Revolutionizing Drug Development : Harnessing AI and Computational Biology.

Format:

Book

Author/Creator:

Chen, Jen-Tsung.

Contributor:

Chen, Jen-Tsung

Language:

English

Subjects (All):

Artificial intelligence.

Computational biology.

Physical Description:

1 online resource (356 pages)

Edition:

1st ed.

Place of Publication:

Chantilly : Elsevier Science & Technology, 2026.

Summary:

Revolutionizing Drug Development: Harnessing AI and Computational Biology presents cutting-edge artificial intelligence (AI) tools, such as machine- and deep-learning models and generative AI, to assist structure-based drug design and clinical trial design and integrate with drug development programs.

Contents:

Front Cover

Revolutionizing Drug Development

Copyright

Contents

List of contributors

Preface

1 Artificial intelligence and accelerated computing in drug discovery: an updated overview

1.1 Introduction

1.2 Chemical optimization

1.3 Traditional methods versus AI-driven lead optimization

1.4 Structure-predicting algorithms

1.5 Key future optimization strategies

1.6 In silico

1.7 AI-driven lead compound discovery and optimization: illuminating case studies

1.7.1 Case study 1

1.7.2 Case study 2

1.7.3 Case study 3

1.8 Conclusions

References

2 AI strategies for drug discovery and bioactivity prediction: opportunities and challenges

2.1 Introduction to AI in drug discovery

2.2 AI techniques for compound screening

2.2.1 Machine learning algorithms for compound screening

2.2.1.1 Random forest

2.2.1.2 Support vector machines

2.2.1.3 Neural networks

2.2.1.4 Gradient boosting machines

2.2.2 Deep-learning approaches for virtual screening

2.2.2.1 Convolutional neural networks

2.2.2.2 Graph neural networks

2.2.2.3 Recurrent neural networks

2.2.2.4 Attention mechanisms

2.2.2.5 Autoencoders

2.2.2.6 Generative models

2.3 Molecular docking and drug design

2.3.1 De novo drug design

2.3.2 AI's role in the virtual complexes explorations

2.4 Predictive modeling of bioactivity

2.4.1 Supervised learning for bioactivity prediction

2.4.2 Quantitative structure-activity relationship models

2.5 Challenges and ethical considerations

2.5.1 Lack of data accuracy and bias matter for automation

2.5.2 Interpretability and explainability of AI models

2.5.3 The ethical dilemma of AI-based drug discoveries

2.6 Future perspectives

2.6.1 AI-R&amp

D forerunning trends in new drug discovery

2.6.2 Future implications for the drug industry.

2.7 Summary

3 AI technologies for drug repurposing: methods and applications

3.1 Introduction

3.2 AI techniques in drug repurposing

3.2.1 Machine learning approaches

3.2.2 Deep learning techniques

3.2.3 Natural language processing

3.2.4 Quantitative structure-activity relationship modeling and molecular docking

3.3 Data sources and integration

3.3.1 Public databases and repositories

3.3.1.1 DrugBank

3.3.1.2 PubChem

3.3.1.3 ChEMBL

3.3.1.4 The Cancer Genome Atlas database

3.3.1.5 Gene Expression Omnibus database

3.3.2 Integration of multiomics data

3.3.3 Data preprocessing and cleaning

3.4 Applications and case studies

3.4.1 Successful drug repurposing cases

3.4.1.1 Thalidomide for multiple myeloma (MM)

3.4.1.2 Sildenafil for pulmonary hypertension

3.4.1.3 Metformin for cancer

3.4.2 AI-driven drug repurposing platforms

3.4.3 AI-driven clinical trial design and dose optimization

3.5 Challenges and limitations

3.5.1 Data quality and availability

3.5.2 Algorithmic and computational challenges

3.5.3 Ethical and regulatory considerations

3.6 Future directions and opportunities

3.6.1 Emerging AI technologies for drug repurposing

3.6.2 Collaborative research and open science

3.6.3 Personalized medicine and precision healthcare

3.7 Conclusion

AI disclosure

4 Data science and databases in drug discovery: technical development and applications

4.1 Introduction

4.2 Drug discovery process overview

4.2.1 Target identification and validation

4.2.2 Hit identification and lead optimization

4.2.3 Preclinical development

4.2.4 Clinical development

4.2.5 Postmarketing surveillance

4.3 The role of data science in drug discovery

4.3.1 Data science methods and tools in drug discovery.

4.3.2 Predictive models in drug discovery

4.3.2.1 Quantitative structure-activity relationship modeling

4.3.2.2 Molecular docking

4.3.2.3 Network pharmacology and systems biology

4.3.2.4 Adverse event prediction and drug toxicity modeling

4.4 Databases in drug discovery

4.4.1 Biological and chemical databases

4.4.2 Integrative platforms and data repositories

4.4.3 The role of databases in drug discovery

4.4.3.1 Virtual screening

4.4.3.2 Target identification and validation

4.4.3.3 Lead optimization

4.4.3.4 Drug repurposing

4.4.3.5 Biomarker discovery

4.4.4 Data integration and challenges

4.4.4.1 Data heterogeneity

4.4.4.2 Data completeness

4.4.4.3 Privacy concerns

4.4.4.4 Reproducibility and transparency

4.5 Technical developments in data science and databases in drug discovery

4.5.1 Advancements in machine learning and AI

4.5.1.1 Deep learning and neural networks

4.5.1.2 Reinforcement learning in drug design

4.5.1.3 Natural language processing

4.5.2 Cloud computing and big data infrastructure

4.5.2.1 Scalability for high-throughput data analysis

4.5.2.2 Data integration across platforms

4.5.3 Advances in databases and data repositories

4.5.3.1 Graph databases and network pharmacology

4.5.3.2 Advances in open-access databases

4.5.3.3 Federated data and secure sharing

4.5.4 Computational drug design and simulation

4.5.4.1 Molecular docking and dynamics simulations

4.5.4.2 Artificial intelligence in simulation

4.6 Applications of data science and databases in drug discovery

4.6.1 Drug-target identification and validation

4.6.2 High-throughput screening and virtual screening

4.6.3 Chemoinformatics and quantitative structure-activity relationship modeling

4.6.4 Drug repurposing

4.6.5 Biomarker discovery and patient stratification.

4.7 Challenges and ethical considerations for data science and databases in drug discovery

4.7.1 Data quality and integrity

4.7.2 Data privacy and security

4.7.3 Bias in data and algorithms

4.7.4 Reproducibility and transparency

4.7.5 Regulatory and legal challenges

4.8 Benefits and challenges of applying data science in drug discovery

4.9 Conclusion

5 Graph neural networks for drug discovery: protocols and applications

5.1 Introduction

5.2 Theoretical framework of graph neural networks

5.2.1 Graph structure

5.2.2 Message passing and information aggregation

5.2.2.1 Message generation and aggregation

5.2.2.2 Incorporating self-information

5.2.2.3 Update function

5.2.3 Incorporating edge features and multirelational graphs

5.2.3.1 Relational graph neural networks

5.2.3.2 Incorporating edge attributes

5.2.4 Pooling and readout

5.2.4.1 Pooling

5.2.4.2 Readout

5.2.5 Challenges in training graph neural networks

5.2.6 Optimization and training strategies

5.2.7 Graph pooling techniques

5.3 Classification of graph neural networks

5.3.1 Graph convolutional networks

5.3.2 Recurrent graph neural networks

5.3.3 Graph attention networks

5.3.4 Graph autoencoders

5.3.5 Graph generative networks

5.3.6 Spatio-temporal graph neural networks

5.4 Graph neural network applications in drug discovery

5.4.1 Drug-target prediction

5.4.2 Drug molecule design

5.4.2.1 Graph neural networks for molecular generation

5.4.2.2 Graph neural networks for molecular docking

5.4.2.3 Graph neural networks for molecular property prediction

5.4.3 Advantages of graph neural networks in drug discovery

5.4.4 Challenges and future directions

5.5 Conclusion

Acknowledgments

References.

6 Deep learning and generative models for drug discovery: techniques and current achievements

6.1 Introduction

6.2 Molecular representation

6.2.1 Line notation

6.2.1.1 International chemical identifier

6.2.1.2 Simplified molecular input line entry system

6.2.1.3 Self-referencing embedded strings

6.2.2 Molecular descriptors

6.2.2.1 Traditional molecular descriptors

6.2.2.2 Tomocomd-CARDD

6.2.2.3 Radial distribution function descriptors

6.2.3 Molecular graph

6.3 Generative AI model

6.3.1 Generative adversarial networks

6.3.2 Variational autoencoders

6.3.3 Large language models

6.3.4 Normalizing flows

6.3.5 Autoregressive models

6.3.6 Diffusion models

6.4 The challenges and the future

6.5 Conclusion

7 Artificial intelligence-enabled personalized medicine: strategies and challenges

7.1 Introduction

7.2 Artificial intelligence applications in personalized medicine

7.3 Disease risk prediction and prevention

7.4 Treatment selection and optimization

7.5 Patient monitoring and outcome prediction

7.6 Drug discovery and development through artificial intelligence

7.6.1 Artificial intelligence's current role in drug development

7.7 Challenges in artificial intelligence-enabled personalized medicine

7.8 Data privacy and security

7.9 Regulatory hurdles and compliance

7.10 Strategies for successful implementation

7.11 Data integration and interoperability

7.12 Artificial intelligence model validation and transparency

7.13 Clinical decision support systems

7.14 Patient engagement and education

7.15 Future directions and opportunities

7.16 Conclusion

8 Artificial intelligence-based technologies for advancing research and development in the pharmaceutical industry: current developments and challenges

8.1 Introduction.

8.2 Artificial intelligence in drug discovery and development.

Notes:

Description based on publisher supplied metadata and other sources.

Part of the metadata in this record was created by AI, based on the text of the resource.

ISBN:

0-443-34060-9

0-443-34059-5

9780443340604

OCLC:

1581081810