Quantitative structure-activity relationship modeling of dopamine D(1) antagonists using comparative molecular field analysis, genetic algorithms-partial least-squares, and K nearest neighbor methods

[2 + 3] Annulative Coupling of Tetrahydroisoquinolines with Aryliodonio diazo compounds To Access 1,2,4-Triazolo[3,4-a]isoquinolines

Base promoted one-pot annulative coupling of 1,2,3,4-tetrahydroisoquinolines (THIQs) with hypervalent iodine(III) species aryliodonio diazo compounds has been devised for the direct construction of 1,2,4-triazolo[3,4-a]isoquinoline derivatives at room temperature in open air for the first time. This approach involves [2 + 3] cascade annulation of nucleophilic THIQ with an electrophilic aryliodonio diazo compound via N-H and α-C1(sp³)-H difunctionalization of THIQ.

Discovery of Natural Product-Derived 5-HT1A Receptor Binders by Cheminfomatics Modeling of Known Binders, High Throughput Screening and Experimental Validation

The human 5-hydroxytryptamine receptor subtype 1A (5-HT1A) is highly expressed in the raphe nuclei region and limbic structures; for that reason 5-HT1A has served as a promising target for treating human mood disorders and neurodegenerative diseases. We have developed binary quantitative structure-activity relationship (QSAR) models for 5- HT1A binding using data retrieved from the WOMBAT database and the k-Nearest Neighbor (kNN) machine learning method. A rigorous QSAR modeling and screening workflow had been followed, with extensive internal and external validation processes. The models' classification accuracies to discriminate 5-HT1A binders from the non-binders are as high as 96% for the external validation. These models were employed further to mine two major natural products screening libraries, i.e. TimTec Natural Product Library (NPL) and Natural Derivatives Library (NDL). In the end five screening hits were tested by radioligand binding assays with a success rate of 40%, and two Library compounds were confirmed to be binders at the μM concentration against the human 5-HT1A receptor. The combined application of rigorous QSAR modeling and model-based virtual screening presents a powerful means for profiling natural products compounds with important biomedical activities.

Diastereoselective synthesis of substituted hexahydrobenzo[de]isochromanes and evaluation of their antileishmanial activity

Hexahydrobenzo[de]isochromanes and hexahydropyrano[3,4,5-ij]isoquinolines can be efficiently synthesized via Friedel Crafts and oxa Pictet-Spengler reaction of acrylyl enol ethers mediated by triflic acid in good yields. The reaction is highly stereoselective. Two of the hexahydrobenzo[de]isochromanes are found to have moderate antileishmanial activity.

Computational analysis of binding between benzamide-based derivatives and Abl wt and T315I mutant kinases

An integrated computational study was performed to identify the binding mechanisms of benzamide-based derivatives with Abl_wt/Abl_T315I kinases for designing Abl inhibitors.

New therapeutic strategies targeting D1-type dopamine receptors for neuropsychiatric disease

The neurotransmitter dopamine acts via two major classes of receptors, D1-type and D2-type. D1 receptors are highly expressed in the striatum and can also be found in the cerebral cortex. Here we review the role of D1 dopamine signaling in two major domains: L-DOPA-induced dyskinesias in Parkinson's disease and cognition in neuropsychiatric disorders. While there are many drugs targeting D2-type receptors, there are no drugs that specifically target D1 receptors. It has been difficult to use selective D1-receptor agonists for clinical applications due to issues with bioavailability, binding affinity, pharmacological kinetics, and side effects. We propose potential therapies that selectively modulate D1 dopamine signaling by targeting second messengers downstream of D1 receptors, allosteric modulators, or by making targeted modifications to D1-receptor machinery. The development of therapies specific to D1-receptor signaling could be a new frontier in the treatment of neurological and psychiatric disorders.

Application of quantitative structure-activity relationship models of 5-HT1A receptor binding to virtual screening identifies novel and potent 5-HT1A ligands

The 5-hydroxytryptamine 1A (5-HT_1A) serotonin receptor has been an attractive target for treating mood and anxiety disorders such as schizophrenia. We have developed binary classification quantitative structure–activity relationship (QSAR) models of 5-HT_1A receptor binding activity using data retrieved from the PDSP K_i database. The prediction accuracy of these models was estimated by external 5-fold cross-validation as well as using an additional validation set comprising 66 structurally distinct compounds from the World of Molecular Bioactivity database. These validated models were then used to mine three major types of chemical screening libraries, i.e., drug-like libraries, GPCR targeted libraries, and diversity libraries, to identify novel computational hits. The five best hits from each class of libraries were chosen for further experimental testing in radioligand binding assays, and nine of the 15 hits were confirmed to be active experimentally with binding affinity better than 10 μM. The most active compound, Lysergol, from the diversity library showed very high binding affinity (K_i) of 2.3 nM against 5-HT_1A receptor. The novel 5-HT_1A actives identified with the QSAR-based virtual screening approach could be potentially developed as novel anxiolytics or potential antischizophrenic drugs.

Direct sp3 C–H bond arylation, alkylation, and amidation of tetrahydroisoquinolines mediated by hypervalent iodine(iii) under mild conditions

We have developed a method for the sp³ C–H bond functionalization of tetrahydroisoquinolines (THIQs) mediated by [bis(trifluoroacetoxy)iodo]benzene (PIFA).

Simple and direct sp3 C-H bond arylation of tetrahydroisoquinolines and isochromans via 2,3-dichloro-5,6-dicyano-1,4-benzoquinone oxidation under mild conditions

The 2,3-dichloro-5,6-dicyano-1,4-benzoquinone (DDQ)-mediated sp(3) C-H bond arylation of tetrahydroisoquinolines and isochromans is described. The corresponding products were facilely synthesized via a simple nucleophilic addition reaction between readily available aryl Grignard reagents and iminium (or oxonium) cations generated in situ by DDQ oxidation of tetrahydroisoquinolines (or isochromans) under mild conditions.

Application of Machine Leaning in Drug Discovery and Development

Machine learning techniques have been widely used in drug discovery and development, particularly in the areas of cheminformatics, bioinformatics and other types of pharmaceutical research. It has been demonstrated they are suitable for large high dimensional data, and the models built with these methods can be used for robust external predictions. However, various problems and challenges still exist, and new approaches are in great need. In this Chapter, the authors will review the current development of machine learning techniques, and especially focus on several machine learning techniques they developed as well as their application to model building, lead discovery via virtual screening, integration with molecular docking, and prediction of off-target properties. The authors will suggest some potential different avenues to unify different disciplines, such as cheminformatics, bioinformatics and systems biology, for the purpose of developing integrated in silico drug discovery and development approaches.

Quantitative structure-activity relationships and docking studies of calcitonin gene-related peptide antagonists

Defining the role of calcitonin gene-related peptide in migraine pathogenesis could lead to the application of calcitonin gene-related peptide antagonists as novel migraine therapeutics. In this work, quantitative structure-activity relationship modeling of biological activities of a large range of calcitonin gene-related peptide antagonists was performed using a panel of physicochemical descriptors. The computational studies evaluated different variable selection techniques and demonstrated shuffling stepwise multiple linear regression to be superior over genetic algorithm-multiple linear regression. The linear quantitative structure-activity relationship model revealed better statistical parameters of cross-validation in comparison with the non-linear support vector regression technique. Implementing only five peptide descriptors into this linear quantitative structure-activity relationship model resulted in an extremely robust and highly predictive model with calibration, leave-one-out and leave-20-out validation R(2) of 0.9194, 0.9103, and 0.9214, respectively. We performed docking of the most potent calcitonin gene-related peptide antagonists with the calcitonin gene-related peptide receptor and demonstrated that peptide antagonists act by blocking access to the peptide-binding cleft. We also demonstrated the direct contact of residues 28-37 of the calcitonin gene-related peptide antagonists with the receptor. These results are in agreement with the conclusions drawn from the quantitative structure-activity relationship model, indicating that both electrostatic and steric factors should be taken into account when designing novel calcitonin gene-related peptide antagonists.

A gallium-catalyzed cycloisomerization/Friedel-Crafts tandem

Under noble (Au, Pt, Ru) and group 13 (Ga, In) metals catalysis, 1,6-arenynes rearrange to give 1,2-dihydronaphthalenes in a high yielding, regiocontrolled fashion. When the reaction is carried out in the presence of electron-rich arenes (anisole, phenol, indole derivatives), Friedel-Crafts addition may follow the cycloisomerization step. Only GaX(3) salts proved able to catalyze these two C-C bond formation events. This specificity of gallium has been exploited for the synthesis of valuable polycyclic compounds that would be very difficult to prepare otherwise. For instance, tetrahydroisoquinolines and tetrahydrobenzoazepines have been obtained by selective 6-exo-dig or 7-endo-dig cyclization of N-tethered 1,6-arenynes. DFT calculations were carried out to shed light on the mechanism and provide a rationale for this regiodivergency. Computations also reveal the fundamental role of the tether in the stabilization of carbocationic species. Differential reactivities of other types of substrates in gallium- and gold-catalyzed cascades are also exposed, showing that the two approaches are complementary. In particular, bimolecular Friedel-Crafts additions are facilitated under gallium catalysis.

Additivity in the analysis and design of HIV protease inhibitors

We explore the applicability of an additive treatment of substituent effects to the analysis and design of HIV protease inhibitors. Affinity data for a set of inhibitors with a common chemical framework were analyzed to provide estimates of the free energy contribution of each chemical substituent. These estimates were then used to design new inhibitors whose high affinities were confirmed by synthesis and experimental testing. Derivations of additive models by least-squares and ridge-regression methods were found to yield statistically similar results. The additivity approach was also compared with standard molecular descriptor-based QSAR; the latter was not found to provide superior predictions. Crystallographic studies of HIV protease-inhibitor complexes help explain the perhaps surprisingly high degree of substituent additivity in this system, and allow some of the additivity coefficients to be rationalized on a structural basis.

Novel computational models for predicting dopamine interactions

Dopamine is a crucial neurotransmitter responsible for functioning and maintenance of the nervous system. Dopamine has also been implicated in a number of diseases including schizophrenia, Parkinson's disease and drug addiction. Dopamine agonists are used in early Parkinson's disease treatment. Dopamine antagonists suppress schizophrenia. Therefore, molecules modulating dopamine receptors activity are vastly important for understanding the nervous system functioning and for the treatment of neurological diseases. In this study we describe novel computational models that efficiently predict binding affinity of the existing small molecule dopamine analogs to dopamine receptor. The model provides the set of molecular descriptors that can be used for the development of new small molecule dopamine agonists.

Machine learning approaches for predicting compounds that interact with therapeutic and ADMET related proteins

Computational methods for predicting compounds of specific pharmacodynamic and ADMET (absorption, distribution, metabolism, excretion and toxicity) property are useful for facilitating drug discovery and evaluation. Recently, machine learning methods such as neural networks and support vector machines have been explored for predicting inhibitors, antagonists, blockers, agonists, activators and substrates of proteins related to specific therapeutic and ADMET property. These methods are particularly useful for compounds of diverse structures to complement QSAR methods, and for cases of unavailable receptor 3D structure to complement structure-based methods. A number of studies have demonstrated the potential of these methods for predicting such compounds as substrates of P-glycoprotein and cytochrome P450 CYP isoenzymes, inhibitors of protein kinases and CYP isoenzymes, and agonists of serotonin receptor and estrogen receptor. This article is intended to review the strategies, current progresses and underlying difficulties in using machine learning methods for predicting these protein binders and as potential virtual screening tools. Algorithms for proper representation of the structural and physicochemical properties of compounds are also evaluated.

Modeling chemical reactions for drug design

Chemical reactions are involved at many stages of the drug design process. This starts with the analysis of biochemical pathways that are controlled by enzymes that might be downregulated in certain diseases. In the lead discovery and lead optimization process compounds have to be synthesized in order to test them for their biological activity. And finally, the metabolism of a drug has to be established. A better understanding of chemical reactions could strongly help in making the drug design process more efficient. We have developed methods for quantifying the concepts an organic chemist is using in rationalizing reaction mechanisms. These methods allow a comprehensive modeling of chemical reactivity and thus are applicable to a wide variety of chemical reactions, from gas phase reactions to biochemical pathways. They are empirical in nature and therefore allow the rapid processing of large sets of structures and reactions. We will show here how methods have been developed for the prediction of acidity values and of the regioselectivity in organic reactions, for designing the synthesis of organic molecules and of combinatorial libraries, and for furthering our understanding of enzyme-catalyzed reactions and of the metabolism of drugs.

Development of quantitative structure-binding affinity relationship models based on novel geometrical chemical descriptors of the protein-ligand interfaces

Novel geometrical chemical descriptors have been derived on the basis of the computational geometry of protein-ligand interfaces and Pauling atomic electronegativities (EN). Delaunay tessellation has been applied to a diverse set of 517 X-ray characterized protein-ligand complexes yielding a unique collection of interfacial nearest neighbor atomic quadruplets for each complex. Each quadruplet composition was characterized by a single descriptor calculated as the sum of the EN values for the four participating atom types. We termed these simple descriptors generated from atomic EN values and derived with the Delaunay Tessellation the ENTess descriptors and used them in the variable selection k-nearest neighbor quantitative structure-binding affinity relationship (QSBR) studies of 264 diverse protein-ligand complexes with known binding constants. Twenty-four complexes with chemically dissimilar ligands were set aside as an independent validation set, and the remaining dataset of 240 complexes was divided into multiple training and test sets. The best models were characterized by the leave-one-out cross-validated correlation coefficient q(2) as high as 0.66 for the training set and the correlation coefficient R(2) as high as 0.83 for the test set. The high predictive power of these models was confirmed independently by applying them to the validation set of 24 complexes yielding R(2) as high as 0.85. We conclude that QSBR models built with the ENTess descriptors can be instrumental for predicting the binding affinity of receptor-ligand complexes.

Structure activity relationships and quantitative structure activity relationships for the flavonoid-mediated inhibition of breast cancer resistance protein

Breast cancer resistance protein (BCRP) is a newly identified ABC transporter, which plays an important role in drug disposition and represents an additional mechanism for the development of MDR. Flavonoids, a major class of natural compounds widely present in foods and herbal products, have been shown to be BCRP inhibitors. The objective of the present study was to elucidate the SAR and derive a QSAR model for flavonoid-BCRP interaction. The EC(50) values for increasing mitoxantrone accumulation in MCF-7 MX100 cells for 25 flavonoids, from five flavonoid subclasses, were determined in this study or obtained from our previous publication [Zhang S, Yang X, Morris ME. Combined effects of multiple flavonoids on breast cancer resistance protein (ABCG2)-mediated transport. Pharm Res 2004;21(7):1263-73], and ranged from 0.07+/-0.02 microM to 183+/-21.7 microM. We found that the presence of a 2,3-double bond in ring C, ring B attached at position 2, hydroxylation at position 5, lack of hydroxylation at position 3 and hydrophobic substitution at positions 6, 7, 8 or 4', are important structural properties important for potent flavonoid-BCRP interaction. These structural requirements are similar but not identical to those for potent flavonoid-NBD2 (P-glycoprotein) interaction, indicating that inhibition of BCRP by flavonoids may involve, in part, the binding of flavonoids with the NBD of BCRP. In addition, a QSAR model consisting three structural descriptors was constructed, and both internally and externally validated, suggesting the model could be used to quantitatively predict BCRP inhibition activity of flavonoids. These findings should be useful for predicting BCRP inhibition activity of other untested flavonoids and for guiding the synthesis of potent BCRP inhibitors for potential clinical application.

The uridine diphosphate glucuronosyltransferases: quantitative structure–activity relationships for hydroxyl polychlorinated biphenyl substrates

Quantitative structure-activity relationships (QSARs), which relate the glucuronidation of hydroxyl polychlorinated biphenyls (OH-PCBs)-catalyzed by the uridine diphosphate glucuronosyltransferases (UGTs)-to their physicochemical properties and molecular structural parameters, can be used to predict the rate constants and interpret the mechanism of glucuronidation. In this study, QSARs have been developed that use 23 semi-empirical calculated quantum chemical descriptors to predict the logarithms of the constants 1/K(m) and V(max), related to enzyme kinetics. A partial least squares regression method was used to select the optimal set of descriptors to minimize the multicollinearity between the descriptors, as well as to maximize the cross-validated coefficient (Q(2) (cum)) values. The key descriptors affecting log(1/K(m)) were E(lumo)- E(homo) (the energy gap between the lowest unoccupied molecular orbital and the highest occupied molecular orbital) and q(C) (-) (the largest negative net atomic charge on a carbon atom), while the key descriptors affecting logV(max) were the polarizability alpha, the Connolly solvent-excluded volume (CSEV), and logP (the logarithm of the partition coefficient for octanol/water). From the results obtained it can be concluded that hydrophobic and electronic aspects of OH-PCBs are important in the glucuronidation of OH-PCBs.

Unbiased descriptor and parameter selection confirms the potential of proteochemometric modelling

Background

Proteochemometrics is a new methodology that allows prediction of protein function directly from real interaction measurement data without the need of 3D structure information. Several reported proteochemometric models of ligand-receptor interactions have already yielded significant insights into various forms of bio-molecular interactions. The proteochemometric models are multivariate regression models that predict binding affinity for a particular combination of features of the ligand and protein. Although proteochemometric models have already offered interesting results in various studies, no detailed statistical evaluation of their average predictive power has been performed. In particular, variable subset selection performed to date has always relied on using all available examples, a situation also encountered in microarray gene expression data analysis.

Results

A methodology for an unbiased evaluation of the predictive power of proteochemometric models was implemented and results from applying it to two of the largest proteochemometric data sets yet reported are presented. A double cross-validation loop procedure is used to estimate the expected performance of a given design method. The unbiased performance estimates (P²) obtained for the data sets that we consider confirm that properly designed single proteochemometric models have useful predictive power, but that a standard design based on cross validation may yield models with quite limited performance. The results also show that different commercial software packages employed for the design of proteochemometric models may yield very different and therefore misleading performance estimates. In addition, the differences in the models obtained in the double CV loop indicate that detailed chemical interpretation of a single proteochemometric model is uncertain when data sets are small.

Conclusion

The double CV loop employed offer unbiased performance estimates about a given proteochemometric modelling procedure, making it possible to identify cases where the proteochemometric design does not result in useful predictive models. Chemical interpretations of single proteochemometric models are uncertain and should instead be based on all the models selected in the double CV loop employed here.

Application of predictive QSAR models to database mining: identification and experimental validation of novel anticonvulsant compounds

We have developed a drug discovery strategy that employs variable selection quantitative structure-activity relationship (QSAR) models for chemical database mining. The approach starts with the development of rigorously validated QSAR models obtained with the variable selection k nearest neighbor (kNN) method (or, in principle, with any other robust model-building technique). Model validation is based on several statistical criteria, including the randomization of the target property (Y-randomization), independent assessment of the training set model's predictive power using external test sets, and the establishment of the model's applicability domain. All successful models are employed in database mining concurrently; in each case, only variables selected as a result of model building (termed descriptor pharmacophore) are used in chemical similarity searches comparing active compounds of the training set (queries) with those in chemical databases. Specific biological activity (characteristic of the training set compounds) of external database entries found to be within a predefined similarity threshold of the training set molecules is predicted on the basis of the validated QSAR models using the applicability domain criteria. Compounds judged to have high predicted activities by all or the majority of all models are considered as consensus hits. We report on the application of this computational strategy for the first time for the discovery of anticonvulsant agents in the Maybridge and National Cancer Institute (NCI) databases containing ca. 250,000 compounds combined. Forty-eight anticonvulsant agents of the functionalized amino acid (FAA) series were used to build kNN variable selection QSAR models. The 10 best models were applied to mining chemical databases, and 22 compounds were selected as consensus hits. Nine compounds were synthesized and tested at the NIH Epilepsy Branch, Rockville, MD using the same biological test that was employed to assess the anticonvulsant activity of the training set compounds; of these nine, four were exact database hits and five were derived from the hits by minor chemical modifications. Seven of these nine compounds were confirmed to be active, indicating an exceptionally high hit rate. The approach described in this report can be used as a general rational drug discovery tool.

Rational selection of training and test sets for the development of validated QSAR models

Quantitative Structure-Activity Relationship (QSAR) models are used increasingly to screen chemical databases and/or virtual chemical libraries for potentially bioactive molecules. These developments emphasize the importance of rigorous model validation to ensure that the models have acceptable predictive power. Using k nearest neighbors (kNN) variable selection QSAR method for the analysis of several datasets, we have demonstrated recently that the widely accepted leave-one-out (LOO) cross-validated R2 (q2) is an inadequate characteristic to assess the predictive ability of the models [Golbraikh, A., Tropsha, A. Beware of q2! J. Mol. Graphics Mod. 20, 269-276, (2002)]. Herein, we provide additional evidence that there exists no correlation between the values of q2 for the training set and accuracy of prediction (R2) for the test set and argue that this observation is a general property of any QSAR model developed with LOO cross-validation. We suggest that external validation using rationally selected training and test sets provides a means to establish a reliable QSAR model. We propose several approaches to the division of experimental datasets into training and test sets and apply them in QSAR studies of 48 functionalized amino acid anticonvulsants and a series of 157 epipodophyllotoxin derivatives with antitumor activity. We formulate a set of general criteria for the evaluation of predictive power of QSAR models.

Predicting the Genotoxicity of Polycyclic Aromatic Compounds from Molecular Structure with Different Classifiers

Classification models were developed to provide accurate prediction of genotoxicity of 277 polycyclic aromatic compounds (PACs) directly from their molecular structures. Numerical descriptors encoding the topological, geometric, electronic, and polar surface area properties of the compounds were calculated to represent the structural information. Each compound's genotoxicity was represented with IMAX (maximal SOS induction factor) values measured by the SOS Chromotest in the presence and absence of S9 rat liver homogenate. The compounds' class identity was determined by a cutoff IMAX value of 1.25-compounds with IMAX > 1.25 in either test were classified as genotoxic, and the ones with IMAX < or = 1.25 were nongenotoxic. Several binary classification models were generated to predict genotoxicity: k-nearest neighbor (k-NN), linear discriminant analysis, and probabilistic neural network. The study showed k-NN to provide the highest predictive ability among the three classifiers with a training set classification rate of 93.5%. A consensus model was also developed that incorporated the three classifiers and correctly predicted 81.2% of the 277 compounds. It also provided a higher prediction rate on the genotoxic class than any other single model.

QSAR analysis of the inhibition of recombinant CYP 3A4 activity by structurally diverse compounds using a genetic algorithm-combined partial least squares method

PURPOSE

To develop a quantitative structure/activity relationship (QSAR) model for predicting drug-CYP 3A4 interactions.

METHOD

The inhibitory effect of 53 structurally diverse drugs on the metabolism of 7-benzyloxy-4-trifluoromethyl coumarin (BFC) by recombinant CYP 3A4 was evaluated using a rapid microtiter plate assay. For each drug, a total of 220 two-dimensional topological indices were calculated using Molconn-Z software. Using a genetic algorithm-based partial least squares (GA-PLS) method, the desired descriptors were automatically selected to maximize the predictability of the IC50 values.

RESULTS

The IC50 values of the drugs tested ranged from 9 nM to 2 mM. Based on the GA-PLS method, five principal components derived from 20 Molconn-Z descriptors were found to be effective for QSAR modeling. Interestingly, these descriptors suggested that the molecular size would be an important factor in determining drug-CYP 3A4 interactions. In the leave-one-out prediction, the rpred and the standard error of prediction (s) were 0.754 and 0.787, respectively. Even in an external validation, the predictions were in good agreement with experimental values (rpred = 0.744, s = 0.769, n = 9).

CONCLUSIONS

The proposed model, in which two-dimensional topological descriptors were used as molecular descriptors, was able to predict drug-CYP 3A4 interactions with reasonable accuracy.

Predictive QSAR modeling based on diversity sampling of experimental datasets for the training and test set selection

One of the most important characteristics of Quantitative Structure Activity Relashionships (QSAR) models is their predictive power. The latter can be defined as the ability of a model to predict accurately the target property (e.g., biological activity) of compounds that were not used for model development. We suggest that this goal can be achieved by rational division of an experimental SAR dataset into the training and test set, which are used for model development and validation, respectively. Given that all compounds are represented by points in multidimensional descriptor space, we argue that training and test sets must satisfy the following criteria: (i) Representative points of the test set must be close to those of the training set; (ii) Representative points of the training set must be close to representative points of the test set; (iii) Training set must be diverse. For quantitative description of these criteria, we use molecular dataset diversity indices introduced recently (Golbraikh, A., J. Chem. Inf. Comput. Sci., 40 (2000) 414-425). For rational division of a dataset into the training and test sets, we use three closely related sphere-exclusion algorithms. Using several experimental datasets, we demonstrate that QSAR models built and validated with our approach have statistically better predictive power than models generated with either random or activity ranking based selection of the training and test sets. We suggest that rational approaches to the selection of training and test sets based on diversity principles should be used routinely in all QSAR modeling research.

Structural modeling extends QSAR analysis of antibody-lysozyme interactions to 3D-QSAR

This work shows that quantitative multivariate modeling is an emerging possibility for unraveling protein-protein interactions using a combination of designed mutations with sequence and structure information. Using this approach, it is possible to stereochemically determine which residue properties contribute most to the interaction. This is illustrated by results from modeling of the interaction of the wild-type and 17 single and double mutants of a camel antibody specific for lysozyme. Linear multivariate models describing association and dissociation rates as well as affinity were developed. Sequence information in the form of amino acid property scales was combined with 3D structure information (obtained using molecular mechanics calculations) in the form of coordinates of the alpha-carbons and the center of the side chains. The results show that in addition to the amino acid properties of the mutated residues 101 and 105, the dissociation rate is controlled by the side-chain coordinate of residue 105, whereas the association is determined by the coordinates of residues 99, 100, 105 (side chain), 111, and 112. The great difference between the models for association and dissociation rates illustrates that the event of molecular recognition and the property of binding stability rely on different physical processes.

Quantitative structure/property relationship analysis of Caco-2 permeability using a genetic algorithm-based partial least squares method

Caco-2 cell monolayers are widely used systems for predicting human intestinal absorption. This study was carried out to develop a quantitative structure-property relationship (QSPR) model of Caco-2 permeability using a novel genetic algorithm-based partial least squares (GA-PLS) method. The Caco-2 permeability data for 73 compounds were taken from the literature. Molconn-Z descriptors of these compounds were calculated as molecular descriptors, and the optimal subset of the descriptors was explored by GA-PLS analysis. A fitness function considering both goodness-of-fit to the training data and predictability of the testing data was adopted throughout the genetic algorithm-driven optimization procedure. The final PLS model consisting of 24 descriptors gave a correlation coefficient (r) of 0.886 for the entire dataset and a predictive correlation coefficient (r(pred)) of 0.825 that was evaluated by a leave-some-out cross-validation procedure. Thus, the GA-PLS analysis proved to be a reasonable QSPR modeling approach for predicting Caco-2 permeability.

Quantitative structure-activity relationship analysis of functionalized amino acid anticonvulsant agents using k nearest neighbor and simulated annealing PLS methods

We report the development of rigorously validated quantitative structure-activity relationship (QSAR) models for 48 chemically diverse functionalized amino acids with anticonvulsant activity. Two variable selection approaches, simulated annealing partial least squares (SA-PLS) and k nearest neighbor (kNN), were employed. Both methods utilize multiple descriptors such as molecular connectivity indices or atom pair descriptors, which are derived from two-dimensional molecular topology. QSAR models with high internal accuracy were generated, with leave-one-out cross-validated R(2) (q(2)) values ranging between 0.6 and 0.8. The q(2) values for the actual dataset were significantly higher than those obtained for the same dataset with randomly shuffled activity values, indicating that models were statistically significant. The original dataset was further divided into several training and test sets, with highly predictive models providing q(2) values greater than 0.5 for the training sets and R(2) values greater than 0.6 for the test sets. These models were capable of predicting with reasonable accuracy the activity of 13 novel compounds not included in the original dataset. The successful development of highly predictive QSAR models affords further design and discovery of novel anticonvulsant agents.

Predictive QSAR modeling based on diversity sampling of experimental datasets for the training and test set selection

One of the most important characteristics of Quantitative Structure Activity Relashionships (QSAR) models is their predictive power. The latter can be defined as the ability of a model to predict accurately the target property (e.g., biological activity) of compounds that were not used for model development. We suggest that this goal can be achieved by rational division of an experimental SAR dataset into the training and test set, which are used for model development and validation, respectively. Given that all compounds are represented by points in multidimensional descriptor space, we argue that training and test sets must satisfy the following criteria: (i) Representative points of the test set must be close to those of the training set; (ii) Representative points of the training set must be close to representative points of the test set; (iii) Training set must be diverse. For quantitative description of these criteria, we use molecular dataset diversity indices introduced recently (Golbraikh, A., J. Chem. Inf. Comput. Sci., 40 (2000) 414-425). For rational division of a dataset into the training and test sets, we use three closely related sphere-exclusion algorithms. Using several experimental datasets, we demonstrate that QSAR models built and validated with our approach have statistically better predictive power than models generated with either random or activity ranking based selection of the training and test sets. We suggest that rational approaches to the selection of training and test sets based on diversity principles should be used routinely in all QSAR modeling research.

Beware of q2!

Validation is a crucial aspect of any quantitative structure-activity relationship (QSAR) modeling. This paper examines one of the most popular validation criteria, leave-one-out cross-validated R2 (LOO q2). Often, a high value of this statistical characteristic (q2 > 0.5) is considered as a proof of the high predictive ability of the model. In this paper, we show that this assumption is generally incorrect. In the case of 3D QSAR, the lack of the correlation between the high LOO q2 and the high predictive ability of a QSAR model has been established earlier [Pharm. Acta Helv. 70 (1995) 149; J. Chemomet. 10(1996)95; J. Med. Chem. 41 (1998) 2553]. In this paper, we use two-dimensional (2D) molecular descriptors and k nearest neighbors (kNN) QSAR method for the analysis of several datasets. No correlation between the values of q2 for the training set and predictive ability for the test set was found for any of the datasets. Thus, the high value of LOO q2 appears to be the necessary but not the sufficient condition for the model to have a high predictive power. We argue that this is the general property of QSAR models developed using LOO cross-validation. We emphasize that the external validation is the only way to establish a reliable QSAR model. We formulate a set of criteria for evaluation of predictive ability of QSAR models.