CHEMOMETRICS IN PRACTICAL APPLICATIONS Edited by Kurt Varmuza Chemometrics in Practical Applications Edited by Kurt Varmuza Published by InTech Janeza Trdine 9, 51000 Rijeka, Croatia Copyright © 2012 InTech All chapters are Open Access distributed under the Creative Commons Attribution 3.0 license, which allows users to download, copy and build upon published articles even for commercial purposes, as long as the author and publisher are properly credited, which ensures maximum dissemination and a wider impact of our publications. After this work has been published by InTech, authors have the right to republish it, in whole or part, in any publication of which they are the author, and to make other personal use of the work. Any republication, referencing or personal use of the work must explicitly identify the original source. As for readers, this license allows users to download, copy and build upon published chapters even for commercial purposes, as long as the author and publisher are properly credited, which ensures maximum dissemination and a wider impact of our publications. Notice Statements and opinions expressed in the chapters are these of the individual contributors and not necessarily those of the editors or publisher. No responsibility is accepted for the accuracy of information contained in the published chapters. The publisher assumes no responsibility for any damage or injury to persons or property arising out of the use of any materials, instructions, methods or ideas contained in the book. Publishing Process Manager Maja Jukic Technical Editor Teodora Smiljanic Cover Designer InTech Design Team First published March, 2012 Printed in Croatia A free online edition of this book is available at www.intechopen.com Additional hard copies can be obtained from orders@intechopen.com Chemometrics in Practical Applications, Edited by Kurt Varmuza p. cm. ISBN 978-953-51-0438-4 Contents Preface IX Part 1 Methods 1 Chapter 1 Model Population Analysis for Statistical Model Comparison 3 Hong-Dong Li, Yi-Zeng Liang and Qing-Song Xu Chapter 2 Critical Aspects of Supervised Pattern Recognition Methods for Interpreting Compositional Data 21 A. Gustavo González Chapter 3 Analysis of Chemical Processes, Determination of the Reaction Mechanism and Fitting of Equilibrium and Rate Constants 41 Marcel Maeder and Peter King Chapter 4 Exploratory Data Analysis with Latent Subspace Models 63 José Camacho Chapter 5 Experimental Optimization and Response Surfaces 91 Veli-Matti Tapani Taavitsainen Part 2 Biochemistry 139 Chapter 6 Metabolic Biomarker Identification with Few Samples 141 Pietro Franceschi, Urska Vrhovsek, Fulvio Mattivi and Ron Wehrens Chapter 7 Kinetic Analyses of Enzyme Reaction Curves with New Integrated Rate Equations and Applications 157 Xiaolan Yang, Gaobo Long, Hua Zhao and Fei Liao Chapter 8 Chemometric Study on Molecules with Anticancer Properties 185 João Elias Vidueira Ferreira, Antonio Florêncio de Figueiredo, Jardel Pinto Barbosa and José Ciríaco Pinheiro VI Contents Chapter 9 Electronic Nose Integrated with Chemometrics for Rapid Identification of Foodborne Pathogen 201 Yong Xin Yu and Yong Zhao Part 3 Technology 215 Chapter 10 Chemometrics in Food Technology 217 Riccardo Guidetti, Roberto Beghi and Valentina Giovenzana Chapter 11 Metabolomics and Chemometrics as Tools for Chemo(bio)diversity Analysis - Maize Landraces and Propolis 253 Marcelo Maraschin, Shirley Kuhnen, Priscilla M.M. Lemos, Simone Kobe de Oliveira, Diego A. da Silva, Maíra M. Tomazzoli, Ana Carolina V. Souza, Rúbia Mara Pinto, Virgílio G. Uarrota, Ivanir Cella, Antônio G. Ferreira, Amélia R.S. Zeggio, Maria B.R. Veleirinho, Ivone Delgadillo and Flavia A. Vieira Chapter 12 Using Principal Component Scores and Artificial Neural Networks in Predicting Water Quality Index 271 Rashid Atta Khan, Sharifuddin M. Zain, Hafizan Juahir, Mohd Kamil Yusoff and Tg Hanidza T.I. Chapter 13 PARAFAC Analysis for Temperature-Dependent NMR Spectra of Poly(Lactic Acid) Nanocomposite 289 Hideyuki Shinzawa, Masakazu Nishida, Toshiyuki Tanaka, Kenzi Suzuki and Wataru Kanematsu Chapter 14 Application of Chemometrics to the Interpretation of Analytical Separations Data 305 James J. Harynuk, A. Paulina de la Mata and Nikolai A. Sinkov Preface Chemometrics has been defined as "a chemical discipline that uses statistical and mathematical methods to design or select optimum procedures and experiments, and to provide maximum chemical information by analyzing chemical data". Chemometrics can be considered as a part of the wider field chemoinformatics, and has close relationships to bioinformatics. The start of chemometrics dates back to the 1960s, when multivariate data analysis methods - like for instance the "learning machine" - have been tried for solving rather complicated problems in chemistry, such as the automatic interpretation of molecular spectra. The name chemometrics was first used by Svante Wold in 1972 (in Swedish, kemometria) and it was established in 1974 by Bruce Kowalski. The first years of chemometrics were characterized by rather uncritical use of machine learning methods for complex - often too complex - tasks in chemistry and consequently sometimes accompanied by ignorance and refusal of many chemists. However, in this time also falls the presentation of the PLS regression method by chemometricians, which is now the most used method for evaluation of multivariate data, not only in chemistry. During the next decades chemometricians learned to use multivariate data analysis in a proper and safe way for problems with a realistic chance for success, and also found back to the underlying statistical concepts. Chemometrics contributed with valuable method developments and provided many stimulants in the area. Furthermore, commercial software became available and nowadays several basic chemometric methods, like principal component analysis, multivariate classification, and multiple regression (by PLS and other approaches) are routinely used in chemical research and industry. Admittedly, sometimes without the necessary elementary knowledge about the used methods. Despite the broad definition of chemometrics, the most important part of it is still the application of multivariate data analysis to chemistry-relevant data. Chemical-physical systems of practical interest are often complicated and relationships between available (measurement) data and desired data (properties, origin) cannot be described by theory. Therefore, a typical chemometric approach is not based on "first principles" but is "data driven" and has the goal to create empirical models. A thorough evaluation of the performance of such models is essential for new cases. Multivariate statistical data analysis has been proven as a powerful tool for analyzing and structuring such data sets from chemistry and biochemistry. X Preface This book is a collection of 14 chapters, divided into three sections. Assignment of the chapters to these sections only indicates the main contents of a chapter because most are interdisciplinary and contains theoretical as well as practical aspects. In section "Methods" the topics comprise statistical model comparison, treatment of compositional data, methods for the estimation of kinetic parameters, and a new approach for exploratory data analysis. A comprehensive chapter presents an overview of experimental optimization. Section "Biochemistry" deals with biomarker identification, kinetics of enzyme reactions, selection of substances with anticancer properties, and the use of an electronic nose for the identification of foodborne pathogens. Section "Technology" focuses on chemometric methods used in food technology, for water quality estimation, for the characterization of nanocomposite materials by NMR spectra, and in chromatographic separation processes. The topics of this book cover a wide range of highly relevant problems in chemistry and chemical/biological technology. The presented solutions may be of interest to the reader even if not working exactly in the fields described in the chapters. The book is intended for chemists, chemical engineers, and biotechnologists working in research, production or education. Students in these areas will find a source with highly diverse and successful applications of chemometric methods. In this sense, the major goal of this "mosaic of contributions" - presented in a book - is to promote new and adequate use of multivariate data analysis methods in chemistry and related fields. March 2012 Kurt Varmuza Vienna University of Technology, Vienna, Austria . CHEMOMETRICS IN PRACTICAL APPLICATIONS Edited by Kurt Varmuza Chemometrics in Practical Applications Edited by Kurt Varmuza Published by InTech Janeza Trdine. make predictions on the remaining 30% samples, resulting in a RMSEP value. Repeating this procedure 1000 times, we, for both datasets, Chemometrics in Practical Applications 6 Fig. 2 assessment. In chemometrics, model comparison is usually conducted by validating different models on an independent test set or by using cross validation [4, 5, 7], resulting in a single value,