Three-dimensional quantitative structure-activity relationship (3D-QSAR) models for a novel class of piperazine-based stromelysin-1 (MMP-3) inhibitors: applying a "divide and conquer" strategy.

Three-dimensional quantitative structure-activity relationship (3D-QSAR) models have been obtained using comparative molecular field analysis (CoMFA) for a novel series of piperazine-based matrix metalloproteinase inhibitors (MMPIs). The crystal structure of stromelysin-1 (MMP-3) was used to identify regions of the enzyme and inhibitors where steric and electrostatic effects correlate strongly with biological activity. A training set composed of a subset of inhibitors (#10-35), which differed only with regards to the substituent (n-alkyl, amide, carbamide and sulfonamide) on the piperazine distal nitrogen, yielded the most predictive CoMFA model, with r(2) values of 0.592 (cross-validated) and 0.989 (conventional); this model was further validated using test compounds from two inhibitor subsets. Investigation of various ligand conformations, inhibitor subsets, alignment schemes and partial charge formalisms was required to obtain satisfactory models. The greatest success was achieved by incorporating inertial alignment together with manual adjustment of the enzyme-docked inhibitors to ensure complementarity between the inhibitors' substituent conformations and the structural characteristics of the MMP-3 S1-S2' binding pockets. Key insights into the structure-activity relationship (SAR) obtained from this analysis for this inhibitor set are in agreement with experimentally observed data on stromelysin-1 biological activity and binding-site topology. In particular, the present study sheds new light on the steric and electrostatic requirements for ligand binding to the partly solvent-exposed S1-S2' area.

Determination of vaporization enthalpies of polychlorinated biphenyls by correlation gas chromatography.

The vaporization enthalpies of 16 polychlorinated biphenyls have been determined by correlation gas chromatography. This study was prompted by the realization that the vaporization enthalpy of the standard compounds used in previous studies, octadecane and eicosane, were values measured at 340 and 362 K, respectively, rather than at 298 K. Adjustment to 298 K amounts to a 7-8 kJ/mol increment in the values. With the inclusion of this adjustment, vaporization enthalpies evaluated by correlation gas chromatography are in good agreement with the values determined previously in the literature. The present results are based on the vaporization enthalpies of several standards whose values are well established in the literature. The standards include a variety of n-alkanes and various chlorinated hydrocarbons. The vaporization enthalpies of PCBs increased with the number of chlorine atoms and were found to be larger for meta- and para-substituted polychlorinated biphenyls.

Homology modeling of the estrogen receptor subtype beta (ER-beta) and calculation of ligand binding affinities.

Estrogen is a steroid hormone playing critical roles in physiological processes such as sexual differentiation and development, female and male reproductive processes, and bone health. Numerous natural and synthetic environmental compounds have been shown capable of estrogenic effects. This area has been the focus of significant fundamental and applied research due both to the potential detrimental effects of these compounds upon normal physiological processes and to the potential beneficial effects of tissue-selective estrogen agonists/antagonists for the prevention and treatment of numerous diseases. Genomic effects of the active form of estrogen, 17beta-estradiol, are mediated through at least two members of the steroid hormone receptor superfamily, estrogen receptor subtype alpha (ER-alpha) and estrogen receptor subtype beta (ER-beta). At the time of this work, the X-ray crystal structure of the ER-alpha had been elucidated, however, coordinates of the ER-beta were not publicly available. Based upon the significant structural conservation across members of the steroid hormone receptor family, and the high sequence homology between ER-alpha and ER-beta (>60%), we have developed a homology model of the ER-beta structure. Using the crystal structure of ER-alpha and the homology model of ER-beta, we demonstrate a strong correlation between computed values of the binding-energy and published values of the observed relative binding affinity (RBA) for a variety of compounds for both receptors, as well as the ability to identify receptor subtype selective compounds. Furthermore, using the recently available crystal structure of ER-beta for comparison purposes, we show that not only is the predicted homology model structurally accurate, but that it can be used to assess ligand binding affinities.

Computational studies on HIV-1 protease inhibitors: influence of calculated inhibitor-enzyme binding affinities on the statistical quality of 3D-QSAR CoMFA models.

A theoretical study was performed on a set of 38 human immunodeficiency type 1 (HIV-1) protease inhibitors that are structurally similar to the AIDS drug Indinavir. Comparison between the computed binding energies and experimental activity data (pIC(50)) found a high degree of correlation (r(2)() = 0.82). Three-dimensional quantitative structure-activity relationship (3D-QSAR) models using comparative molecular field analysis (CoMFA) yielded predicted activities that were in excellent agreement with the corresponding experimentally determined values. Inclusion of the calculated enzyme-inhibitor binding energy as an additional descriptor in the CoMFA model yielded a significant improvement in the internal predictive ability of our model (q(2)() = 0.45 to q(2)() = 0.69). Separate CoMFA models were constructed to evaluate the influence of different alignment schemes (Atom Fit and Field Fit) and different partial atomic charge assignment schemes (Discover CVFF, Gasteiger-Marsili, and AM1-ESP) on the statistical quality of the models.

Polynomial neural network for linear and non-linear model selection in quantitative-structure activity relationship studies on the internet.

This article presents a self-organising multilayered iterative algorithm that provides linear and non-linear polynomial regression models thus allowing the user to control the number and the power of the terms in the models. The accuracy of the algorithm is compared to the partial least squares (PLS) algorithm using fourteen data sets in quantitative-structure activity relationship studies. The calculated data show that the proposed method is able to select simple models characterized by a high prediction ability and thus provides a considerable interest in quantitative-structure activity relationship studies. The software is developed using client-server protocol (Java and C++ languages) and is available for world-wide users on the Web site of the authors.

Development of a novel class of monocyclic and bicyclic alkyl amides that exhibit CB1 and CB2 cannabinoid receptor affinity and receptor activation.

CB1 and CB2 cannabinoid receptors can be activated by several different classes of agonists, including cannabinoids such as delta9-tetrahydrocannabinol and 9-nor-9beta-hydroxyhexahydrocannabinol, and eicosanoids such as arachidonylethanolamide. Structure-activity relationship studies have identified potential pharmacophoric elements for binding to cannabinoid receptors by both cannabinoids and eicosanoids. Molecular models have hypothesized conformational, spatial, and pharmacophoric distance requirements based upon radioligand binding data whereby overlap of pharmacophoric elements of the two classes disclose a low energy conformation of arachidonylethanolamide that can occupy the same receptor space as cannabinoid ligands. To test this model, we have developed a novel class of monocyclic and bicyclic alkyl amide cannabinoid receptor ligands. Further, we predicted a spatial conformation for these compounds in a molecular model based on the pharmacophoric and structural requirements for binding to the CB1 cannabinoid receptor.

Evidence for a strong sulfur-aromatic interaction derived from crystallographic data.

We have uncovered new evidence for a significant interaction between divalent sulfur atoms and aromatic rings. Our study involves a statistical analysis of interatomic distances and other geometric descriptors derived from entries in the Cambridge Crystallographic Database (F. H. Allen and O. Kennard, Chem. Design Auto. News, 1993, Vol. 8, pp. 1 and 31-37). A set of descriptors was defined sufficient in number and type so as to elucidate completely the preferred geometry of interaction between six-membered aromatic carbon rings and divalent sulfurs for all crystal structures of nonmetal-bearing organic compounds present in the database. In order to test statistical significance, analogous probability distributions for the interaction of the moiety X-CH(2)-X with aromatic rings were computed, and taken a priori to correspond to the null hypothesis of no significant interaction. Tests of significance were carried our pairwise between probability distributions of sulfur-aromatic interaction descriptors and their CH(2)-aromatic analogues using the Smirnov-Kolmogorov nonparametric test (W. W. Daniel, Applied Nonparametric Statistics, Houghton-Mifflin: Boston, New York, 1978, pp. 276-286), and in all cases significance at the 99% confidence level or better was observed. Local maxima of the probability distributions were used to define a preferred geometry of interaction between the divalent sulfur moiety and the aromatic ring. Molecular mechanics studies were performed in an effort to better understand the physical basis of the interaction. This study confirms observations based on statistics of interaction of amino acids in protein crystal structures (R. S. Morgan, C. E. Tatsch, R. H. Gushard, J. M. McAdon, and P. K. Warme, International Journal of Peptide Protein Research, 1978, Vol. 11, pp. 209-217; R. S. Morgan and J. M. McAdon, International Journal of Peptide Protein Research, 1980, Vol. 15, pp. 177-180; K. S. C. Reid, P. F. Lindley, and J. M. Thornton, FEBS Letters, 1985, Vol. 190, pp. 209-213), as well as studies involving molecular mechanics (G. Nemethy and H. A. Scheraga, Biochemistry and Biophysics Research Communications, 1981, Vol. 98, pp. 482-487) and quantum chemical calculations (B. V. Cheney, M. W. Schulz, and J. Cheney, Biochimica Biophysica Acta, 1989, Vol. 996, pp.116-124; J. Pranata, Bioorganic Chemistry, 1997, Vol. 25, pp. 213-219)-all of which point to the possible importance of the sulfur-aromatic interaction. However, the preferred geometry of the interaction, as determined from our analysis of the small-molecule crystal data, differs significantly from that found by other approaches.

Comparative molecular field analysis as a tool to evaluate mode of action of chemical hybridization agents.

The 3D-QSAR method of comparative molecular field analysis (CoMFA) was applied to three patent families of chemical hybridization agents (CHAs) in the MON21200 class of chemistry. The models for each CHA family gave good correlations between the variations in log percent male sterility and in the steric-electrostatic properties of the patent set. For all CHA families, observed sterility rates are generally higher for the sodium salts than for the corresponding esters. This is consistent with our CoMFA models which show that negative charge is favored in the region of the carboxylate group. The CoMFA models also indicated that for the MON21200 family increased steric bulk at the 4-position on the phenyl ring is associated with enhanced activity. However, for the RH0007 and the HYBRID families, male sterility is generally enhanced with increased steric bulk at the 2- or 3-position on the phenyl ring. Although the models cannot provide unambiguous conclusions about a common mode of action, similarities in the CoMFA contour maps provided some clues for a common agrophore for these three CHA families.

Comparison of estrogen receptor alpha and beta subtypes based on comparative molecular field analysis (CoMFA).

A substantial body of evidence indicates that both humans and wildlife suffer adverse health effects from exposure to environmental chemicals that are capable of interacting with the endocrine system. The recent cloning of the estrogen receptor beta subtype (ER-beta) suggests that the selective effects of estrogenic compounds may arise in part by the control of different subsets of estrogen-responsive promoters by the two ER subtypes, ER-alpha and ER-beta. In order to identify the structural prerequisites for ligand-ER binding and to discriminate ER-alpha and ER-beta in terms of their ligand-binding specificities, Comparative Molecular Field Analysis (CoMFA) was employed to construct a three-dimensional Quantitative Structure-Activity Relationship (3D-QSAR) model on a data set of 31 structurally-diverse compounds for which competitive binding affinities have been measured against both ER-alpha and ER-beta. Structural alignment of the molecules in CoMFA was achieved by maximizing overlap of their steric and electrostatic fields using the Steric and Electrostatic ALignment (SEAL) algorithm. The final CoMFA models, generated by correlating the calculated 3D steric and electrostatic fields with the experimentally observed binding affinities using partial least-squares (PLS) regression, exhibited excellent self-consistency (r2 > 0.99) as well as high internal predictive ability (q2 > 0.65) based on cross-validation. CoMFA-predicted values of RBA for a test set of compounds outside of the training set were consistent with experimental observations. These CoMFA models can serve as guides for the rational design of ER ligands that possess preferential binding affinities for either ER-alpha or ER-beta. These models can also prove useful in risk assessment programs to identify real or suspected EDCs.

Signal transduction of eicosanoid CB1 receptor ligands.

The eicosanoid ligand, arachidonylethanolamide (anandamide), interacts with the CB1 cannabinoid receptor in the brain to signal its response. Pharmacophoric points of interaction between this agonist and the receptor have been proposed based upon structure-activity relationship studies of ligand binding to the receptor. Three dimensional quantitative structure-activity relationship (3D-QSAR) models have been constructed based upon the corresponding pharmacophoric points predicted for cannabinoid ligands delta9-tetrahydrocannabinol and 9-nor-9beta-hydroxyhexa-hydrocannabinol. A novel data set has been used to test the statistical validity of these models. Once the ligand interacts with the CB1 receptor, signal transduction occurs via G-proteins of the Gi/o family which are shown to be associated with the receptor. Evidence suggests that the juxtamembrane region of the C-terminal of the CB1 receptor is critical for activation of these G-proteins.

Pharmaceutical fingerprinting in phase space. 1. Construction of phase fingerprints.

The present study proposes a general method for constructing pharmaceutical fingerprints in the analysis of HPLC trace organic impurity patterns. The approach considers signals in phase space and accounts for two different types of noise: additive and perturbative. The first type, additive noise, contributes to distortion of the absolute values of signal peaks. The second type, perturbative noise, contributes to variations of the retention times of signal peaks and distorts the time scale of the trace organic impurity patterns. The ability of the proposed approach to consider both types of noise significantly distinguishes it from existing methods of data analysis that are usually designed to treat only the additive noise. Analysis of the HPLC signals in phase space eliminates the problem of perturbation noise and enables detection and comparison of similar signal segments recorded at different retention times. The current study analyzes the chromatographic trace organic impurity patterns collected from six different manufacturers of L-tryptophan using three HPLC columns. For five manufacturers the variability of data recorded with the same column are in perfect agreement with the proposed model. A significant variance of parameters is detected for one manufacturer, thus indicating a possible change in its product consistency. The analysis in phase space is also used to explain the previously detected variability of HPLC signals across columns. The accompanying paper reports an application of the proposed approach for the pattern recognition of HPLC data.

Pharmaceutical fingerprinting in phase space. 2. Pattern recognition.

The current study introduces an approach for pattern recognition of drug manufacturers according to their HPLC trace impurity data. This method considers signals in phase space and accounts for two different types of noise: additive and perturbative. The pharmaceutical fingerprints are estimated as mean trajectories of HPLC trace impurity data and are used as reference models for recognition of new data by the minimal length classifier. The chromatographic trace organic impurity patterns collected from six different manufacturers of L-tryptophan are analyzed as an example. The prediction ability of the new method tested using three different cross-validation procedures remains about 95% even if the number of available data in the training sets decreases by 5 times. The accuracy of prediction in phase space is superior compared to results calculated using a Window Preprocessing method and artificial neural networks. The difference in performance between new and previous methods becomes more significant under particular conditions that are more adequate for practical application of the method. In addition, the current approach enables simple and comprehensive interpretation of the calculated results.

Regulation of Gi by the CB1 cannabinoid receptor C-terminal juxtamembrane region: structural requirements determined by peptide analysis.

A CB1 cannabinoid receptor peptide fragment from the C-terminal juxtamembrane region autonomously inhibits adenylyl cyclase activity in a neuroblastoma membrane preparation. The cannabinoid receptor antagonist, SR141716A, failed to block the response. The peptide was able to evoke the response in membranes from Chinese hamster ovary (CHO) cells that do not express the CB1 receptor. These studies are consistent with a direct activation of Gi by the peptide. To test the importance of a BXBXXB sequence, Lys403 was acetylated, resulting in a peptide having similar affinity but reduced efficacy. N-Terminal truncation of Arg401 resulted in a 6-fold loss of affinity, which was not further reduced by sequential truncation of up to the first seven amino acids, four of which are charged. N-Terminal-truncated peptides exhibited maximal activity, suggesting that Gi activation can be conferred by the remaining amino acids. Truncation of the C-terminal Glu417 or substitution of Glu417 by a Leu or of Arg401 by a Norleucine reduced activity at 100 microM. The C-terminal juxtamembrane peptide was constrained to a loop peptide by placement of Cys residues at both terminals and disulfide coupling. This modification reduced the affinity 3-fold but yielded near-maximal efficacy. Blocking the Cys termini resulted in a loss of efficacy. Circular dichroism spectropolarimetry revealed that all C-terminal juxtamembrane peptide analogues exist in a random coil conformation in an aqueous environment. A hydrophobic environment (trifluoroethanol) failed to induce alpha-helix formation in the C-terminal juxtamembrane peptide but did so in less active peptides. The anionic detergent sodium dodecyl sulfate induced alpha-helix formation in all analogues except the loop peptide, where it induces a left-handed PII conformation. It is concluded that alpha-helix formation is not required for Gi activation.

Three-dimensional quantitative structure-activity relationship study of the cannabimimetic (aminoalkyl)indoles using comparative molecular field analysis.

The present study describes the implementation of comparative molecular field analysis (CoMFA) to develop two 3D-QSAR (quantitative structure-activity relationship) models (CoMFA models 1 and 2) of the cannabimimetic (aminoalkyl)indoles (AAIs) for CB1 cannabinoid receptor binding affinity, based on pKi values measured using radioligand binding assays that displace two different agonist ligands, [3H]CP-55940 and [3H]WIN-55212-2. Both models exhibited a strong correlation between the calculated steric-electrostatic fields and the observed biological activity for the respective training set compounds. In light of the basicity of the morpholine nitrogen in the AAIs, separate CoMFA models were built for the AAIs as unprotonated and protonated species. Comparison of the statistical parameters resulting from these CoMFA models failed to provide unequivocal evidence as to whether the AAIs are protonated or neutral as receptor-bound species. Although the training sets of CoMFA model 1 and CoMFA model 2 differed with respect to composition and to the choice of displacement radioligand in each biological assay, their CoMFA StDevCoeff contour plots reveal similarities in terms of identifying those regions around the AAIs that are important for CB1 cannabinoid receptor binding such as the sterically favored region around the C3 aroyl group and the sterically forbidden region around the indole ring. When the experimental pKi values for the training set compounds to displace the AAI radioligand [3H]WIN-55212-2 were plotted against the pKi values as predicted for the same compounds to displace the cannabinoid radioligand [3H]CP-55940, the correlation was moderately strong (r = 0.73). However, the degree of correlation may have been lowered by the structural differences in the compounds comprising the training sets for CoMFA model 1 and CoMFA model 2. Taken together, the results of this study suggest that the binding site region within the CB1 cannabinoid receptor can accommodate a wide range of structurally diverse cannabimimetic analogues including the AAIs.

Derivation of a pharmacophore model for anandamide using constrained conformational searching and comparative molecular field analysis.

Constrained molecular dynamics simulations on anandamide, together with a systematic distance comparison search, have revealed a specific low-energy conformer whose spatial disposition of the pharmacophoric elements closely matches that of HHC. This conformer enables near superposition of the following: (1) the oxygen of the carboxyamide and the phenolic hydroxyl group of HHC, (2) the hydroxyl group of the ethanol and the cyclohexyl hydroxyl group of HHC, (3) the alkyl tail and the lipophilic side chain of HHC, and (4) the polyolefin loop and the tricyclic ring structure of HHC. The close matching of common pharmacophoric elements of anandamide with HHC offers persuasive evidence of the biological relevance of this conformer. The proposed pharmacophore model was capable of discriminating between structurally related compounds exhibiting different pharmacological potency for the CB1 cannabinoid receptor, i.e., anandamide and N-(2-hydroxyethyl)prostaglandinamide. Furthermore, a 3D-QSAR model was derived using CoMFA for a training set of 29 classical and nonclassical analogues which rationalized the binding affinity in terms of steric and electrostatic properties and, more importantly, which predicted the potency of anandamide in excellent agreement with experimental data. The ABC tricyclic HU-210/HU-211 and ACD tricyclic CP55,243/CP55,244 enantiomeric pairs were employed as test compounds to validate the present CoMFA model. For each enantiomeric pair, the CoMFA-predicted log Ki values correctly identified that enantiomer exhibiting the higher affinity for the receptor.

Application of a pruning algorithm to optimize artificial neural networks for pharmaceutical fingerprinting.

The present study investigates an application of artificial neural networks (ANNs) for use in pharmaceutical fingerprinting. Several pruning algorithms were applied to decrease the dimension of the input parameter data set. A localized fingerprint region was identified within the original input parameter space from which a subset of input parameters was extracted leading to enhanced ANN performance. The present results confirm that ANNs can provide a fast, accurate, and consistent methodology applicable to pharmaceutical fingerprinting.

Evaluation of quantitative structure-activity relationship methods for large-scale prediction of chemicals binding to the estrogen receptor.

Three different QSAR methods, Comparative Molecular Field Analysis (CoMFA), classical QSAR (utilizing the CODESSA program), and Hologram QSAR (HQSAR), are compared in terms of their potential for screening large data sets of chemicals as endocrine disrupting compounds (EDCs). While CoMFA and CODESSA (Comprehensive Descriptors for Structural and Statistical Analysis) have been commercially available for some time, HQSAR is a novel QSAR technique. HQSAR attempts to correlate molecular structure with biological activity for a series of compounds using molecular holograms constructed from counts of sub-structural molecular fragments. In addition to using r2 and q2 (cross-validated r2) in assessing the statistical quality of QSAR models, another statistical parameter was defined to be the ratio of the standard error to the activity range. The statistical quality of the QSAR models constructed using CoMFA and HQSAR techniques were comparable and were generally better than those produced with CODESSA. It is notable that only 2D-connectivity, bond and elemental atom-type information were considered in building HQSAR models. Since HQSAR requires no conformational analysis or structural alignment, it is straightforward to use and lends itself readily to the rapid screening of large numbers of compounds. Among the QSAR methods considered, HQSAR appears to offer many attractive features, such as speed, reproducibility and ease of use, which portend its utility for prioritizing large numbers of potential EDCs for subsequent toxicological testing and risk assessment.

Quantitative structure-activity relationships (QSARs) for estrogen binding to the estrogen receptor: predictions across species.

The recognition of adverse effects due to environmental endocrine disruptors in humans and wildlife has focused attention on the need for predictive tools to select the most likely estrogenic chemicals from a very large number of chemicals for subsequent screening and/or testing for potential environmental toxicity. A three-dimensional quantitative structure-activity relationship (QSAR) model using comparative molecular field analysis (CoMFA) was constructed based on relative binding affinity (RBA) data from an estrogen receptor (ER) binding assay using calf uterine cytosol. The model demonstrated significant correlation of the calculated steric and electrostatic fields with RBA and yielded predictions that agreed well with experimental values over the entire range of RBA values. Analysis of the CoMFA three-dimensional contour plots revealed a consistent picture of the structural features that are largely responsible for the observed variations in RBA. Importantly, we established a correlation between the predicted RBA values for calf ER and their actual RBA values for human ER. These findings suggest a means to begin to construct a more comprehensive estrogen knowledge base by combining RBA assay data from multiple species in 3D-QSAR based predictive models, which could then be used to screen untested chemicals for their potential to bind to the ER. Another QSAR model was developed based on classical physicochemical descriptors generated using the CODESSA (Comprehensive Descriptors for Structural and Statistical Analysis) program. The predictive ability of the CoMFA model was superior to the corresponding CODESSA model.

QSAR models for binding of estrogenic compounds to estrogen receptor alpha and beta subtypes.

We have developed Quantitative Structure-Activity Relationship (QSAR) models based on Comparative Molecular Field Analysis (CoMFA) for 31 estrogenic chemicals whose relative binding affinity (RBA) is available for both ER-alpha and ER-beta. The models demonstrated a significant correlation (r2>0.95) between the CoMFA-calculated steric/electrostatic fields and corresponding RBA data and a good predictive capability (q2>0.6) based on cross-validation. The CoMFA models and contour plots obtained for ER-alpha and ER-beta suggest a close similarity between the receptors in terms of mode of binding and provide a rational basis for ligand selectivity.

Preprocessing of HPLC trace impurity patterns by wavelet packets for pharmaceutical fingerprinting using artificial neural networks.

The immediate objective of this research program is to evaluate several computer-based classifiers as potential tools for pharmaceutical fingerprinting based on analysis of HPLC trace organic impurity patterns. In the present study, wavelet packets (WPs) are investigated for use as a preprocessor of the chromatographic data taken from commercial samples of L-tryptophan (LT) to extract input data appropriate for classifying the samples according to manufacturer using artificial neural networks (ANNs) and the standard classifiers KNN and SIMCA. Using the Haar function, WP decompositions for levels L = 0-10 were generated for the trace impurity patterns of 253 chromatograms corresponding to LT samples that had been produced by six commercial manufacturers. Input sets of N = 20, 30, 40, and 50 inputs were constructed, each one consisting of the first N/2 WP coefficents and corresponding positions from the overall best level (L = 2). The number of hidden nodes in the ANNs was also varied to optimize performance. Optimal ANN performance based on percent correct classifications of test set data was achieved by ANN-30-30-6 (97%) and ANN-20-10-6 (94%), where the integers refer to the numbers of input, hidden, and output nodes, respectively. This performance equals or exceeds that obtained previously (Welsh, W.J.; et al.Anal.Chem. 1996, 68, 3473) using 46 inputs from a so-called Window preprocessor (93%). KNN performance with 20 inputs (97%) or 30 inputs (90%) from the WP preprocessor also exceeded that obtained from the Window preprocessor (85%), while SIMCA performance with 20 inputs (86%) or 30 inputs (82%) from the WP preprocessor was slightly inferior to that obtained from the Window preprocessor (87%). These results indicate that, at least for the ANN and KNN classifiers considered here, the WP preprocessor can yield superior performance and with fewer inputs compared to the Window preprocessor.