¹³C NMR-distance matrix descriptors: optimal abstract 3D space granularity for predicting estrogen binding.

An improved three-dimensional quantitative spectral data-activity relationship (3D-QSDAR) methodology was used to build and validate models relating the activity of 130 estrogen receptor binders to specific structural features. In 3D-QSDAR, each compound is represented by a unique fingerprint constructed from (13)C chemical shift pairs and associated interatomic distances. Grids of different granularity can be used to partition the abstract fingerprint space into congruent "bins" for which the optimal size was previously unexplored. For this purpose, the endocrine disruptor knowledge base data were used to generate 50 3D-QSDAR models with bins ranging in size from 2 ppm × 2 ppm × 0.5 Å to 20 ppm × 20 ppm × 2.5 Å, each of which was validated using 100 training/test set partitions. Best average predictivity in terms of R(2)test was achieved at 10 ppm ×10 ppm × Z Å (Z = 0.5, ..., 2.5 Å). It was hypothesized that this optimum depends on the chemical shifts' estimation error (±4.13 ppm) and the precision of the calculated interatomic distances. The highest ranked bins from partial least-squares weights were found to be associated with structural features known to be essential for binding to the estrogen receptor.

Modeling chemical interaction profiles: I. Spectral data-activity relationship and structure-activity relationship models for inhibitors and non-inhibitors of cytochrome P450 CYP3A4 and CYP2D6 isozymes.

An interagency collaboration was established to model chemical interactions that may cause adverse health effects when an exposure to a mixture of chemicals occurs. Many of these chemicals--drugs, pesticides, and environmental pollutants--interact at the level of metabolic biotransformations mediated by cytochrome P450 (CYP) enzymes. In the present work, spectral data-activity relationship (SDAR) and structure-activity relationship (SAR) approaches were used to develop machine-learning classifiers of inhibitors and non-inhibitors of the CYP3A4 and CYP2D6 isozymes. The models were built upon 602 reference pharmaceutical compounds whose interactions have been deduced from clinical data, and 100 additional chemicals that were used to evaluate model performance in an external validation (EV) test. SDAR is an innovative modeling approach that relies on discriminant analysis applied to binned nuclear magnetic resonance (NMR) spectral descriptors. In the present work, both 1D ¹³C and 1D ¹5N-NMR spectra were used together in a novel implementation of the SDAR technique. It was found that increasing the binning size of 1D ¹³C-NMR and ¹5N-NMR spectra caused an increase in the tenfold cross-validation (CV) performance in terms of both the rate of correct classification and sensitivity. The results of SDAR modeling were verified using SAR. For SAR modeling, a decision forest approach involving from 6 to 17 Mold2 descriptors in a tree was used. Average rates of correct classification of SDAR and SAR models in a hundred CV tests were 60% and 61% for CYP3A4, and 62% and 70% for CYP2D6, respectively. The rates of correct classification of SDAR and SAR models in the EV test were 73% and 86% for CYP3A4, and 76% and 90% for CYP2D6, respectively. Thus, both SDAR and SAR methods demonstrated a comparable performance in modeling a large set of structurally diverse data. Based on unique NMR structural descriptors, the new SDAR modeling method complements the existing SAR techniques, providing an independent estimator that can increase confidence in a structure-activity assessment. When modeling was applied to hazardous environmental chemicals, it was found that up to 20% of them may be substrates and up to 10% of them may be inhibitors of the CYP3A4 and CYP2D6 isoforms. The developed models provide a rare opportunity for the environmental health branch of the public health service to extrapolate to hazardous chemicals directly from human clinical data. Therefore, the pharmacological and environmental health branches are both expected to benefit from these reported models.

Modeling chemical interaction profiles: II. Molecular docking, spectral data-activity relationship, and structure-activity relationship models for potent and weak inhibitors of cytochrome P450 CYP3A4 isozyme.

Polypharmacy increasingly has become a topic of public health concern, particularly as the U.S. population ages. Drug labels often contain insufficient information to enable the clinician to safely use multiple drugs. Because many of the drugs are bio-transformed by cytochrome P450 (CYP) enzymes, inhibition of CYP activity has long been associated with potentially adverse health effects. In an attempt to reduce the uncertainty pertaining to CYP-mediated drug-drug/chemical interactions, an interagency collaborative group developed a consensus approach to prioritizing information concerning CYP inhibition. The consensus involved computational molecular docking, spectral data-activity relationship (SDAR), and structure-activity relationship (SAR) models that addressed the clinical potency of CYP inhibition. The models were built upon chemicals that were categorized as either potent or weak inhibitors of the CYP3A4 isozyme. The categorization was carried out using information from clinical trials because currently available in vitro high-throughput screening data were not fully representative of the in vivo potency of inhibition. During categorization it was found that compounds, which break the Lipinski rule of five by molecular weight, were about twice more likely to be inhibitors of CYP3A4 compared to those, which obey the rule. Similarly, among inhibitors that break the rule, potent inhibitors were 2-3 times more frequent. The molecular docking classification relied on logistic regression, by which the docking scores from different docking algorithms, CYP3A4 three-dimensional structures, and binding sites on them were combined in a unified probabilistic model. The SDAR models employed a multiple linear regression approach applied to binned 1D ¹³C-NMR and 1D ¹5N-NMR spectral descriptors. Structure-based and physical-chemical descriptors were used as the basis for developing SAR models by the decision forest method. Thirty-three potent inhibitors and 88 weak inhibitors of CYP3A4 were used to train the models. Using these models, a synthetic majority rules consensus classifier was implemented, while the confidence of estimation was assigned following the percent agreement strategy. The classifier was applied to a testing set of 120 inhibitors not included in the development of the models. Five compounds of the test set, including known strong inhibitors dalfopristin and tioconazole, were classified as probable potent inhibitors of CYP3A4. Other known strong inhibitors, such as lopinavir, oltipraz, quercetin, raloxifene, and troglitazone, were among 18 compounds classified as plausible potent inhibitors of CYP3A4. The consensus estimation of inhibition potency is expected to aid in the nomination of pharmaceuticals, dietary supplements, environmental pollutants, and occupational and other chemicals for in-depth evaluation of the CYP3A4 inhibitory activity. It may serve also as an estimate of chemical interactions via CYP3A4 metabolic pharmacokinetic pathways occurring through polypharmacy and nutritional and environmental exposures to chemical mixtures.

Improving proton MR spectroscopy of brain tissue for noninvasive diagnostics.

PURPOSE: To examine preprocessing methods affecting the potential use of Magnetic Resonance Spectroscopy (MRS) as a noninvasive modality for detection and characterization of brain lesions and for directing therapy progress. MATERIALS AND METHODS: Two reference point re-calibration with linear interpolation (to compensate for magnetic field nonhomogeneity), weighting of spectra (to emphasize consistent peaks and depress chemical noise), and modeling based on chemical shift locations of 97 biomarkers were investigated. Results for 139 categorized scans were assessed by comparing Leave-One-Out (LOO) cross-validation and external validation. RESULTS: For distinction of nine brain tissue categories, use of re-calibration, variance weighting, and biomarker modeling improved LOO classification of MRS spectra from 31% to 95%. External validation of the two best nine-category models on 47 unknown samples gave 96% or 100% accuracy, respectively, compared with pathological diagnosis. CONCLUSION: Preprocessing of MRS spectra can significantly improve their diagnostic utility for automated consultation of pattern recognition models. Use of several techniques in combination greatly increases available proton MRS information content. Accurate assignment of unknowns among nine tissue classes represents a significant improvement, for a much more demanding task, than has been previously reported.

Human organ/tissue growth algorithms that include obese individuals and black/white population organ weight similarities from autopsy data.

Physiologically based pharmacokinetic (PBPK) models need the correct organ/tissue weights to match various total body weights in order to be applied to children and the obese individual. Baseline data from Reference Man for the growth of human organs (adrenals, brain, heart, kidneys, liver, lungs, pancreas, spleen, thymus, and thyroid) were augmented with autopsy data to extend the describing polynomials to include the morbidly obese individual (up to 250 kg). Additional literature data similarly extends the growth curves for blood volume, muscle, skin, and adipose tissue. Collectively these polynomials were used to calculate blood/organ/tissue weights for males and females from birth to 250 kg, which can be directly used to help parameterize PBPK models. In contrast to other black/white anthropomorphic measurements, the data demonstrated no observable or statistical difference in weights for any organ/tissue between individuals identified as black or white in the autopsy reports.

Windows based general PBPK/PD modeling software.

A physiologically based pharmacokinetic (PBPK) model and program (called PostNatal) was developed which focuses on postnatal growth. Algorithms defining organ/tissue growth curves from birth through adulthood for male and female humans, dogs, rats, and mice are utilized to calculate the appropriate weight and blood flow for the internal organs/tissues. This Windows based program is actually four linked PBPK models with each PBPK model acting independently or totally integrated with the others through metabolism by first order or Michaelis-Menten kinetics. Data fitting is accomplished by a weighted least square regression algorithm. The model includes linkages for the simulation of pharmacodynamic (PD) effects.

Postnatal growth considerations for PBPK modeling.

A physiologically based pharmacokinetic (PBPK) model and Windows-based program (called PostNatal) was developed that focuses on postnatal growth, from birth through adulthood, using appropriate growth curves for each species and gender. Postnatal growth algorithms relating organs/tissues weights with total body weight for male and female humans, dogs, rats, and mice are an integral part of the software and are utilized to assign the appropriate weight and blood flow for each of 22 organs/tissues for each simulation. Upper limits of body weight were chosen that reflect the available data used to define the algorithms; above these limits a set percent body weight was assigned to all organs/tissues.

Complementary PLS and KNN algorithms for improved 3D-QSDAR consensus modeling of AhR binding.

Multiple validation techniques (Y-scrambling, complete training/test set randomization, determination of the dependence of R2test on the number of randomization cycles, etc.) aimed to improve the reliability of the modeling process were utilized and their effect on the statistical parameters of the models was evaluated. A consensus partial least squares (PLS)-similarity based k-nearest neighbors (KNN) model utilizing 3D-SDAR (three dimensional spectral data-activity relationship) fingerprint descriptors for prediction of the log(1/EC50) values of a dataset of 94 aryl hydrocarbon receptor binders was developed. This consensus model was constructed from a PLS model utilizing 10 ppm x 10 ppm x 0.5 Å bins and 7 latent variables (R2test of 0.617), and a KNN model using 2 ppm x 2 ppm x 0.5 Å bins and 6 neighbors (R2test of 0.622). Compared to individual models, improvement in predictive performance of approximately 10.5% (R2test of 0.685) was observed. Further experiments indicated that this improvement is likely an outcome of the complementarity of the information contained in 3D-SDAR matrices of different granularity. For similarly sized data sets of Aryl hydrocarbon (AhR) binders the consensus KNN and PLS models compare favorably to earlier reports. The ability of 3D-QSDAR (three dimensional quantitative spectral data-activity relationship) to provide structural interpretation was illustrated by a projection of the most frequently occurring bins on the standard coordinate space, thus allowing identification of structural features related to toxicity.

A model-free ensemble method for class prediction with application to biomedical decision making.

OBJECTIVE: A classification algorithm that utilizes two-dimensional convex hulls of training-set samples is presented. METHODS AND MATERIAL: For each pair of predictor variables, separate convex hulls of positive and negative samples in the training set are formed, and these convex hulls are used to classify test points according to a nearest-neighbor criterion. An ensemble of these two-dimensional convex-hull classifiers is formed by trimming the (m)C(2) possible classifiers derived from the m predictors to a set of classifiers comprised of only unique predictor variables. Because only two-dimensional spaces are required to be populated by training-set samples, the "curse of dimensionality" is not an issue. At the same time, the power of ensemble voting is exploited by combining the classifications of the unique two-dimensional classifiers to reach a final classification. RESULTS: The algorithm is illustrated by application to three publicly available biomedical data sets with genomic predictors and is shown to have prediction accuracy that is competitive with a number of published classification procedures. CONCLUSION: Because of its superior performance in terms of sensitivity and negative predictive value compared to its competitors, the convex-hull ensemble classifier demonstrates good potential for medical screening, where often the major emphasis is placed on having reliable negative predictions.