Identifiability correlations

Another way to identify correlations is to plot the values of the parameters in graphical form this can help to identify any correlations and the presence of outliers. A Craig plot is a two-dimerrsional scatterplot of one parameter against another ideally, the molecules should sample from all four quadrants of the plot. 

MVA is a very useful tool for classifying sets of compounds and identifying the primary latent variables that summarize the data through PCA, and for identifying correlations between variables describing the properties of compounds and the biological effects of these compounds through PLS [40],... 

Fig. 4. A schematic illustration of graph comparisons. The purpose of comparing different types of graphs is to identify correlated clusters of nodes.

A synergy approach which is the combination of linear/neural net and neighborhood behavior models that are independent ways of identifying correlations between molecular description and experimental activity. 

Connell-Carrick, K. (2003) A critical review of the empirical literature identifying correlates of child neglect. Child and Adolescent Social Work Journal 20, 5, 389-425. 

Plot the data in whatever ways are useful to gain insight. Plotting two sets of measurements against each other in a scatter plot can help identify correlations. Plotting different measurements on the same time line can help find causes for unusual events by the alignment of certain results. 

Figure 7. Plan-view distribution of arsenic in acid-insoluble residues of borehole rock samples as a series of squares whose size is proportional to the concentration of As in the sample. The plot only shows sites at which arsenic was detected in concentrations ISOppm. Multiple values at individual sites are shown as concentric symbols. Note the concentration of elevated values in the southern Ozarks and Data is from Lee and Goldhaber (2001). Major tectonic zones are shown for reference - Lee (2000) identified correlations between the faults and fractures of these tectonic zones and enrichments in MVT-related metals such as Zn and Pb although these correlations are not evident from the arsenic plot. 

We used principal component analysis to identify correlated motions in different forms of hPNP, namely, its apo and complexed forms, and assess whether they facilitate the 241-265 loop rearrangement prior to the subsequent phosphorolysis reaction. We compared the principal components for the apo and complexed hPNP simulations, and examined the different correlated motions for each form of the enzyme, comparing directly to the crystallographic B-factors. Finally, via experimental site-directed mutagenesis, several residues implicated in the correlated motion were mutated, and the kinetic constants kcat and KM (fingerprints of catalytic efficiency), were measured to weigh the impact of these residues in the phosphorolytic efficiency. 

In addition, classical MD simulations52 have identified correlated domain motions in the reactant DHF complex but not in product complexes, indicating they are related to catalysis. These domains are in the same regions highlighted by the NMR studies. 

PCA is widely used for descriptor selection in order to identify correlations between descriptors, but there are also examples where PCA is directly used for virtual screening. In a recent work by Knox et al. [73], PCA was applied in a virtual screening run to identify ligands for the estrogen receptor by identifying the part of the chemical space where known estrogen receptor ligands lie. 

PLS (Partial Least Squares) regression was used for quantification and classification of aristeromycin and neplanocin A (Figure 4). Matlab was used for PCA (Principal Components Analysis) (according to the NIPALS algorithm) to identify correlations amongst the variables from the 882 wavenumbers and reduce the number of inputs for Discriminant Function Analysis (DFA) (first 15 PCA scores used) (Figure 5). 

Principal components analysis is a well-established multivariate statistical technique that can be used to identify correlations within large data sets and to reduce the number of dimensions required to display the variation within the data. A new set of axes, principal components (PCs), are constructed, each of which accounts for the maximum variation not accounted for by previous principal components. Thus, a plot of the first two PCs displays the best two-dimensional representation of the total variance within the data. With pyrolysis mass spectra, principal components analysis is used essentially as a data reduction technique prior to performing canonical variates analysis, although information obtained from principal components plots can be used to identify atypical samples or outliers within the data and as a test for reproducibihty. 

The ID F spectrum (by direct polarization or rotor-synchronized Hahn-echo pulse sequence with MAS), 2D HETCOR [67] and relaxation times have demonstrated to be very useful for identifying correlations, interactions, amorphous contents in tablets or for investigating mixtures [68-71]. The 2D experiments that involve F are CPLG-HETCOR and f CP-DARR (which is based m... 

With respect to the different options of power distribution between buyer and supplier as highlighted above (Fig. 5.2), Cox (2004) also identifies correlations between this distribution and the types of buyer-supplier relationships presented... 

Once the resonances of each unit were identified, the attachments were determined by identifying correlations in selective COSY spectra like those shown in Figure 24.3. In the/i-decoupled selective COSY spectra sufficient chemical shift dispersion and spectral resolution was achieved to identify most of the stereo-sequences present in the oligomers. A similar approach enabled them to identify the structures of all the chain ends in these oligomers and to assign their resonances [48]. 

---