Multivariate Biomarker Discovery: Data Science Methods for Efficient Analysis of High-Dimensional Biomedical Data

by Darius M. Dziuda

Overview

Multivariate biomarker discovery is increasingly important in the realm of biomedical research, and is poised to become a crucial facet of personalized medicine. This will prompt the demand for a myriad of novel biomarkers representing distinct 'omic' biosignatures, allowing selection and tailoring treatments to the various individual characteristics of a particular patient. This concise and self-contained book covers all aspects of predictive modeling for biomarker discovery based on high-dimensional data, as well as modern data science methods for identification of parsimonious and robust multivariate biomarkers for medical diagnosis, prognosis, and personalized medicine. It provides a detailed description of state-of-the-art methods for parallel multivariate feature selection and supervised learning algorithms for regression and classification, as well as methods for proper validation of multivariate biomarkers and predictive models implementing them. This is an invaluable resource for scientists and students interested in bioinformatics, data science, and related areas.

Product Details

ISBN-13:	9781316518700
Publisher:	Cambridge University Press
Publication date:	06/06/2024
Pages:	294
Product dimensions:	6.97(w) x 9.84(h) x 0.87(d)

About the Author

Darius M. Dziuda, Ph.D., is Professor of Data Science and Bioinformatics at Central Connecticut State University (CCSU), with both academic and biotechnology industry experience. His research focuses on multivariate biomarker discovery for medical diagnosis, prognosis, and personalized medicine. Dr. Dziuda is also designing and teaching courses for two specializations of CCSU's graduate data science program: Bioinformatics and Advanced Data Science Methods.

Table of Contents

Preface; Acknowledgments; Part I. Framework for Multivariate Biomarker Discovery: 1. Introduction; 2. Multivariate analytics based on high-dimensional data: concepts and misconceptions; 3. Predictive modeling for biomarker discovery; 4. Evaluation of predictive models; 5. Multivariate feature selection; Part II. Regression Methods for Estimation: 6. Basic regression methods; 7. Regularized regression methods; 8. Regression with random forests; 9. Support vector regression; Part III. Classification Methods: 10. Classification with random forests; 11. Classification with support vector machines; 12. Discriminant analysis; 13. Neural networks and deep learning; Part IV. Biomarker Discovery via Multistage Signal Enhancement and Identification of Essential Patterns: 14. Multistage signal enhancement; 15. Essential patterns, essential variables, and interpretable biomarkers; Part V. Multivariate Biomarker Discovery Studies: 16. Biomarker discovery study 1: searching for essential gene expression patterns and multivariate biomarkers that are common for multiple types of cancer; 17. Biomarker discovery study 2: multivariate biomarkers for liver cancer; References; Index.

Editorial Reviews

‘I consider this book required reading for anyone involved in biomarker discovery. It is equally relevant for newcomers to and experts in the field. It provides all the foundations explained in a succinct and easy to understand way, while being precise and detailed on the respective methods. I particularly like that the book is easy to read and factual in its assessment of the methods discussed. The book provides a perfect guide to multivariate statistics and will help the reader to avoid pitfalls.’

From the Publisher