Predictive Modeling of Drug Sensitivity

Chapter 1: Introduction

• Abstract
• 1.1 Cancer Statistics
• 1.2 Promise of Targeted Therapies
• 1.3 Market Trends
• 1.4 Roadblocks to Success
• 1.5 Overview of Research Directions

Chapter 2: Data characterization

• Abstract
• 2.1 Introduction
• 2.2 Review of Molecular Biology
• 2.3 Genomic Characterizations
• 2.4 Pharmacology
• 2.5 Functional Characterizations

Chapter 3: Feature selection and extraction from heterogeneous genomic characterizations

• Abstract
• 3.1 Introduction
• 3.2 Data-Driven Feature Selection
• 3.3 Data-Driven Feature Extraction
• 3.4 Multiomics Feature Extraction and Selection

Chapter 4: Validation methodologies

• Abstract
• 4.1 Introduction
• 4.2 Fitness Measures
• 4.3 Sample Selection Techniques for Accuracy Estimation
• 4.4 Small Sample Issues
• 4.5 Experimental Validation Techniques

Chapter 5: Tumor growth models

• Abstract
• 5.1 Introduction
• 5.2 Exponential Linear Models
• 5.3 Logistic and Gompertz Models
• 5.4 Power Law Models
• 5.5 Stochastic Tumor Growth Models
• 5.6 Modeling Tumor Spheroid Growth
• 5.7 Discussion

Chapter 6: Overview of predictive modeling based on genomic characterizations

• Abstract
• 6.1 Introduction
• 6.2 Predictive Modeling Techniques
• 6.3 Applications

Chapter 7: Predictive modeling based on random forests

• Abstract
• 7.1 Introduction
• 7.2 Random Forest Regression
• 7.3 Combining Models Trained on Different Genomic Characterizations
• 7.4 Probabilistic Random Forests

Chapter 8: Predictive modeling based on multivariate random forests

• Abstract
• 8.1 Introduction
• 8.2 MRF Based on Covariance Approach
• 8.3 MRF Based on Copula

Chapter 9: Predictive modeling based on functional and genomic characterizations

• Abstract
• 9.1 Introduction
• 9.2 Mathematical Formulation
• 9.3 Data Preprocessing: Drug Target and Output Sensitivity Normalization
• 9.4 Model Generation
• 9.5 Generate Tumor Proliferation Circuit
• 9.6 Model Refinement
• 9.7 Prediction Error Analysis
• 9.8 Application Results
• 9.9 Discussion

Chapter 10: Inference of dynamic biological networks based on perturbation data

• Abstract
• 10.1 Introduction
• 10.2 Discrete Deterministic Dynamic Model Inference
• 10.3 Discrete Stochastic Dynamic Model Inference
• 10.4 Discussion

Chapter 11: Combination therapeutics

• Abstract
• 11.1 Introduction
• 11.2 Analyzing Drug Combinations
• 11.3 Model-Based Combination Therapy Design
• 11.4 Model-Free Combination Therapy Design

Chapter 12: Online resources

• Abstract
• 12.1 Pathway Databases
• 12.2 Drug-Protein Interaction and Protein Structure Databases
• 12.3 Drug Sensitivity, Genetic Characterization, and Functional Databases
• 12.4 Drug Toxicity
• 12.5 Missing Value Estimation
• 12.6 Regression Tools
• 12.7 Target Inhibition Maps
• 12.8 Estimating Drug Combination Synergy
• 12.9 Survival Analysis
• 12.10 Prediction Challenges
• 12.11 Regulatory Information

Chapter 13: Challenges

• Abstract
• 13.1 Impediments to the Design of Predictive Models for Personalized Medicine
• 13.2 Tumor Heterogeneity
• 13.3 Data Inconsistencies
• 13.4 Prediction Accuracy Limitations
• 13.5 Toxicity of Combination Therapeutics
• 13.6 Collaborative Constraints
• 13.7 Ethical Considerations