‑Driven Approach 30
2.5 Case Studies of Successful Digital Transformation 31
2.6 Conclusion 34
References 35
3 Computational Protein Design Strategies for Optimization
ofAntigen Generation to Drive Antibody Discovery 40
Trevor Wilkinson
3.1 Introduction 40
3.2 Target Protein (Antigen) Considerations for Antibody Discovery 42
Antigen Generation Strategies 45
3.3
3.4 Computational Methods 46
viii Contents
3.4.1 Impact of AI/ML on Target Protein Expression, Construct
Design, and Protein Production 47
3.4.2 Computational Protein Structure Prediction 48
3.5 Case Study Examples of Antigen Design Strategies to Drive Drug
Discovery and Immunogen Performance 50
3.6 Conclusions: Computational Antigen Design and Future
Developments 52
References 53
4 Bioinformatic Analyses of Antibody Repertoires
and Their Roles in Modern Antibody Drug Discovery 59
Melody Shahsavarian, Thomas Watkins,
Ponraj Prabakaran, Adrian Carr, Maria Wendt, and Yu Qiu
4.1 Introduction 59
4.2 NGS Technologies, Tools, and Data Analysis for Modern Antibody
Discovery 60
4.3 NGS‑Enabled In Vivo Antibody Discovery from Immunized Animals 64
4.4 NGS‑Enabled In Vitro Antibody Discovery from Display Libraries 66
4.5 NGS‑Enabled In Silico Antibody Discovery via Articial
Intelligence Methods 68
4.6 Summary and Future Directions 71
Acknowledgments 71
References 71
5 Applications of Articial Intelligence and Machine Learning
toward Antibody Discovery and Development 77
Anahita Rouyan, Paweł Dudzic, Wiktoria Wilman,
Tadeusz Satława, Sonia Wróbel, and Konrad Krawczyk
5.1 Introduction 77
5.2 Databases 78
5.2.1 Databases in Machine Learning Approaches 79
5.2.2 Database Types 80
5.3 Applications of Machine Learning in Antibody Discovery and
Development 84
5.3.1 Structure Prediction with Deep Learning 84
5.3.2 Antibody‑Binding Prediction by Deep Learning
(Paratope Prediction) 87
5.3.3 Developability 90
5.4 Antibody Generation and Design by Language Models 96
5.4.1 Antibody Representations 97
5.4.2 Representation Learning 98
5.4.3 Language Models 99
5.5 Conclusions and Future Perspectives in AI for Antibody Discovery 103
References 104
Contents ix
6 From Deep Generative Models to Structure‑Based Simulations:
Computational Approaches for Antibody Design 116
Daisuke Kuroda
6.1 Introduction 116
6.2 Antibody Generation through Deep Generative Models 119
6.2.1 B‑Cell Repertoires in the Era of Articial
Intelligence 119
6.2.2 Deep Generative Models and Large Language Models in
Protein Science 122
6.2.3 Antibody Sequence Generation through
Deep Generative Models 122
6.3 Antibody Optimization through Structure‑Based Simulations and
Machine Learning 125
6.3.1 Sampling and Scoring 125
6.3.2 Machine Learning in the Context of Protein
Sequence Design 127
6.3.3 Computational Strategy to Improve Stability of Antibodies 127
6.3.4 Computational Strategy to Improve Functionality of
Antibodies through Structure‑Based Simulations 130
6.3.5 Computational Strategy to Improve Functionality of
Antibodies through Machine Learning 136
6.3.6 Computer‑Aided Antibody Repositioning 141
6.4 Geometric and Computational Considerations in the Design of
Multispecic Biologics 142
6.4.1 Antibody Formats in Multispecic Biologics 142
6.4.2 Computational Multistate Design of
Bispecic IgG Antibodies 144
6.5 Conclusions and Perspectives 145
Acknowledgments 146
References 146
7 Computational Biophysical Analyses of Antibody
Structure‑Function Relationships with Emphasis
on Therapeutic Antibody‑Based Biologics 161
Puneet Rawat, Eva Smorodina, DivyaSharma, R. Prabakaran,
Jack Wade, RahmadAkbar, Amrinder Singh, Sandeep Kumar,
VictorGreiff, and M. Michael Gromiha
7.1 Introduction 161
7.2 Computational Resources for Antibody Structure and Function 165
7.2.1 Antibody‑Related Online Resources and Databases 165
7.2.2 Computational Methods for Investigating
Structure‑Function Relationship 168
7.2.3 Computational Approaches to Predict
Antibody–Antigen Interaction 169
7.2.4 In Silico Prediction of Binding Afnity 171
x Contents
7.2.5 Biophysical Parameters Affecting Antibody Design 180
7.2.6 Role of Mutational Scanning in Antibody–Antigen
Interaction Prediction 182
7.2.7 Language Models for Antibody Structure and Function
Prediction 182
7.2.8 Role of MD Simulations in Antibody Structure-Function
Prediction 184
7.3 Conclusion 185
Competing Interests 185
Acknowledgments 185
References 186
8 Use of Molecular Simulations to Understand Structural
Dynamics of Antibodies 201
Daniel A. Nissley, Matthew I. J. Raybould, Charlotte M. Deane,
and Sandeep Kumar
8.1 Why Run Molecular Simulations on Antibodies? 201
8.2 Common Types of Molecular Simulations for Biomolecules 202
8.2.1 Molecular Dynamics (MD) Simulations 202
8.2.2 Monte Carlo (MC) Simulations 205
8.2.3 Challenges of Molecular Simulations 206
8.3 Modeling Perspective: Why We Cannot Simulate Everything in
the Real System 207
8.3.1 Periodic Boundary Conditions 207
8.3.2 Inclusion versus Exclusion of
Constant Domains 208
8.3.3 All-Atom versus Coarse-Grain (CG)
Simulations 208
8.4 Uses of Molecular Simulation in Antibody Drug Development 210
8.4.1 Predicting and Understanding Protein-Protein
Interactions in mAb Solutions 210
8.4.2 Predicting and Understanding Binding Mechanisms,
Energetics, and Aggregation 216
8.5 Conclusion 221
References 222
9 Considerations of Developability During the Early Stages
of Antibody Drug Discovery and Design 228
Maximiliano Vásquez, Bianka Prinz, Eric Krauland,
and Tushar Jain
9.1 Introduction 228
9.2 Historical Perspective 230
9.3 Clinical Antibody Data Set 232
9.4 Human B-Cell-Derived Antibodies 234
9.5 Control Antibodies 235
Contents xi
9.6 Assays Results for Human Antibodies from
De Novo Discovery Campaigns 237
9.7 Assessment of Chemical Liabilities 241
9.8 Conclusions and Future Perspectives 243
Acknowledgments 246
References 246
10 In Silico Approaches to Deliver Better Antibodies
byDesign:ThePast, the Present, and the Future 252
Andreas Evers, Shipra Malhotra, and Vanita D. Sood
Abbreviations 252
10.1 Introduction 253
10.2 The Classical Approach–Design of Specic
Sequence‑Optimization Variants 256
10.3 The Contemporary Approach–Engineered Libraries toward
Improved Developability an Alternative 264
10.3.1 Design of Specic Hit Optimization Display Libraries in
Combination with AI/ML Approaches 264
10.3.2 Design of Diverse Hit Identication Libraries 267
10.4 The Emerging Approach ‑ De Novo Design of Developable
Antibody Therapeutics 270
10.4.1 Conclusions and Outlook 273
Acknowledgments 274
References 274
11 Use of Systems Biology Approaches toward
Target Discovery, Validation, and Drug Development 281
Madhuresh Sumit and Venkata Gayatri Dhara
11.1 Introduction (Introduction to Systems Biology and Its Scope in
Drug Discovery and Development) 281
11.2 Experimental Methods for Systems Approach in
Biopharmaceutical Drug Discovery and Development 282
11.3 Computational Methods for Systems Approach in
Biopharmaceutical Drug Discovery and Development 285
11.4 Applications of Systems Approaches to Target Identication
and Validation in Drug Discovery 287
11.5 Application of Systems Biology in Biopharmaceutical
Development–Optimizing Growth and Productivity 292
11.6 Application of Systems Biology in Biopharmaceutical
Development–Controlling Product Quality Attributes 296
11.7 Big Data Approach in Biologics Drug Development 298
11.8 Conclusions and Future Directions 299
References 300