
Cheminformatics, QSAR and Machine Learning Applications for Novel Drug Development
- 1st Edition - May 23, 2023
- Imprint: Academic Press
- Editor: Kunal Roy
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 1 8 6 3 8 - 7
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 1 8 6 3 9 - 4
Cheminformatics, QSAR and Machine Learning Applications for Novel Drug Development aims at showcasing different structure-based, ligand-based, and machine learning tools currently… Read more

Purchase options

Institutional subscription on ScienceDirect
Request a sales quoteCheminformatics, QSAR and Machine Learning Applications for Novel Drug Development aims at showcasing different structure-based, ligand-based, and machine learning tools currently used in drug design. It also highlights special topics of computational drug design together with the available tools and databases. The integrated presentation of chemometrics, cheminformatics, and machine learning methods under is one of the strengths of the book.
The first part of the content is devoted to establishing the foundations of the area. Here recent trends in computational modeling of drugs are presented. Other topics present in this part include QSAR in medicinal chemistry, structure-based methods, chemoinformatics and chemometric approaches, and machine learning methods in drug design. The second part focuses on methods and case studies including molecular descriptors, molecular similarity, structure-based based screening, homology modeling in protein structure predictions, molecular docking, stability of drug receptor interactions, deep learning and support vector machine in drug design. The third part of the book is dedicated to special topics, including dedicated chapters on topics ranging from de design of green pharmaceuticals to computational toxicology. The final part is dedicated to present the available tools and databases, including QSAR databases, free tools and databases in ligand and structure-based drug design, and machine learning resources for drug design. The final chapters discuss different web servers used for identification of various drug candidates.
- Presents chemometrics, cheminformatics and machine learning methods under a single reference
- Showcases the different structure-based, ligand-based and machine learning tools currently used in drug design
- Highlights special topics of computational drug design and available tools and databases
- Cover image
- Title page
- Table of Contents
- Copyright
- Dedication
- Contributors
- Preface
- Section 1: Introduction
- Chapter 1: Quantitative structure-activity relationships (QSARs) in medicinal chemistry
- Abstract
- Acknowledgment
- 1: Introduction
- 2: QSAR: Background and its brief history
- 3: Chemical information and descriptors
- 4: The standard algorithm of QSAR modeling
- 5: Application of QSAR modeling in a real-world scenario: A case study example
- 6: Various challenges in QSAR modeling
- 7: Combinatorial library design for QSAR analysis
- 8: A few examples of successful application of QSAR in drug and pesticide design
- 9: Future avenues with concluding remarks
- References
- Chapter 2: Computer-aided drug design: An overview
- Abstract
- 1: Introduction
- 2: Brief history
- 3: Databases used in drug discovery
- 4: Benchmarking techniques of computational tools in drug design and discovery
- 5: Scoring functions for evaluating protein-ligand complexes
- 6: Polypharmacology
- 7: Drug repositioning
- 8: Applications of computational tools in drug discovery
- 9: Summary
- References
- Chapter 3: Structure-based virtual screening in drug discovery
- Abstract
- Acknowledgments
- 1: Introduction
- 2: Structure-based virtual screening
- 3: Source of target structures
- 4: Source of the ligand structures
- 5: Software resources for SBVS
- 6: The process of structure-based virtual screening
- 7: Preparation of the ligand structures
- 8: Docking in structure-based virtual screening
- 9: Types of docking
- 10: The docking process
- 11: Software for docking
- 12: Assessment of the docking by using scoring function
- 13: Validation of the docking procedure
- 14: Concluding remarks
- References
- Chapter 4: The impact of artificial intelligence methods on drug design
- Abstract
- 1: Introduction
- 2: The drug discovery process
- 3: From data to models
- 4: Bio-inspired learning systems
- 5: Symbolic and probabilistic AI methods
- 6: AI methods in drug development
- 7: Discussion and limitations
- 8: Conclusions
- References
- Section 2: Methods and case studies
- Chapter 5: Graph machine learning in drug discovery
- Abstract
- Acknowledgments
- 1: Introduction
- 2: Primer to graph machine learning
- 3: Applications of GNNs in drug discovery
- 4: Conclusion
- References
- Chapter 6: Support vector machine in drug design
- Abstract
- Acknowledgment
- 1: Introduction
- 2: An intuitive description of SVM
- 3: SVM in drug design: Recent examples
- 4: Summary and outlook
- References
- Chapter 7: Understanding protein-ligand interactions using state-of-the-art computer simulation methods
- Abstract
- 1: Introduction
- 2: Binding thermodynamics and methods to compute binding energy
- 3: Enhanced sampling methods to study ligand binding kinetics
- 4: State-of-the-art machine learning models
- 5: Datasets
- 6: Feature extraction
- 7: Modeling approaches
- 8: Binding affinity prediction
- 9: Binding site prediction
- 10: Miscellaneous
- References
- Chapter 8: Structure-based methods in drug design
- Abstract
- Acknowledgments
- 1: Introduction
- 2: Structure-based drug design methodologies
- 3: Case studies for some FDA approved drugs
- 4: Conclusions
- References
- Chapter 9: Structure-based virtual screening
- Abstract
- Acknowledgments
- 1: Introduction
- 2: 3D protein structure prediction
- 3: Importance of target-template modeling
- 4: Protein-protein interactions network analysis
- 5: Fragment-based de novo design
- 6: Drug target selection
- 7: Molecular docking and scoring functions
- 8: Molecular dynamics simulation
- 9: Structure-based pharmacophore modeling
- 10: ML-based scoring functions
- 11: Compound databases
- 12: Virtual screening
- 13: Recent trends from receptor-based virtual screening
- 14: Limitations of SBVS
- 15: Conclusions
- References
- Chapter 10: Deep learning for novel drug development
- Abstract
- Acknowledgments
- 1: Introduction
- 2: From shallow to deep neural nets
- 3: Specific neural network architectures
- 4: Further topics in deep learning for drug development
- 5: Cases studies
- 6: Discussion: Future prospects and challenges
- References
- Chapter 11: Computational methods in the analysis of viral-host interactions
- Abstract
- 1: Introduction
- 2: Experimental approaches for virus-host interaction analysis
- 3: Computational analysis of virus-host interactions
- 4: Conclusions
- References
- Chapter 12: Chemical space and molecular descriptors for QSAR studies
- Abstract
- 1: Introduction
- 2: Molecular descriptors in the current epistemological framework
- 3: Which characteristics molecular descriptors should have
- 4: Classification of molecular descriptors
- 5: Conclusions and new trends in molecular descriptors
- References
- Chapter 13: Machine learning methods in drug design
- Abstract
- 1: Introduction
- 2: Classification of machine learning algorithms
- 3: Machine learning techniques in drug discovery
- 4: Overview and conclusions
- References
- Chapter 14: Deep learning methodologies in drug design
- Abstract
- 1: Introduction
- 2: Molecular representation for deep learning
- 3: Predictive deep learning models
- 4: Deep learning frameworks for generating novel molecules
- 5: Deep learning frameworks for the de novo design of drugs with desired properties
- 6: Open source libraries for de novo drug design
- 7: Conclusion and future perspectives
- References
- Chapter 15: Molecular dynamics in predicting the stability of drug-receptor interactions
- Abstract
- Acknowledgments
- 1: Introduction
- 2: Theoretical background
- 3: Free energy calculations
- 4: Enhanced sampling methods for free energy calculations
- 5: Rapid/approximate methods for free energy calculation: Representation of solvent
- 6: Applications of PBSA/GBSA methods to determine the binding energetics of a ligand to its biomolecular target (receptor)
- 7: Combined quantum mechanical/molecular mechanical methods
- 8: Why molecular dynamics?
- 9: Some success stories of MD-based computer-aided drug discovery
- 10: Conclusion
- References
- Section 3: Special topics
- Chapter 16: Toward models for bioaccumulation suitable for the pharmaceutical domain
- Abstract
- 1: The biology of bioaccumulation
- 2: Empirical models to predict bioaccumulation
- 3: Active pharmaceutical ingredients data
- 4: The performance of existing models on pharma data and their AD
- 5: Toward a better qualification of model applicability domain: What really matters?
- 6: Covariate selection in the prediction of pharma bioaccumulation
- 7: A biological interpretation of our empirical results
- 8: Future developments
- 9: Conclusions
- References
- Chapter 17: Machine learning as a modeling approach for the account of nonlinear information in MIA-QSAR applications: A case study with SVM applied to antimalarial (aza)aurones
- Abstract
- 1: Rationale
- 2: Expected results and deliverables
- 3: Workflow
- 4: Results
- 5: Learning and knowledge outcomes
- References
- Chapter 18: Deep learning using molecular image of chemical structure
- Abstract
- 1: Introduction
- 2: Development
- 3: Quantitative structure-activity relationship as in silico approach
- 4: Deep learning
- 5: Image classification in deep learning
- 6: Deep learning-based QSAR
- 7: Parameter optimization in deep learning
- 8: Visualization of feature values extracted by deep learning
- 9: Concluding remarks
- References
- Chapter 19: Recent advances in deep learning enabled approaches for identification of molecules of therapeutics relevance
- Abstract
- Acknowledgments
- 1: Introduction
- 2: Deep learning
- 3: Current trends
- 4: Concluding remarks
- References
- Chapter 20: Computational toxicology of pharmaceuticals
- Abstract
- Authors’ contribution
- 1: Introduction
- 2: Development
- 3: Concluding remarks
- References
- Chapter 21: Ecotoxicological QSAR modeling and fate estimation of pharmaceuticals
- Abstract
- Author contributions
- 1: Introduction
- 2: QSAR/QSTR models for APIs
- 3: Interspecies quantitative structure-toxicity-toxicity relationship
- 4: QSAR models on mixture toxicity
- 5: QSAR models for environmentally-related fate parameters of pharmaceuticals
- 6: QSAR studies in the removal of pharmaceuticals
- 7: Conclusion
- References
- Chapter 22: Computational modeling of drugs for neglected diseases
- Abstract
- 1: Introduction
- 2: Parasitic neglected diseases
- 3: Viral neglected diseases
- 4: Bacterial neglected diseases
- 5: Conclusions
- References
- Chapter 23: Modeling ADMET properties based on biomimetic chromatographic data
- Abstract
- 1: Introduction
- 2: Biomimetic chromatography
- 3: The use of biomimetic chromatography in modeling ADMET properties
- 4: Conclusions
- References
- Chapter 24: A systematic chemoinformatic analysis of chemical space, scaffolds and antimicrobial activity of LpxC inhibitors
- Abstract
- Acknowledgment
- 1: Introduction
- 2: Development
- 3: Results and discussion
- 4: Conclusion and future perspective
- References
- Section 4: Tools and databases
- Chapter 25: Tools and software for computer-aided drug design and discovery
- Abstract
- Acknowledgments
- Declaration of competing interest
- Funding
- 1: Drug discovery and computer-aided drug design
- 2: Role of tools and software in CADD
- 3: Types of tools and software in CADD
- 4: Overview and conclusion
- References
- Chapter 26: Machine learning resources for drug design
- Abstract
- 1: Introduction
- 2: Machine learning for de novo design
- 3: Machine learning for drug target prediction
- 4: Machine learning for retrosynthesis
- 5: Machine learning for predictive toxicology
- 6: Machine learning for virtual screening
- 7: Machine learning in drug design: Case studies
- 8: Concluding remarks
- References
- Chapter 27: Building bioinformatics web applications with Streamlit
- Abstract
- 1: Introduction
- 2: Benefits of building web applications for drug discovery
- 3: Challenges in building web applications
- 4: Streamlit web development framework
- 5: Extending Streamlit functionality with components
- 6: Bioinformatics web app built with Streamlit
- 7: Thought process of building Streamlit apps and components
- 8: Conclusions
- References
- Chapter 28: Free tools and databases in ligand and structure-based drug design
- Abstract
- Acknowledgments
- 1: Introduction
- 2: Types of CADD: Structure-based drug design and ligand-based drug design
- 3: Concluding remarks
- References
- Index
- Edition: 1
- Published: May 23, 2023
- Imprint: Academic Press
- No. of pages: 768
- Language: English
- Paperback ISBN: 9780443186387
- eBook ISBN: 9780443186394
KR