Support vector machines and their application in chemistry and biotechnology

 Content: Overview of support vector machines  Background  Maximal Interval Linear Classifier  Kernel Functions and Kernel Matrix  Optimization Theory  Elements of Support Vector Machines  Applications of Support Vector Machines   Support vector machines for classification and regression  Kernel Functions and Dimension Superiority  Notion of Kernel Functions  Kernel Matrix  Support Vector Machines for Classification  Computing SVMs for Linearly Separable Case  Computing SVMs for Linearly Inseparable Case  Application of SVC to Simulated Data  Support Vector Machines for Regression  I -Band and I -Insensitive Loss Function  Linear I -SVR  Kernel-Based I -SVR  Application of SVR to Simulated Data  Parametric Optimization for Support Vector Machines  Variable Selection for Support Vector Machines  Related Materials and Comments  VC Dimension  Kernel Functions and Quadratic Programming  Dimension Increasing versus Dimension Reducing  Appendix A: Computation of Slack Variable-Based SVMs  Appendix B: Computation of Linear I -SVR   Kernel methods  Kernel Methods: Three Key Ingredients  Primal and Dual Forms  Nonlinear Mapping  Kernel Function and Kernel Matrix  Modularity of Kernel Methods  Kernel Principal Component Analysis  Kernel Partial Least Squares  Kernel Fisher Discriminant Analysis  Relationship between Kernel Function and SVMs  Kernel Matrix Pretreatment  Internet Resources   Ensemble learning of support vector machines Ensemble Learning  Idea of Ensemble Learning  Diversity of Ensemble Learning  Bagging Support Vector Machines  Boosting Support Vector Machines  Boosting: A Simple Example  Boosting SVMs for Classification  Boosting SVMs for Regression  Further Consideration   Support vector machines applied to near-infrared spectroscopy  Near-Infrared Spectroscopy  Support Vector Machines for Classification of Near-Infrared Data  Recognition of Blended Vinegar Based on Near-Infrared Spectroscopy  Related Work on Support Vector Classification on NIR  Support Vector Machines for Quantitative Analysis of Near-Infrared Data  Correlating Diesel Boiling Points with NIR Spectra Using SVR  Related Work on Support Vector Regression on NIR  Some Comments   Support vector machines and QSAR/QSPR  Quantitative Structure-Activity/Property Relationship History of QSAR/QSPR and Molecular Descriptors Principles for QSAR Modeling Related QSAR/QSPR Studies Using SVMs  Support Vector Machines for Regression  Dataset Description  Molecular Modeling and Descriptor Calculation  Feature Selection Using a Generalized Cross-Validation Program  Model Internal Validation  PLS Regression Model  BPN Regression Model  SVR Model  Applicability Domain and External Validation  Model Interpretation  Support Vector Machines for Classification  Two-Step Algorithm: KPCA Plus LSVM  Dataset Description Performance Evaluation  Effects of Model Parameters  Prediction Results for Three SAR Datasets   Support vector machines applied to traditional Chinese medicine  Introduction  Traditional Chinese Medicines and Their Quality Control  Recognition of Authentic PCR and PCRV Using SVM  Background  Data Description  Recognition of Authentic PCR and PCRV Using Whole Chromatography Variable Selection Improves Performance of SVM Some Remarks   Support vector machines applied to OMICS study  A Brief Description of OMICS Study  Support Vector Machines in Genomics  Support Vector Machines for Identifying Proteotypic Peptides in Proteomics  Biomarker Discovery in Metabolomics Using Support Vector Machines  Some Remarks   Index
 Abstract:             ''Support vector machines (SVMs), a promising machine learning method, is a powerful tool for chemical data analysis and for modeling complex physicochemical and biological systems. It is of growing interest to chemists and has been applied to problems in such areas as food quality control, chemical reaction monitoring, metabolite analysis, QSAR/QSPR, and toxicity. This book presents the theory of SVMs in a way that is easy to understand regardless of mathematical background. It includes simple examples of chemical and OMICS data to demonstrate the performance of SVMs and compares SVMs to other traditional classification/regression methods''--
''Support vector machines (SVMs) seem a very promising kernel-based machine learning method originally developed for pattern recognition and later extended to multivariate regression. What distinguishes SVMs from traditional learning methods lies in its exclusive objective function, which minimizes the structural risk of the model. The introduction of the kernel function into SVMs made it extremely attractive, since it opens a new door for chemists/biologists to use SVMs to solve difficult nonlinear problems in chemistry and biotechnology through the simple linear transformation technique. The distinctive features and excellent empirical performances of SVMs have drawn the eyes of chemists and biologists so much that a number of papers, mainly concerned with the applications of SVMs, have been published in chemistry and biotechnology in recent years. These applications cover a large scope of chemical and/or biological meaningful problems, e.g. spectral calibration, drug design, quantitative structure-activity/property relationship (QSAR/QSPR), food quality control, chemical reaction monitoring, metabolic fingerprint analysis, protein structure and function prediction, microarray data-based cancer classification and so on. However, in order to efficiently apply this rather new technique to solve difficult problems in chemistry and biotechnology, one should have a sound in-depth understanding of what kind information this new mathematical tool could really provide and what its statistic property is. This book aims at giving a deeper and more thorough description of the mechanism of SVMs from the point of view of chemists/biologists and hence to make it easy for chemists and biologists to understand''