Computational biology is an interdisciplinary research that applies approaches and methodologies of information sciences and engineering to address complex pr- lems in biology. With rapid developments in the omics and computer technologies over the past decade, computational biology has been evolving to cover a much wider research domain and applications in order to adequately address challenging problems in systems biology and medicine. This edited book focuses on recent - sues and applications of computational biology in oncology. This book contains 11 chapters that cover diverse advanced computationalmethods applied to oncologyin an attempt to ?nd more effective ways for the diagnosis and cure of cancer. Chapter 1 by Chen and Nguyen addresses an analysis of cancer genomics data using partial least squares weights for identifying relevant genes, which are useful for follow-up validations. In Chap. 2, Zhao and Yan report an interesting biclust- ing method for microarray data analysis, which can handle the case when only a subset of genes coregulates under a subset of conditions and appears to be a novel technique for classifying cancer tissues. As another computational method for - croarray data analysis, the work by Le ^ Cao and McLachlan in Chap. 3 discusses the dif?culties encountered when dealing with microarray data subjected to sel- tion bias, multiclass, and unbalanced problems, which can be overcome by careful selection of gene expression pro?les. Novel methods presented in these chapters can be applied for developing diagnostic tests and therapeutic treatments for cancer patients.
Computational Biology: Issues and Applications in Oncology provides a comprehensive report on recent techniques and results in computational oncology essential to the knowledge of scientists, engineers, as well as postgraduate students working on the areas of computational biology, bioinformatics, and medical informatics.
With chapters timely prepared and written by experts in the field, this in-depth and up-to-date volume covers advanced statistical methods, heuristic algorithms, cluster analysis, data modeling, image and pattern analysis applied to cancer research. The literature and coverage of a spectrum of key topics in issues and applications in oncology make this a useful resource to computational life-science researchers wishing to enhance the most recent knowledge to facilitate their own investigations.
