Predictive Modeling of Drug Sensitivity
- 1st Edition - November 15, 2016
- Imprint: Academic Press
- Author: Ranadip Pal
- Language: English
- Paperback ISBN:9 7 8 - 0 - 1 2 - 8 0 5 2 7 4 - 7
- eBook ISBN:9 7 8 - 0 - 1 2 - 8 0 5 4 3 1 - 4
Predictive Modeling of Drug Sensitivity gives an overview of drug sensitivity modeling for personalized medicine that includes data characterizations, modeling technique… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quotePredictive Modeling of Drug Sensitivity gives an overview of drug sensitivity modeling for personalized medicine that includes data characterizations, modeling techniques, applications, and research challenges. It covers the major mathematical techniques used for modeling drug sensitivity, and includes the requisite biological knowledge to guide a user to apply the mathematical tools in different biological scenarios.
This book is an ideal reference for computer scientists, engineers, computational biologists, and mathematicians who want to understand and apply multiple approaches and methods to drug sensitivity modeling. The reader will learn a broad range of mathematical and computational techniques applied to the modeling of drug sensitivity, biological concepts, and measurement techniques crucial to drug sensitivity modeling, how to design a combination of drugs under different constraints, and the applications of drug sensitivity prediction methodologies.
- Applies mathematical and computational approaches to biological problems
- Covers all aspects of drug sensitivity modeling, starting from initial data generation to final experimental validation
- Includes the latest results on drug sensitivity modeling that is based on updated research findings
- Provides information on existing data and software resources for applying the mathematical and computational tools available
Computer scientists, engineers, computational biologists, and mathematicians
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
- Edition: 1
- Published: November 15, 2016
- Imprint: Academic Press
- No. of pages: 354
- Language: English
- Paperback ISBN: 9780128052747
- eBook ISBN: 9780128054314
RP
Ranadip Pal
Ranadip Pal is an associate professor in the Electrical and Computer Engineering Department, at the Texas Tech University, USA. His research areas are stochastic modeling and control, genomic signal processing, and computational biology. He is the author of more than 60 peer-reviewed articles including publications in high impact journals such as Nature Medicine and Cancer Cell. He has contributed extensively to robustness analysis of genetic regulatory networks and predictive modeling of drug sensitivity. His research group was a top performer in NCI supported drug sensitivity prediction challenge.
Affiliations and expertise
Texas Tech University, USARead Predictive Modeling of Drug Sensitivity on ScienceDirect