Kernel Methods in Computational Biology

Description:

Modern machine learning techniques are proving to be extremely valuable for the analysis of data in computational biology problems. One branch of machine learning, kernel methods, lends itself particularly well to the difficult aspects of biological data, which include high dimensionality (as in microarray measurements), representation as discrete and structured data (as in DNA or amino acid sequences), and the need to combine heterogeneous sources of information. This book provides a detailed overview of current research in kernel methods and their applications to computational biology.

Following three introductory chapters -- an introduction to molecular and computational biology, a short review of kernel methods that focuses on intuitive concepts rather than technical details, and a detailed survey of recent applications of kernel methods in computational biology -- the book is divided into three sections that reflect three general trends in current research. The first part presents different ideas for the design of kernel functions specifically adapted to various biological data; the second part covers different approaches to learning from heterogeneous data; and the third part offers examples of successful applications of support vector machine methods.

Bernhard Schölkopf is Director at the Max Planck Institute for Biological Cybernetics in Tübingen, Germany, and Professor at the Technical University in Berlin.

Koji Tsuda is a Research Scientist at the Max Planck Institute and a Researcher at AIST Computational Biology Research Center, Tokyo.

Jean-Philippe Vert is Researcher and Leader of the Bioinformatics Group at École des Mines de Paris.

Table of Contents:

Preface	vii
I	INTRODUCTION	1
1	A Primer on Molecular Biology Alexander Zien	3
2	A Primer on Kernel Methods Jean-Philippe Vert, Koji Tsuda and Bernhard Schölkopf	35
3	Support Vector Machine Applications in Computational Biology William S. Noble	71
II	KERNELS FOR BIOLOGICAL DATA	93
4	Inexact Matching String Kernels for Protein Classification Christina Leslie, Rui Kuang and Eleazar Eskin	95
5	Fast Kernels for String and Tree Matching S. V. N. Vishwanathan and Alexander J. Smola	113
6	Local Alignment Kernels for Biological Sequences Jean-Philippe Vert, Hiroto Saigo and Tatsuya Akutsu	131
7	Kernels for Graphs Hisashi Kashima, Koji Tsuda and Akihiro Inokuchi	155
8	Diffusion Kernels Risi Kondor and Jean-Philippe Vert	171
9	A Kernel for Protein Secondary Structure Prediction Yann Guermeur, Alain Lifchitz and Régis Vert	193
III	DATA FUSION WITH KERNEL METHODS	207
10	Heterogeneous Data Comparison and Gene Selection with Kernel Canonical Correlation Analysis Yoshihiro Yamanishi, Jean-Philippe Vert and Minoru Kanehisa	209
11	Kernel-Based Integration of Genomic Data Using Semidefinite Programming Gert R. G. Lanckriet, Nello Cristianini, Michael I. Jordan and William S. Noble	231
12	Protein Classification via Kernel Matrix Completion Taishin Kin, Tsuyoshi Kato and Koji Tsuda	261
IV	ADVANCED APPLICATION OF SUPPORT VECTOR MACHINES	275
13	Accurate Splice Site Detection for Caenorhabditis elegans Gunnar Rätsch and Sören Sonnenburg	277
14	Gene Expression Analysis: Joint Feature Selection and Classifier Design Balaji Krishnapuram, Lawrence Carin and Alexander Hartemink	299
15	Gene Selection for Microarray Data Sepp Hochreiter and Klaus Obermayer	319
	References	357
	Contributors	391
	Index	397