Predictive modeling of drug sensitivity / Ranadip Pal.

Format:

Book

Author/Creator:

Pal, Ranadip, 1980- author.

Contributor:

ebrary, Inc.

Language:

English

Subjects (All):

Drugs--Side effects--Statistical methods.

Drugs.

Drugs--Mathematical models.

Pharmacology--Mathematical models.

Pharmacology.

Drug resistance.

Models, Statistical.

Mathematical models.

Drugs--Side effects.

Statistics.

Medical Subjects:

Models, Statistical.

Physical Description:

1 online resource

polychrome

Place of Publication:

London, United Kingdom : Academic Press, [2017]

System Details:

text file

Summary:

This book 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 The applications of drug sensitivity prediction methodologies Key Features 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 latest results on drug sensitivity modeling based on the latest research findings Provides information on existing data and software resources for applying the mathematical and computational tools available Book jacket.

Contents:

Front Cover; Predictive Modeling of Drug Sensitivity; Copyright; Contents; Preface; Chapter 1: Introduction; 1.1 Cancer Statistics; 1.2 Promise of Targeted Therapies; 1.3 Market Trends; 1.3.1 Biomarker Testing; 1.3.2 Pharmaceutical Solutions; 1.3.3 Value-Driven Outcomes; 1.4 Roadblocks to Success; 1.4.1 Linking Patient-Specific Traits to Efficacious Therapy; 1.4.2 High Costs of Targeted Therapies; 1.4.3 Resistance to Therapies; 1.4.4 Personalized Combination Therapy Clinical Trials; 1.5 Overview of Research Directions; References; Chapter 2: Data characterization; 2.1 Introduction.

2.2 Review of Molecular BiologyTranslation; Mutation; 2.3 Genomic Characterizations; 2.3.1 DNA Level; 2.3.2 Epigenetic Level; 2.3.3 Transcriptomic Level; 2.3.4 Proteome Level; 2.3.5 Metabolome Level; 2.3.6 Missing Value Estimation; 2.4 Pharmacology; 2.4.1 Pharmacokinetics; 2.4.2 Pharmacodynamics; 2.4.2.1 Modeling techniques; Indirect response models; 2.4.3 Software Packages; 2.4.4 Drug Toxicity; 2.5 Functional Characterizations; 2.5.1 Cell Viability Measurements; 2.5.2 Drug Characterizations; References; Chapter 3: Feature selection and extraction from heterogeneous genomic characterizations.

3.1 Introduction3.2 Data-Driven Feature Selection; 3.2.1 Filter Techniques; 3.2.1.1 Relief; Example to illustrate Relief; 3.2.1.2 Relief-F; 3.2.1.3 R-Relief-F; Example to illustrate regression ReliefF; 3.2.2 Wrapper Techniques; 3.2.2.1 Sequential forward search; 3.2.2.2 Sequential floating forward search; Example to illustrate SFFS; 3.3 Data-Driven Feature Extraction; 3.3.1 Principal Component Analysis; Example to illustrate PCA; 3.4 Multiomics Feature Extraction and Selection; 3.4.1 Category 1: Union of Transcriptomic and Proteomic Data.

3.4.2 Category 2: Extraction of Common Functional Context of Transcriptomic and Proteomic Features3.4.3 Category 3: Topological Network-Based Techniques; 3.4.4 Category 4: Missing Value Estimation of Proteomic Data Based on Nonlinear Optimization; 3.4.5 Category 5: Multiple Regression Analysis to Predict Contribution of Sequence Features in mRNA-Protein Correlation; 3.4.6 Category 6: Clustering-Based Techniques; 3.4.7 Category 7: Dynamic Modeling; References; Chapter 4: Validation methodologies; 4.1 Introduction; 4.1.1 Model Evaluation; 4.2 Fitness Measures; Data Representation.

4.2.1 Norm-Based Fitness Measures4.2.2 Correlation Coefficient; 4.2.3 Coefficient of Determination R2; 4.2.4 Akaike Information Criterion; 4.3 Sample Selection Techniques for Accuracy Estimation; 4.3.1 Resubstitution or Training Error; 4.3.2 Hold Out; 4.3.3 K-Fold Cross Validation; 4.3.4 Bootstrap; 4.3.5 Confidence Interval; 4.4 Small Sample Issues; 4.4.1 Simulation Study; 4.4.1.1 NCI-DREAM drug sensitivity dataset; 4.4.1.2 CCLE dataset; 4.4.1.3 Bias correction; 4.5 Experimental Validation Techniques; 4.5.1 In Vitro Cell Lines; 4.5.2 In Vitro Primary Tumor Cultures.

Notes:

Includes index.

Electronic reproduction. Palo Alto, Calif. Available via World Wide Web.

Description based on online resource; title from digital title page (viewed on December 28, 2016).

Other Format:

Print version: Pal, Ranadip. Predictive modeling of drug sensitivity.

ISBN:

9780128054314

012805431X

Publisher Number:

99970107565

Access Restriction:

Restricted for use by site license.