Chapter
Chapter 2 Relational Chemical Databases: Creation, Management, and Usage
Step-by-Step Instructions
Chapter 3 Handling of Markush Structures
Step-by-Step Instructions
Chapter 4 Processing of SMILES, InChI, and Hashed Fingerprints
Step-by-Step Instructions
Chapter 5 Design of Diverse and Focused Compound Libraries
Compound Library Creation
Compound Library Analysis
Normalization of Descriptor Values
Visualizing Descriptor Distributions
Decorrelation and Dimension Reduction
Partitioning and Diverse Subset Calculation
Combinatorial Enumeration of Compounds
Retrosynthetic Approaches to Library Design
Part 3 Data Analysis and Visualization
Chapter 6 Hierarchical Clustering in R
Hierarchical Clustering Using Fingerprints
Hierarchical Clustering Using Descriptors
Visualization of the Data Sets
Alternative Clustering Methods
Chapter 7 Data Visualization and Analysis Using Kohonen Self-Organizing Maps
Part 4 Obtaining and Validation QSAR/QSPR Models
Chapter 8 Descriptors Generation Using the CDK Toolkit and Web Services
Step-by-Step Instructions
Chapter 9 QSPR Models on Fragment Descriptors
Data Split Into Training and Test Sets
Substructure Molecular Fragment (SMF) Descriptors
Forward and Backward Stepwise Variable Selection
Parameters of Internal Model Validation
Applicability Domain (AD) of the Model
Storage and Retrieval Modeling Results
Analysis of Modeling Results
Root-Mean Squared Error (RMSE) Estimation
Analysis of n-Fold Cross-Validation Results
Loading Structure-Data File
Descriptors and Fitting Equation
Model Applicability Domain
n-Fold External Cross-Validation
Saving and Loading of the Consensus Modeling Results
Statistical Parameters of the Consensus Model
Consensus Model Performance as a Function of Individual Models Acceptance Threshold
Building Consensus Model on the Entire Data Set
Loading Selected Models and Choosing their Applicability Domain
Reporting Predicted Values
Analysis of the Fragments Contributions
Chapter 10 Cross-Validation and the Variable Selection Bias
Step-by-Step Instructions
Chapter 11 Classification Models
Step-by-Step Instructions
Chapter 12 Regression Models
Step-by-Step Instructions
Chapter 13 Benchmarking Machine-Learning Methods
Step-by-Step Instructions
Chapter 14 Compound Classification Using the scikit-learn Library
Step-by-Step Instructions
Chapter 15 Bagging and Boosting of Classification Models
Chapter 16 Bagging and Boosting of Regression Models
Step-by-Step Instructions
Chapter 17 Instability of Interpretable Rules
Step-by-Step Instructions
Chapter 18 Random Subspaces and Random Forest
Step-by-Step Instructions
Step-by-Step Instructions
Part 6 3D Pharmacophore Modeling
Chapter 20 3D Pharmacophore Modeling Techniques in Computer-Aided Molecular Design Using LigandScout
Theory: 3D Pharmacophores
Representation of Pharmacophore Models
Hydrogen-Bonding Interactions
Aromatic and Cation‐π Interactions
Manual Pharmacophore Construction
Structure-Based Pharmacophore Models
Ligand-Based Pharmacophore Models
3D Pharmacophore-Based Virtual Screening
3D Pharmacophore Creation
Annotated Database Creation
Virtual Screening-Database Searching
Tutorial: Creating 3D-Pharmacophore Models Using LigandScout
Creating Structure-Based Pharmacophores From a Ligand-Protein Complex
Description: Create a Structure-Based Pharmacophore Model
Create a Shared Feature Pharmacophore Model From Multiple Ligand-Protein Complexes
Description: Create a Shared Feature Pharmacophore and Align it to Ligands
Create Ligand-Based Pharmacophore Models
Description: Ligand-Based Pharmacophore Model Creation
Tutorial: Pharmacophore-Based Virtual Screening Using LigandScout
Virtual Screening, Model Editing, and Viewing Hits in the Target Active Site
Description: Virtual Screening and Pharmacophore Model Editing
Analyzing Screening Results with Respect to the Binding Site
Description: Analyzing Hits in the Active Site Using LigandScout
Parallel Virtual Screening of Multiple Databases Using LigandScout
Virtual Screening in the Screening Perspective of LigandScout
Description: Virtual Screening Using LigandScout
Part 7 The Protein 3D-Structures in Virtual Screening
Chapter 21 The Protein 3D-Structures in Virtual Screening
Description of the Example Case
Thrombin and Blood Coagulation
Active Thrombin and Inactive Prothrombin
Thrombin as a Drug Target
Thrombin Three-Dimensional Structure: The 1OYT PDB File
Overall Description of the Input Data Available on the Editor Website
Exercise 1: Protein Analysis and Preparation
Step 1: Identification of Molecules Described in the 1OYT PDB File
Step 2: Protein Quality Analysis of the Thrombin/Inhibitor PDB Complex Using MOE Geometry Utility
Step 3: Preparation of the Protein for Drug Design Applications
Step 4: Description of the Protein‐Ligand Binding Mode
Step 5: Detection of Protein Cavities
Exercise 2: Retrospective Virtual Screening Using the Pharmacophore Approach
Step 1: Description of the Test Library
Step 2.1: Pharmacophore Design, Overview
Step 2.2: Pharmacophore Design, Flexible Alignment of Three Thrombin Inhibitors
Step 2.3: Pharmacophore Design, Query Generation
Step 3: Pharmacophore Search
Exercise 3: Retrospective Virtual Screening Using the Docking Approach
Step 1: Description of the Test Library
Step 2: Preparation of the Input
Step 3: Re-Docking of the Crystallographic Ligand
Step 4: Virtual Screening of a Database
Part 8 Protein-Ligand Docking
Chapter 22 Protein-Ligand Docking
Description of the Example Case
Description of Input Data Available on the Editor Website
A Quick Start with LeadIT
Re-Docking of Tacrine into AChE
Preparation of AChE From 1ACJ PDB File
Docking of Neutral Tacrine, then of Positively Charged Tacrine
Docking of Positively Charged Tacrine in AChE in Presence of Water
Cross-Docking of Tacrine‐Pyridone and Donepezil Into AChE
Preparation of AChE From 1ACJ PDB File
Cross-Docking of Tacrine-Pyridone Inhibitor and Donepezil in AChE in Presence of Water
Re-Docking of Donepezil in AChE in Presence of Water
Annex: Screen Captures of LeadIT Graphical Interface
Part 9 Pharmacophorical Profiling Using Shape Analysis
Chapter 23 Pharmacophorical Profiling Using Shape Analysis
Description of the Example Case
Description of the Searched Data Set
Other Programs for Shape Comparison
Description of Input Data Available on the Editor Website
Preamble: Practical Considerations
What are ROCS Output Files?
Part 10 Algorithmic Chemoinformatics
Chapter 24 Algorithmic Chemoinformatics
Similarity Searching Using Data Fusion Techniques
Introduction to Virtual Screening
The Three Pillars of Virtual Screening
Search Strategy (Data Fusion)
Fingerprint Representations
Generation of Fingerprints
Completed Virtual Screening Program
Benchmarking VS Performance
Multiple Runs and Reproducibility
Adjusting the VS Program for Benchmarking
Analyzing Benchmark Results
Introduction to Chemoinformatics Toolkits
Basic Usage: Creating and Manipulating Molecules in RDKit
Creation of Molecule Objects
An Example: Hill Notation for Molecules
Canonical SMILES: The Canon Algorithm
Canonicalization of SMILES
Substructure Searching: The Ullmann Algorithm
Atom Environment Fingerprints
The Initial Atom Invariant