Hidden Harkov Models for Bioinformatics by Timo Koski - 2001

No Dust Jacket

Book: Blemishes -- Light uniform toning the book spine caused by prolonged light exposure during long-term shelf storage. The rest of the book is in "As New" condition.

All pages and illustrations are present, pages are unmarrked with no toning. No marks, marginalia, underlining, or entries. The boards are unblemished, rubs, dents, or chips, and the ISBN is visible and undisturbed (photo).

From the Book: "Audience. This book will be of interest to advanced underratue and gradulate students with a fairly limited background in probability theory, but other will sell trained in mathmaticsandalready familiar with at least some of the techniques of algorithmic sequence analysis."

Amazon Review: "Hidden Markov Models of Bioinformatics" is an excellent exploration of the subject matter: appropriate coverage, well written, and engaging. Hidden Markov Models are a rather broad class of probabilistic models useful for sequential processes. Their use in the modeling and abstraction of motifs in, for example, gene and protein families is a specialization that bears a thorough description, and this book does so very well. This is a book for understanding the theory and core ideas underlying profile HMMs, and if the term Expectation Maximization doesn't sound familiar or interesting to you, this is probably not the book you're looking for. Personally I found it clearer in some ways than the standard reference by Durbin, Eddy, Krogh, and Mitchison, but actually the two complement each other very nicely. If you are interested in constructing an HMM for your favorite protein family you probably want to look at the HMMER or SAM documentation instead; if you want to understand where HMMs come from or how you might architect one, there's probably no better book than this one."

The author, at time of publication, was professor of mathmatics, University of Linkoping, Sweden.