Chemometrics, present and future success

Abstract How successful has chemometrics been? The answer depends, of course, on how success is defined and measured. A brief discussion of this subject is given, with reference to academic and industrial research and other application areas, notably industrial development and production. The areas where chemometrics has been most successful according to all measures are the following: (1) multivariate calibration, (2) structure—(re)activity modelling, (3) pattern recognition, classification, and discriminant analysis, and (4) multivariate process modelling and monitoring. Possible reasons are ventilated for these seemingly disparate success stories, together with some reflections of what remains to be done in these areas, and why success is slower in other areas. To continue the successful development of chemometrics, the most important is, in our opinion, that we continue to see ourselves primarily as chemical problem solvers—and only when needed, as developers of new methodology. To illustrate the chemistry driven development of chemometrics, we shall describe some recent work in multivariate modelling and analysis, applied in the areas of structure–activity relationships (peptides, proteins, RNA, DNA, hemes), modelling of batch processes and complicated kinetics, wavelet data compression, and orthogonal preprocessing of spectral data (NIR) for multivariate calibration.

[1]  Anders Berglund,et al.  Alignment of flexible molecules at their receptor site using 3D descriptors and Hi-PCA , 1997, J. Comput. Aided Mol. Des..

[2]  S. Wold,et al.  Partial least squares analysis with cross‐validation for the two‐class problem: A Monte Carlo study , 1987 .

[3]  S. Wold,et al.  Orthogonal signal correction of near-infrared spectra , 1998 .

[4]  S Wold,et al.  Chemometrics, why, what and where to next? , 1991, Journal of pharmaceutical and biomedical analysis.

[5]  William G. Hunter,et al.  Designs for Discriminating Between Two Rival Models , 1965 .

[6]  H. Haario,et al.  COMBINING SOFT AND HARD MODELLING IN CHEMICAL KINETIC MODELS , 1998 .

[7]  Stefan Rännar,et al.  Polypeptide sequence property relationships in Escherichia coli based on auto cross covariances , 1995 .

[8]  S. Wold,et al.  Fuzzy clustering of 627 alcohols, guided by a strategy for cluster analysis of chemical compounds for combinatorial chemistry , 1998 .

[9]  Han van de Waterbeemd,et al.  Computer-Assisted Lead Finding and Optimization , 1997 .

[10]  Svante Wold,et al.  PLS DISCRIMINANT PLOTS , 1986 .

[11]  Svante Wold,et al.  Hierarchical multiblock PLS and PC models for easier model interpretation and as an alternative to variable selection , 1996 .

[12]  John F. MacGregor,et al.  Adaptive batch monitoring using hierarchical PCA , 1998 .

[13]  Han van de Waterbeemd,et al.  Chemometric methods in molecular design , 1995 .

[14]  A. Höskuldsson.  PLS regression methods , 1988 .

[15]  Svante Wold,et al.  Modelling and diagnostics of batch processes and analogous kinetic experiments , 1998 .

[16]  S. Wold,et al.  PLS regression on wavelet compressed NIR spectra , 1998 .

[17]  J. E. Jackson.  A User's Guide to Principal Components , 1991 .

[18]  Thomas E. Marlin,et al.  Multivariate statistical monitoring of process operating performance , 1991 .

[19]  John F. MacGregor,et al.  Multi-way partial least squares in monitoring batch processes , 1995 .

[20]  S Wold,et al.  Classification of human cancer cells by means of capillary gas chromatography and pattern recognition analysis. , 1981, Journal of chromatography.