
As an Amazon Associate and affiliate partner, Menrva Books earns from qualifying purchases. Learn more
The emerging biotechnologies have significantly advanced the study of biological mechanisms. However, biological data usually contain a great amount of missing information, e.g. missing features, missing labels or missing samples, which greatly limits the extensive usage of the data. In this book, we introduce different types of biological data missing scenarios and propose machine learning models to improve the data analysis, including deep recurrent neural network recovery for feature missings, robust information theoretic learning for label missings and structure-aware rebalancing for minor sample missings. Models in the book cover the fields of imbalance learning, deep learning, recurrent neural network and statistical inference, providing a wide range of references of the integration between artificial intelligence and biology. With simulated and biological datasets, we apply approaches to a variety of biological tasks, including single-cell characterization, genome-wide association studies, medical image segmentations, and quantify the performances in a number of successful metrics. The outline of this book is as follows. In Chapter 2, we introduce the statistical recovery of missing data features; in Chapter 3, we introduce the statistical recovery of missing labels; in Chapter 4, we introduce the statistical recovery of missing data sample information; finally, in Chapter 5, we summarize the full text and outlook future directions. This book can be used as references for researchers in computational biology, bioinformatics and biostatistics. Readers are expected to have basic knowledge of statistics and machine learning.
This book addresses the critical challenge of incomplete data in biological research by proposing advanced machine learning models for its reconstruction. The author, Feng Bao, introduces various missing data scenarios in biological datasets and presents novel machine learning approaches, including deep recurrent neural networks for feature imputation, information-theoretic learning for label recovery, and structure-aware rebalancing for sample imputation. The book details applications across diverse biological tasks such as single-cell characterization, genome-wide association studies, and medical image segmentation, demonstrating the integration of artificial intelligence with biological sciences.
The book is positioned as a reference for researchers in computational biology, bioinformatics, and biostatistics, assuming a foundational understanding of statistics and machine learning. Its structure, progressing from feature, label, to sample missing data recovery, suggests a systematic approach to tackling data incompleteness. The inclusion of both simulated and biological datasets indicates a practical, evidence-based methodology. The work aims to provide a comprehensive overview of integrating artificial intelligence with biological research to overcome data limitations.
Page Count:
105
Publication Date:
2021-08-08
Publisher:
Springer Nature Singapore
ISBN-10:
9811630631
ISBN-13:
9789811630637