Hierarchical clustering, description

The bottleneck in utilizing Raman shifted rapidly from data acquisition to data interpretation. Visual differentiation works well when polymorph spectra are dramatically different or when reference samples are available for comparison, but is poorly suited for automation, for spectrally similar polymorphs, or when the form was previously unknown [231]. Spectral match techniques, such as are used in spectral libraries, help with automation, but can have trouble when the reference library is too small. Easily automated clustering techniques, such as hierarchical cluster analysis (HCA) or PCA, group similar spectra and provide information on the degree of similarity within each group [223,230]. The techniques operate best on large data sets. As an alternative, researchers at Pfizer tested several different analysis of variance (ANOVA) techniques, along with descriptive statistics, to identify different polymorphs from measurements of Raman... 

Fig. 1. Structure adapted hierarchical description of Coulomb interactions in biological macromolecules. Filled circles (level 0) represent atoms, structural units (li vel 1) are surrounded by a single-line border, and clusters (level 2) are surrounded by a double-line border.

The cluster energies are obtained from the solution of the nonrelativistic Schrodinger equation for each system. The expansion of the trial many-electron wave function delineates the level of theory (description of electron correlation), whereas the description of the constituent orbitals is associated with the choice of the orbital basis set. A recent review (Dunning 2000) outlines a path, which is based on hierarchical approaches in this double expansion in order to ensure convergence of both the correlation and basis set problems. It also describes the application of these hierarchical approaches to various chemical systems that are associated with very diverse bonding characteristics, such as covalent bonds, hydrogen bonds and weakly bound clusters. 

---