Multivariate data analysis capabilities

Despite the broad definition of chemometrics, the most important part of it is the application of multivariate data analysis to chemistry-relevant data. Chemistry deals with compounds, their properties, and their transformations into other compounds. Major tasks of chemists are the analysis of complex mixtures, the synthesis of compounds with desired properties, and the construction and operation of chemical technological plants. However, chemical/physical systems of practical interest are often very complicated and cannot be described sufficiently by theory. Actually, a typical chemometrics approach is not based on first principles—that means scientific laws and mles of nature—but is data driven. Multivariate statistical data analysis is a powerful tool for analyzing and structuring data sets that have been obtained from such systems, and for making empirical mathematical models that are for instance capable to predict the values of important properties not directly measurable (Figure 1.1). 

One of the often-overlooked aspects in PAT is the intrinsic capability of some monitoring tools to combine different quality attributes. For example one of the major reasons why NIR spectroscopy is such a prevalent PAT monitoring technique is its capability of capturing both physical and chemical attributes in one multivariate measurement. The different attributes can be extracted from the data in numerous ways, which may include multivariate data analysis. 

Common ways to compare two (or more) Py-MS results are those based on different types of measures. A particular case of multivariate data analysis is that of two samples to be compared. The comparison can be done, for example, by simple procedures such as subtracting the peaks obtained in the second spectrum from the corresponding ones obtained in the first spectrum and plotting the result. The spectra subtraction is commonly performed with the electronic capabilities of data processing available in modern instrumentation. As an example. Figure 5.5.5 shows the subtracted spectrum of cellulose from glycogen (glycogen - cellulose) [73a]. The peak intensities were reported to the total ion intensity in the spectrum. 

Principles and Characteristics As already indicated in Chp. 1.2.3, Raman scattering induced by radiation (UV/VIS/NIR lasers) in gas, liquid or solid samples contains information about molecular vibrations. Raman specfioscopy (RS) was restricted for a long time primarily to academic research and was a technique rarely used outside the research laboratory. Within an industrial spectroscopy laboratory, two of the more significant advances in recent years have been the allying of FT-Raman and FTIR capabilities, coupled with the availability of multivariate data analysis software. Raman process control (in-line, on-line, in situ, onsite) is now taking off with various robust commercial instrumental systems equipped with stable laser sources, stable and sensitive CCD detectors, inexpensive fibre optics, etc. With easy interfacing with process streams and easy multiplexing with normal (remote) spectrometers the technique is expected to have impact on product and process quality. 

Fortunately, various chemometric-based techniques, including multivariate experimental design and data analysis techniques, have been devised to aid in optimizing the performance of systems and extend their separation capabilities. In broadest terms, chemometrics is a subdiscipline of analytical chemistry that uses mathematical, statistical, and formal logic to (10) ... 

Another study was done using 122 diverse molecules with biological activity data for eight proteins including human GST (activity measured with the probe l-chloro-2,4,-dinitrobenzene). Data from this study was used with a multivariate regression analysis to develop models capable of making predictions for new proteins.This data, in itself, may also be valuable for building a computational model for the human GST in the future. 

Progress in the design of mass spectrometers and the availability of online computer systems has allowed the integration of Py-MS data acquisition with multivariate mathematical data reduction methods into a single analysis technique. Such an approach combines rapid analysis capability with expert system or pattern recognition based data evaluation (Figure 13). 

The advent of analytical techniques capable of providing data on a large number of analytes in a given specimen had necessitated that better techniques be employed in the assessment of data quality and for data interpretation. In 1983 and 1984, several volumes were published on the application of pattern recognition, cluster analysis, and factor analysis to analytical chemistry. These treatises provided the theoretical basis by which to analyze these environmentally related data. The coupling of multivariate approaches to environmental problems was yet to be accomplished. 

If it is not necessary to know the specific concenirations of the species of interest, bnt to simply know whether such species are present, or not, in a complex sample then, a multivariate pattern recognition method, such as linear discriminant analysis (LDA) or artificial nenral networks (ANNs), may be used to identify the spectral characteristics of the species of interest [10]. Such methods are capable of comparing a large number of variables within a data set, such as intensity, frequency and bandwidth. LDA and ANNs are known as supervised methods because a priori... 

---