Predictive Modeling of Drug Sensitivity

Predictive 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 problemsCovers all aspects of drug sensitivity modeling, starting from initial data generation to final experimental validationIncludes the latest results on drug sensitivity modeling that is based on updated research findingsProvides information on existing data and software resources for applying the mathematical and computational tools available

1: Introduction 2: Data characterization 3: Feature selection and extraction from heterogeneous genomic characterizations 4: Validation methodologies 5: Tumor growth models 6: Overview of predictive modeling based on genomic characterizations 7: Predictive modeling based on random forests 8: Predictive modeling based on multivariate random forests 9: Predictive modeling based on functional and genomic characterizations 10: Inference of dynamic biological networks based on perturbation data 11: Combination therapeutics 12: Online resources 13: Challenges