Chapman and Hall/CRC
384 pages | 62 B/W Illus.
Lucidly Integrates Current Activities
Focusing on both fundamentals and recent advances, Introduction to Machine Learning and Bioinformatics presents an informative and accessible account of the ways in which these two increasingly intertwined areas relate to each other.
Examines Connections between Machine Learning & Bioinformatics
The book begins with a brief historical overview of the technological developments in biology. It then describes the main problems in bioinformatics and the fundamental concepts and algorithms of machine learning. After forming this foundation, the authors explore how machine learning techniques apply to bioinformatics problems, such as electron density map interpretation, biclustering, DNA sequence analysis, and tumor classification. They also include exercises at the end of some chapters and offer supplementary materials on their website.
Explores How Machine Learning Techniques Can Help Solve Bioinformatics Problems
Shedding light on aspects of both machine learning and bioinformatics, this text shows how the innovative tools and techniques of machine learning help extract knowledge from the deluge of information produced by today’s biological experiments.
… The stated audience for this book is M.S. and Ph.D. students in bioinformatics, machine intelligence, applied statistics, biostatistics, computer science, and related areas. … a well-written collection from multiple authors that I recommend for the intended audience. Several chapters include exercises.
—Technometrics, November 2009, Vol. 51, No. 4
…a good text/reference book that summarizes the latest developments in the interface between bioinformatics and machine learning and offer[s] a thorough introduction to each field. … One of the strengths of this book is the clear notation with a mathematical and statistical flavor, which will be attractive to Biometrics readers, especially to those new to statistical learning and data mining. It is also very readable for a variety of interested learners, researchers, and audiences from various backgrounds and disciplines. …
—Biometrics, March 2009
… a well-structured book that is a good starting point for machine learning in bioinformatics. … Using many popular examples, the statistical theory becomes comprehensible and bioinformatics examples motivate [readers] to apply the concepts to real data.
—Markus Schmidberger, Journal of Statistical Software, November 2008
The Biology of a Living Organism
DNA and Genes
Biological Regulation Systems: When They Go Awry
Probabilistic and Model-Based Learning
Introduction: Probabilistic Learning
Basics of Probability
Random Variables and Probability Distributions
Basics of Information Theory
Basics of Stochastic Processes
Hidden Markov Models
Frequentist Statistical Inference
Some Computational Issues
Introduction and Problem Formulation
Applications of Classification Techniques to Bioinformatics Problems
Unsupervised Learning Techniques
Principal Components Analysis
Other Dimension Reduction Techniques
Cluster Analysis Techniques
Computational Intelligence in Bioinformatics
Artificial Neural Networks
Application to Bioinformatics
Analysis of High-Throughput Gene Expression Data
Machine Learning in Structural Biology
Soft Computing in Biclustering
Fuzzy Possibilistic Biclustering
Conclusions and Discussion
Bayesian Methods for Tumor Classification
Classification Based on Reproducing Kernel Hilbert Spaces
Hierarchical Classification Model
Likelihoods of RKHS Models
The Bayesian Analysis
Prediction and Model Choice
Modeling and Analysis of iTRAQ Data
Statistical Modeling of iTRAQ Data
Discussion and Concluding Remarks
Mass Spectrometry Classification
Background on Proteomics
Data and Implementation
Results and Discussion
References appear at the end of each chapter.