Megavariate analysis of hierarchical QSAR data

1H-Nuclear Magnetic Resonance Analysis of Urine as Diagnostic Tool for Organic Acidemias and Aminoacidopathies

The utility of low-resolution 1H-NMR analysis for the identification of biomarkers provided evidence for rapid biochemical diagnoses of organic acidemia and aminoacidopathy. 1H-NMR, with a sensitivity expected for a field strength of 400 MHz at 64 scans was used to establish the metabolomic urine sample profiles of an infant population diagnosed with small molecule Inborn Errors of Metabolism (smIEM) compared to unaffected individuals. A qualitative differentiation of the 1H-NMR spectral profiles of urine samples obtained from individuals affected by different organic acidemias and aminoacidopathies was achieved in combination with GC-MS. The smIEM disorders investigated in this study included phenylalanine metabolism; isovaleric, propionic, 3-methylglutaconicm and glutaric type I acidemia; and deficiencies in medium chain acyl-coenzyme and holocarboxylase synthase. The observed metabolites were comparable and similar to those reported in the literature, as well as to those detected with higher-resolution NMR. In this study, diagnostic marker metabolites were identified for the smIEM disorders. In some cases, changes in metabolite profiles differentiated post-treatments and follow-ups while allowing for the establishment of different clinical states of a biochemical disorder. In addition, for the first time, a 1H-NMR-based biomarker profile was established for holocarboxylase synthase deficiency spectrum.

EBC metabolomics for asthma severity

Asthma is a heterogeneous disease with diverse severity and represents a considerable socio-economic burden. Exhaled Breath Condensate (EBC) is a biofluid directly obtained from the airway lining fluid non-invasively. We attempted to discriminate severe from mild-to-moderate asthma using EBC metabolomics based on both NMR and UHPLC-MS techniques. 36 patients were included in this study (15 patients with severe and 21 with mild-to-moderate asthma). EBC was collected and analyzed using both NMR and UHPLC-MS techniques for possible metabolites. Using PLS and oPLS analysis for the UHPLC-MS data, no metabolite was found to be sufficient for the discrimination of asthma severity. However, when another PLS-regression model was applied five metabolites were found to discriminate severe from mild-to-moderate asthma. Amino-acid lysine was the only metabolite that discriminated the two study groups using NMR data (p= 0.04, t-test with Welch's correction, AUC 0.66). EBC is an easily available biofluid which directly represents the lower airways but difficult-to-use for metabolomic analysis. Our study presents some encouraging findings for the discrimination of asthma severity subgroups using EBC metabolomics but more well-designed studies with a higher number of patients need to be conducted.

Metabolomics Studies on Cytoplasmic Male Sterility during Flower Bud Development in Soybean

Abnormal reactive oxygen species (ROS) may mediate cytoplasmic male sterility (CMS). To observe the effect of ROS on soybean CMS, metabolite content and antioxidant enzyme activity in the flower buds between soybean N8855-derived CMS line and its maintainer were compared. Of the 612 metabolites identified, a total of 74 metabolites were significantly differentiated in flower buds between CMS line and its maintainer. The differential metabolites involved 32 differential flavonoids, 13 differential phenolamides, and 1 differential oxidized glutathione (GSSG) belonging to a non-enzymatic ROS scavenging system. We observed lower levels of flavonoids and antioxidant enzyme activities in flower buds of the CMS line than in its maintainer. Our results suggest that deficiencies of enzymatic and non-enzymatic ROS scavenging systems in soybean CMS line cannot eliminate ROS in anthers effectively, excessive accumulation of ROS triggered programmed cell death and ultimately resulted in pollen abortion of soybean CMS line.

Chemometric-assisted method development in hydrophilic interaction liquid chromatography: A review

With an enormous growth in the application of hydrophilic interaction liquid chromatography (HILIC), there has also been significant progress in HILIC method development. HILIC is a chromatographic method that utilises hydro-organic mobile phases with a high organic content, and a hydrophilic stationary phase. It has been applied predominantly in the determination of small polar compounds. Theoretical studies in computer-aided modelling tools, most importantly the predictive, quantitative structure retention relationship (QSRR) modelling methods, have attracted the attention of researchers and these approaches greatly assist the method development process. This review focuses on the application of computer-aided modelling tools in understanding the retention mechanism, the classification of HILIC stationary phases, prediction of retention times in HILIC systems, optimisation of chromatographic conditions, and description of the interaction effects of the chromatographic factors in HILIC separations. Additionally, what has been achieved in the potential application of QSRR methodology in combination with experimental design philosophy in the optimisation of chromatographic separation conditions in the HILIC method development process is communicated. Developing robust predictive QSRR models will undoubtedly facilitate more application of this chromatographic mode in a broader variety of research areas, significantly minimising cost and time of the experimental work.

Metabolic profiling of hepatitis B virus-related hepatocellular carcinoma with diverse differentiation grades

The most effective diagnostic tool for the majority of hepatocellular carcinoma (HCC) patients is determining the differentiation grade of their tumors. However liver biopsies, which are currently the most effective way of determining tumor differentiation grade, have several limitations. The present study was designed to select serum characteristic metabolites that correlate with the differentiation grades of hepatitis B virus (HBV)-related HCC, and so could be used in the clinic as a non-invasive method of differentiating patients with different grades of HCC. A total of 58 patients with HBV-related HCC were included in the present study, and divided into three groups according to their tumor differentiation grade. A further 20 patients with HBV-related liver cirrhosis and 19 healthy volunteers were enrolled. Ultra-performance liquid chromatography-mass spectrometry was used to analyze endogenous metabolites. Multivariate statistical analysis was used to examine the data using MZmine 2.0 software. The 14 metabolites that were highly correlated with specific differentiation grades of HCC were then selected for additional study. Receiver operator characteristic curve analysis was used to evaluate their clinical value. In total, 5 metabolites were finally identified, including lysophosphatidylcholine (16:0), oleamide, monoglyceride (0:0/15:0/0:0), lysophosphatidylcholine (18:0) and lysophosphatidylcholine [22:5(7Z,10Z,13Z,16Z,19Z)]. All these metabolites exhibited an excellent ability to distinguish different types of HCC with various differentiation grades and the area under the curve of these metabolites was up to 0.942, showing promising clinical value.

Lipidomic Signature of Progression of Chronic Kidney Disease in the Chronic Renal Insufficiency Cohort

Introduction

Human studies report conflicting results on the predictive power of serum lipids on the progression of chronic kidney disease. We aimed to systematically identify the lipids that predict progression to end-stage kidney disease.

Methods

From the Chronic Renal Insufficiency Cohort, 79 patients with chronic kidney disease stages 2 to 3 who progressed to end-stage kidney disease over 6 years of follow-up were selected and frequency matched by age, sex, race, and diabetes with 121 nonprogressors with less than 25% decline in estimated glomerular filtration rate during the follow-up. The patients were randomly divided into training and test sets. We applied liquid chromatography-mass spectrometry-based lipidomics on visit year 1 samples.

Results

We identified 510 lipids, of which the top 10 coincided with false discovery threshold of 0.058 in the training set. From the top 10 lipids, the abundance of diacylglycerols and cholesteryl esters was lower, but that of phosphatidic acid 44:4 and monoacylglycerol 16:0 was significantly higher in progressors. Using logistic regression models, a multimarker panel consisting of diacylglycerols and monoacylglycerol independently predicted progression. The c-statistic of the multimarker panel added to the base model consisting of estimated glomerular filtration rate and urine protein-to-creatinine ratio as compared with that of the base model was 0.92 (95% confidence interval: 0.88–0.97) and 0.83 (95% confidence interval: 0.76–0.90, P < 0.01), respectively, an observation that was validated in the test subset.

Discussion

We conclude that a distinct panel of lipids may improve prediction of progression of chronic kidney disease beyond estimated glomerular filtration rate and urine protein-to-creatinine ratio when added to the base model.

Predictive modeling of chemical toxicity towards Pseudokirchneriella subcapitata using regression and classification based approaches

Biodiversity nurturing may be a valuable pathway in controlling chemical stress on the ecosystem. In the present work, in silico studies have been performed to develop regression based quantitative structure toxicity relationship (QSTR) models using a data set containing 105 organic chemicals for the prediction of 48-h chemical toxicity towards Pseudokirchneriella subcapitata. Classification based linear discriminant analysis (LDA) was also performed to distinguish chemicals into toxic and nontoxic groups using the same data set. The developed models were found to possess good predictive quality in terms of internal, external and overall validation parameters. The regression based QSTR model suggests that second order molecular connectivity index (molecular size and lipophilicity), density (aromaticity), relative shape of molecules (cyclicity/aromaticity), and specific molecular fragments of the chemicals are important properties of chemicals to exert their toxicity on P. subcapitata. The classification based LDA QSTR model suggested that fused ring aromatic systems, secondary carbon atom fragments, second order valence molecular connectivity indices (molecular size and branching) and molecular weight are the distinguishing features to differentiate chemicals into toxic and nontoxic groups.

Environmental toxicological fate prediction of diverse organic chemicals based on steady-state compartmental chemical mass ratio using quantitative structure-fate relationship (QSFR) models

Four quantitative prediction models for steady-state compartmental chemical mass concentrations (Wn,g) were obtained from structural information, physiochemical properties, degradation rate and transport coefficients of 455 diverse organic chemicals using chemometric tools in a quantitative structure-fate relationship (QSFR) study. The mass ratio assessment of environmentally prevalent organic chemicals may be helpful to predict their toxicological fate in the ecosystems. Four sets of mass ratios [(1) log(Wair) from water emissions (water to air compartment), (2) log(Wair) from air emissions (within different zones of the air compartment), (3) log(Wwater) from water emissions (within different zones of the water compartment) and (4) log(Wwater) from air emissions (air to water compartment)] have been used. The developed models using genetic function approximation followed by multiple linear regression (GFA-MLR) and subsequent partial least squares (PLS) treatment identify only four descriptors for log(Wair) from water emission, six descriptors for log(Wair) from air emission, five descriptors for log(Wwater) from water emission and seven descriptors for log(Wwater) from air emission for predicting efficiently a large number of test set chemicals (ntest=182). The conclusive models suggest that descriptors such as partition coefficients (Kaw, Kow and Ksw), degradation parameters (Ksoil,Kwater and Kair), vapor pressure (Pv), diffusivity (Dwater), spatial descriptors (Jurs-WNSA-1, Jurs-WNSA-2, Jurs-WPSA-3, Jurs-FNSA-3 and Density), thermodynamic descriptors (MolRef and AlogP98), electrotopological state indices (S_dsN, S_ssNH and S_dsCH) are important for predicting the chemical mass ratios. The developed models may be applicable in toxicological fate prediction of diverse chemicals in the ecosystems.

Current technological challenges in biomarker discovery and validation

In this review we will give an overview of the issues related to biomarker discovery studies with a focus on liquid chromatography-mass spectrometry (LC-MS) methods. Biomarker discovery is based on a close collaboration between clinicians, analytical scientists and chemometritians/statisticians. It is critical to define the final purpose of a biomarker or biomarker pattern at the onset of the study and to select case and control samples accordingly. This is followed by designing the experiment, starting with the sampling strategy, sample collection, storage and separation protocols, choice and validation of the quantitative profiling platform followed by data processing, statistical analysis and validation workflows. Biomarker candidates that result after statistical validation should be submitted for further validation and, ideally, be connected to the disease mechanism after their identification. Since most discovery studies work with a relatively small number of samples, it is necessary to assess the specificity and sensitivity of a given biomarker-based assay in a larger set of independent samples, preferably analyzed at another clinical center. Targeted analytical methods of higher throughput than the original discovery method are needed at this point and LC-tandem mass spectrometry is gaining acceptance in this field. Throughout this review, we will focus on possible sources of variance and how they can be assessed and reduced in order to avoid false positives and to reduce the number of false negatives in biomarker discovery research.

Predicting cell-penetrating peptides

Possibility to predict short peptide sequences capable to penetrate the plasma membrane opens new opportunities for developing peptide based intracellular delivery vectors, called cell-penetrating peptides (CPPs). Predictions of CPPs, however are often based on trial and error and may not always lead to new potent sequences. In this review we discuss different problems associated with CPP prediction. Additionally, the used methods of CPP prediction are compared. Also, a few suggestions are made for designing new CPP sequences and improvement of predictions.

QSAR models for the human H(+)/peptide symporter, hPEPT1: affinity prediction using alignment-independent descriptors

A data set comprising the major known chemical classes of hPEPT1 ligands was compiled from the literature. For these compounds, alignment-independent descriptors (VolSurf, GRIND/Almond, and MOE) were computed. Using hierarchical partial least-squares projection to latent structures (H-PLS), a one-component model with r2 = 0.77 and q2 = 0.75 was obtained. The model satisfied a set of rigorous validation criteria and performed well in the prediction of an external test set. Mechanistic interpretation of the model reveals polarity properties to be the dominant factors in determining hPEPT1 affinity, with hydrophobic interactions contributing to a lesser extent. The model is superior to previously reported models due to its combination of quality and speed. Accordingly, it is suitable for ligand-based virtual screening, such as QSAR-based database mining.

Inhibitors of type III secretion in Yersinia: Design, synthesis and multivariate QSAR of 2-arylsulfonylamino-benzanilides

Compound 1, 2-(benzo[1,2,5]thiadiazole-4-sulfonylamino)-5-chloro-N-(3,4-dichloro-phenyl)-benzamide, was identified as a putative type III secretion inhibitor in Yersinia, and the compound thus has a potential to be used to prevent or treat bacterial infections. A set of seven analogues was synthesized and evaluated in a type III secretion dependent reporter-gene assay with viable bacterial to give basic SAR. A second set of 19 compounds was obtained by statistical molecular design in the building block and product space and by subsequent synthesis. Evaluation in the reporter-gene assay showed that the compounds ranged from non-active to compounds more potent than 1. Based on the data multivariate QSAR models were established and the final Hi-PLS model showed good correlation between experimentally determined % inhibition and the calculated % inhibition of the reporter-gene signal.

Development, interpretation and temporal evaluation of a global QSAR of hERG electrophysiology screening data

A 'global' model of hERG K(+) channel was built to satisfy three basic criteria for QSAR models in drug discovery: (1) assessment of the applicability domain, (2) assuring that model decisions can be interpreted by medicinal chemists and (3) assessment of model performance after the model was built. A combination of D-optimal onion design and hierarchical partial least squares modelling was applied to construct a global model of hERG blockade in order to maximize the applicability domain of the model and to enhance its interpretability. Additionally, easily interpretable hERG specific fragment-based descriptors were developed. Model performance was monitored, throughout a time period of 15 months, after model implementation. It was found that after this time duration a greater proportion of molecules were outside the model's applicability domain and that these compounds had a markedly higher average prediction error than those from molecules within the model's applicability domain. The model's predictive performance deteriorated within 4 months after building, illustrating the necessity of regular updating of global models within a drug discovery environment.

Gene expression in acute Stanford type A dissection: a comparative microarray study

Background

We compared gene expression profiles in acutely dissected aorta with those in normal control aorta.

Materials and methods

Ascending aorta specimen from patients with an acute Stanford A-dissection were taken during surgery and compared with those from normal ascending aorta from multiorgan donors using the BD Atlas™ Human1.2 Array I, BD Atlas™ Human Cardiovascular Array and the Affymetrix HG-U133A GeneChip^®. For analysis only genes with strong signals of more than 70 percent of the mean signal of all spots on the array were accepted as being expressed. Quantitative real-time polymerase chain reaction (RT-PCR) was used to confirm regulation of expression of a subset of 24 genes known to be involved in aortic structure and function.

Results

According to our definition expression profiling of aorta tissue specimens revealed an expression of 19.1% to 23.5% of the genes listed on the arrays. Of those 15.7% to 28.9% were differently expressed in dissected and control aorta specimens. Several genes that encode for extracellular matrix components such as collagen IV α2 and -α5, collagen VI α3, collagen XIV α1, collagen XVIII α1 and elastin were down-regulated in aortic dissection, whereas levels of matrix metalloproteinases-11, -14 and -19 were increased. Some genes coding for cell to cell adhesion, cell to matrix signaling (e.g., polycystin1 and -2), cytoskeleton, as well as several myofibrillar genes (e.g., α-actinin, tropomyosin, gelsolin) were found to be down-regulated. Not surprisingly, some genes associated with chronic inflammation such as interleukin -2, -6 and -8, were up-regulated in dissection.

Conclusion

Our results demonstrate the complexity of the dissecting process on a molecular level. Genes coding for the integrity and strength of the aortic wall were down-regulated whereas components of inflammatory response were up-regulated. Altered patterns of gene expression indicate a pre-existing structural failure, which is probably a consequence of insufficient remodeling of the aortic wall resulting in further aortic dissection.

Megavariate Analysis of Environmental QSAR Data. Part II – Investigating Very Complex Problem Formulations Using Hierarchical, Non-Linear and Batch-Wise Extensions of PCA and PLS

Three extensions of the basic PCA and PLS methodologies are described. These extensions are hierarchical, non-linear and batch-based in nature. The objectives of these methods are to assist in problem understanding and problem solving in very complex (QSAR) problem formulations. The method extensions are illustrated using two example QSAR data sets containing many X- and Y-variables.

Substrate specificity of lipases in alkoxycarbonylation reaction: QSAR model development and experimental validation

Although lipases are known to catalyze alkoxycarbonylation reactions in organic solvents, the existing knowledge base on their substrate specificity in alkoxycarbonylation reaction is sparse. Moreover, models to predict substrate specificity have not been reported. Here, we report the experimentally measured rate constants for 180 acyl donor-alcohol pairs and demonstrate the two-step synthesis of over 70 disubstituted carbonate products from simple precursors such as diphenyl carbonate and alcohols. The efficiency of synthesis was found to be dependent on the order of alcohol addition. This motivated the need to develop a model to predict lipase specificity in alkoxycarbonylation reactions. A partial least square model has been developed to correlate the reaction rate with (i) descriptors of alcohol for a fixed acyl donor, (ii) descriptors of acyl donor for a fixed alcohol, (iii) descriptors of both the acyl donor and the alcohol. The number of descriptors being far greater than the number of observations was a potential limitation in the model development. This was addressed by selecting a subset of descriptors using a systematic procedure based on (a) correlation among the descriptors and step-wise regression methodology, and (b) variable influence on projection methodology. The model was able to accurately predict the reaction rate and the optimal order of addition of alcohols in the two-step synthesis of disubstituted carbonates using the enzyme mixture. The descriptor subset and the relevant model would benefit the users of lipases in synthetic applications while the modeling strategy presented here can have applications in predicting specificity of other enzymes.

Megavariate analysis of environmental QSAR data. Part I – A basic framework founded on principal component analysis (PCA), partial least squares (PLS), and statistical molecular design (SMD)

This paper introduces principal component analysis (PCA), partial least squares projections to latent structures (PLS), and statistical molecular design (SMD) as useful tools in deriving multi- and megavariate quantitative structure-activity relationship (QSAR) models. Two QSAR data sets from the fields of environmental toxicology and environmental chemistry are worked out in detail, showing the benefits of PCA, PLS and SMD. PCA is useful when overviewing a data set and exploring relationships among compounds and relationships among variables. PLS is the regression extension of PCA and is used for establishing QSARs. SMD is essential for selecting informative training and test sets of compounds for QSAR calibration and validation.

Hierarchical PLS Modeling for Predicting the Binding of a Comprehensive Set of Structurally Diverse Protein−Ligand Complexes

A new approach is presented for predicting ligand binding to proteins using hierarchical partial-least-squares regression to latent structures (Hi-PLS). Models were based on information from the 2002 release of the PDBbind database containing (after in-house refinement) high-resolution X-ray crystallography and binding affinity (Kd or Ki) data for 612 protein-ligand complexes. The complexes were characterized by four different descriptor blocks: three-dimensional (3D) structural descriptors of the proteins, protein-ligand interactions according to the Validate scoring function, binding site surface areas, and ligand 2D and 3D descriptors. These descriptor blocks were used in Hi-PLS models, generated using both linear and nonlinear terms, to relate the characterizations to pKd/i. The results show that each of the four descriptor blocks contributed to the model, and the predictions of pKd/i of the internal test set gave a root-mean-square error of prediction (RMSEP) of 1.65. The data were further divided according to the structural classification of the proteins, and Hi-PLS models were constructed for the resulting subclasses. The models for the four subclasses differed considerably in terms of both their ability to predict pKd/i (with RMSEPs ranging from 0.8 to 1.56) and the descriptor block that had the strongest influence. The models were validated with an external test set of 174 complexes from the 2003 release of the PDBbind database. The overall results show that the presented Hi-PLS methodology could facilitate the difficult task of predicting binding affinity.

Multivariate modeling of cytochrome P450 3A4 inhibition

In the early phases of current pharmaceutical research projects, huge numbers of compounds are tested on their biological activity with respect to a certain target by experimental or virtual screening campaigns. To reduce the attrition rate in later stages of a project, other relevant properties such as physicochemical and ADMET (absorption, distribution, metabolism, excretion, toxicity) properties should be assessed as early as possible in lead discovery and optimization. The present study describes the development of in silico models to predict the inhibition of human cytochrome P450 3A4 (CYP3A4) from calculated molecular descriptors. The models were trained and validated using a set of 967 structural diverse drug-like research compounds with an experimentally determined CYP3A4 inhibition potency (IC50 value) which was carefully split into a training and a test set. For classification models, the data sets were further subdivided into strong, medium, and weak inhibitors. Different descriptor sets were used to cover various aspects of molecular properties, including properties derived from the 2D structure, the interaction of the molecule with its environment, and properties derived from quantum-mechanical calculations. The descriptors were related to the CYP3A4 inhibition potency by multivariate data analysis methods such as partial least-squares projection to latent structures (PLS), PLS discriminant analysis (PLS-DA), and soft independent class modeling (SIMCA). The squared correlation between experimental and predicted IC50 values of the previously unseen test set compounds was Qext2=0.6 for the best PLS models, corresponding to a root mean squared error (RMSE) of RMSE=0.45 (logarithm of IC50). The best PLS-DA models were able to correctly classify more than 60% of the test set compounds, whereas almost no strong inhibitors were wrongly classified as weak inhibitors and vice versa. Furthermore, relevant molecular properties were identified which are closely related to the CYP3A4 inhibition potency of a compound. The results presented here are very encouraging since our models could, for instance, serve to flag problematic compounds or to guide further synthesis efforts.

A support vector machine approach to classify human cytochrome P450 3A4 inhibitors

The cytochrome P450 (CYP) enzyme superfamily plays a major role in the metabolism of commercially available drugs. Inhibition of these enzymes by a drug may result in a plasma level increase of another drug, thus leading to unwanted drug-drug interactions when two or more drugs are coadministered. Therefore, fast and reliable in silico methods predicting CYP inhibition from calculated molecular properties are an important tool which can be applied to assess both already synthesized as well as virtual compounds. We have studied the performance of support vector machines (SVMs) to classify compounds according to their potency to inhibit CYP3A4. The data set for model generation consists of more than 1300 structural diverse drug-like research molecules which were divided into training and test sets. The predictive power of SVMs crucially depends on a careful selection of parameters specifying the kernel function and the penalty for misclassifications. In this study we have investigated a procedure to identify a valid set of SVM parameters which is based on a sampling of the parameter space on a regular grid. From this set of parameters, either single SVMs or SVM committees were trained to distinguish between strong and weak inhibitors or to achieve a more realistic three-class assignment, with one class representing medium inhibitors. This workflow was studied for several kernel functions and descriptor sets. All SVM models performed significantly better than PLS-DA models which were generated from the corresponding descriptor sets. As a very promising result, simple two-dimensional (2D) descriptors yield a three-class model which correctly classifies more than 70% of the test set. Our work illustrates that SVMs used in combination with simple 2D descriptors provide a very effective and reliable tool which allows a fast assessment of CYP3A4 inhibition potency in an early in silico filtering process.

Immediate Gene Expression Changes After the First Course of Neoadjuvant Chemotherapy in Patients with Primary Breast Cancer Disease

PURPOSE

Our goal was to identify genes undergoing expressional changes shortly after the beginning of neoadjuvant chemotherapy for primary breast cancer.

EXPERIMENTAL DESIGN

The biopsies were taken from patients with primary breast cancer prior to any treatment and 24 hours after the beginning of the neoadjuvant chemotherapy. Expression analyses from matched pair samples representing 25 patients were carried out with Clontech filter arrays. A subcohort of those 25 paired samples were additionally analyzed with the Affymetrix GeneChip platform. All of the transcripts from both platforms were queried for expressional changes.

RESULTS

Performing hierarchical cluster analysis, we clustered pre- and posttreatment samples from individual patients more closely to each other than the samples taken from different patients. This reflects the rather low number of transcripts responding directly to the drugs used. Although transcriptional drug response occurring during therapy differed between individual patients, two genes (p21(WAF1/CIP1) and MIC-1) were up-regulated in posttreatment samples. This could be validated by semiquantitative and real-time reverse transcription-PCR. Partial least- discriminant analysis based on approximately 25 genes independently identified by either Clontech or Affymetrix platforms could clearly discriminate pre- and posttreatment samples. However, correlation of certain gene expression levels as well as of differential patterns and clusters as determined by a different platform was not always satisfying.

CONCLUSIONS

This study has demonstrated the potential of monitoring posttreatment changes in gene expression as a measure of the pharmacodynamics of drugs. As a clinical laboratory model, it can be useful to identify patients with sensitive and reactive tumors and to help for optimized choice for sequential therapy and obviously improve relapse- free and overall survival.

Using chemometrics for navigating in the large data sets of genomics, proteomics, and metabonomics (gpm)

This article describes the applicability of multivariate projection techniques, such as principal-component analysis (PCA) and partial least-squares (PLS) projections to latent structures, to the large-volume high-density data structures obtained within genomics, proteomics, and metabonomics. PCA and PLS, and their extensions, derive their usefulness from their ability to analyze data with many, noisy, collinear, and even incomplete variables in both X and Y. Three examples are used as illustrations: the first example is a genomics data set and involves modeling of microarray data of cell cycle-regulated genes in the microorganism Saccharomyces cerevisiae. The second example contains NMR-metabonomics data, measured on urine samples of male rats treated with either of the drugs chloroquine or amiodarone. The third and last data set describes sequence-function classification studies in a set of G-protein-coupled receptors using hierarchical PCA.

Applying data mining techniques to library design, lead generation and lead optimization

Many data mining techniques have been applied to activity and ADMET datasets and the resulting models are being used to understand quantitative structure-activity relationships and design new libraries. This review summarizes data mining concepts and discuss their application to library design, lead generation (particularly for sequential screening) and lead optimization (specifically for generating and interpreting QSAR models). Also, this review discusses recent comparative studies between data mining techniques and draws some conclusions about the patterns emerging in the drug discovery data mining field.

Methods for reliability and uncertainty assessment and for applicability evaluations of classification- and regression-based QSARs

This article provides an overview of methods for reliability assessment of quantitative structure-activity relationship (QSAR) models in the context of regulatory acceptance of human health and environmental QSARs. Useful diagnostic tools and data analytical approaches are highlighted and exemplified. Particular emphasis is given to the question of how to define the applicability borders of a QSAR and how to estimate parameter and prediction uncertainty. The article ends with a discussion regarding QSAR acceptability criteria. This discussion contains a list of recommended acceptability criteria, and we give reference values for important QSAR performance statistics. Finally, we emphasize that rigorous and independent validation of QSARs is an essential step toward their regulatory acceptance and implementation.