QSAR modeling based on structure-information for properties of interest in human health

Prediction of logP for Pt(II) and Pt(IV) complexes: Comparison of statistical and quantum-chemistry based approaches

The octanol/water partition coefficient, logP, is one of the most important physico-chemical parameters for the development of new metal-based anticancer drugs with improved pharmacokinetic properties. This study addresses an issue with the absence of publicly available models to predict logP of Pt(IV) complexes. Following data collection and subsequent development of models based on 187 complexes from literature, we validate new and previously published models on a new set of 11 Pt(II) and 35 Pt(IV) complexes, which were kept blind during the model development step. The error of the consensus model, 0.65 for Pt(IV) and 0.37 for Pt(II) complexes, indicates its good accuracy of predictions. The lower accuracy for Pt(IV) complexes was attributed to experimental difficulties with logP measurements for some poorly-soluble compounds. This model was developed using general-purpose descriptors such as extended functional groups, molecular fragments and E-state indices. Surprisingly, models based on quantum-chemistry calculations provided lower prediction accuracy. We also found that all the developed models strongly overestimate logP values for the three complexes measured in the presence of DMSO. Considering that DMSO is frequently used as a solvent to store chemicals, its effect should not be overlooked when logP measurements by means of the shake flask method are performed. The final models are freely available at http://ochem.eu/article/76903.

Role of in silico genotoxicity tools in the regulatory assessment of pharmaceutical impurities

The toxicological assessment of genotoxic impurities is important in the regulatory framework for pharmaceuticals. In this context, the application of promising computational methods (e.g. Quantitative Structure-Activity Relationships (QSARs), Structure-Activity Relationships (SARs) and/or expert systems) for the evaluation of genotoxicity is needed, especially when very limited information on impurities is available. To gain an overview of how computational methods are used internationally in the regulatory assessment of pharmaceutical impurities, the current regulatory documents were reviewed. The software recommended in the guidelines (e.g. MCASE, MC4PC, Derek for Windows) or used practically by various regulatory agencies (e.g. US Food and Drug Administration, US and Danish Environmental Protection Agencies), as well as other existing programs were analysed. Both statistically based and knowledge-based (expert system) tools were analysed. The overall conclusions on the available in silico tools for genotoxicity and carcinogenicity prediction are quite optimistic, and the regulatory application of QSAR methods is constantly growing. For regulatory purposes, it is recommended that predictions of genotoxicity/carcinogenicity should be based on a battery of models, combining high-sensitivity models (low rate of false negatives) with high-specificity ones (low rate of false positives) and in vitro assays in an integrated manner.

QSAR models for anti-androgenic effect--a preliminary study

Three modelling systems (MultiCase®, LeadScope® and MDL® QSAR) were used for construction of androgenic receptor antagonist models. There were 923-942 chemicals in the training sets. The models were cross-validated (leave-groups-out) with concordances of 77-81%, specificity of 78-91% and sensitivity of 51-76%. The specificity was highest in the MultiCase® model and the sensitivity was highest in the MDL® QSAR model. A complementary use of the models may be a valuable tool when optimizing the prediction of chemicals for androgenic receptor antagonism. When evaluating the fitness of the model for a particular application, balance of training sets, domain definition, and cut-offs for prediction interpretation should also be taken into account. Different descriptors in the modelling systems are illustrated with hydroxyflutamide and dexamethasone as examples (a non-steroid and a steroid anti-androgen, respectively). More research concerning the mechanism of anti-androgens would increase the possibility for further optimization of the QSAR models. Further expansion of the basis for the models is in progress, including the addition of more drugs.

New public QSAR model for carcinogenicity

BACKGROUND

One of the main goals of the new chemical regulation REACH (Registration, Evaluation and Authorization of Chemicals) is to fulfill the gaps in data concerned with properties of chemicals affecting the human health. (Q)SAR models are accepted as a suitable source of information. The EU funded CAESAR project aimed to develop models for prediction of 5 endpoints for regulatory purposes. Carcinogenicity is one of the endpoints under consideration.

RESULTS

Models for prediction of carcinogenic potency according to specific requirements of Chemical regulation were developed. The dataset of 805 non-congeneric chemicals extracted from Carcinogenic Potency Database (CPDBAS) was used. Counter Propagation Artificial Neural Network (CP ANN) algorithm was implemented. In the article two alternative models for prediction carcinogenicity are described. The first model employed eight MDL descriptors (model A) and the second one twelve Dragon descriptors (model B). CAESAR's models have been assessed according to the OECD principles for the validation of QSAR. For the model validity we used a wide series of statistical checks. Models A and B yielded accuracy of training set (644 compounds) equal to 91% and 89% correspondingly; the accuracy of the test set (161 compounds) was 73% and 69%, while the specificity was 69% and 61%, respectively. Sensitivity in both cases was equal to 75%. The accuracy of the leave 20% out cross validation for the training set of models A and B was equal to 66% and 62% respectively. To verify if the models perform correctly on new compounds the external validation was carried out. The external test set was composed of 738 compounds. We obtained accuracy of external validation equal to 61.4% and 60.0%, sensitivity 64.0% and 61.8% and specificity equal to 58.9% and 58.4% respectively for models A and B.

CONCLUSION

Carcinogenicity is a particularly important endpoint and it is expected that QSAR models will not replace the human experts opinions and conventional methods. However, we believe that combination of several methods will provide useful support to the overall evaluation of carcinogenicity. In present paper models for classification of carcinogenic compounds using MDL and Dragon descriptors were developed. Models could be used to set priorities among chemicals for further testing. The models at the CAESAR site were implemented in java and are publicly accessible.

New public QSAR model for carcinogenicity

BACKGROUND

One of the main goals of the new chemical regulation REACH (Registration, Evaluation and Authorization of Chemicals) is to fulfill the gaps in data concerned with properties of chemicals affecting the human health. (Q)SAR models are accepted as a suitable source of information. The EU funded CAESAR project aimed to develop models for prediction of 5 endpoints for regulatory purposes. Carcinogenicity is one of the endpoints under consideration.

RESULTS

Models for prediction of carcinogenic potency according to specific requirements of Chemical regulation were developed. The dataset of 805 non-congeneric chemicals extracted from Carcinogenic Potency Database (CPDBAS) was used. Counter Propagation Artificial Neural Network (CP ANN) algorithm was implemented. In the article two alternative models for prediction carcinogenicity are described. The first model employed eight MDL descriptors (model A) and the second one twelve Dragon descriptors (model B). CAESAR's models have been assessed according to the OECD principles for the validation of QSAR. For the model validity we used a wide series of statistical checks. Models A and B yielded accuracy of training set (644 compounds) equal to 91% and 89% correspondingly; the accuracy of the test set (161 compounds) was 73% and 69%, while the specificity was 69% and 61%, respectively. Sensitivity in both cases was equal to 75%. The accuracy of the leave 20% out cross validation for the training set of models A and B was equal to 66% and 62% respectively. To verify if the models perform correctly on new compounds the external validation was carried out. The external test set was composed of 738 compounds. We obtained accuracy of external validation equal to 61.4% and 60.0%, sensitivity 64.0% and 61.8% and specificity equal to 58.9% and 58.4% respectively for models A and B.

CONCLUSION

Carcinogenicity is a particularly important endpoint and it is expected that QSAR models will not replace the human experts opinions and conventional methods. However, we believe that combination of several methods will provide useful support to the overall evaluation of carcinogenicity. In present paper models for classification of carcinogenic compounds using MDL and Dragon descriptors were developed. Models could be used to set priorities among chemicals for further testing. The models at the CAESAR site were implemented in java and are publicly accessible.

CE50: quantifying collision induced dissociation energy for small molecule characterization and identification

Survival yield analysis is routinely used in mass spectroscopy as a tool for assessing precursor ion stability and internal energy. Because ion internal energy and decomposition reaction rates are dependent on chemical structure, we reasoned that survival yield curves should be compound-specific and therefore useful for chemical identification. In this study, a quantitative approach for analyzing the correlation between survival yield and collision energy was developed and validated. This method is based on determining the collision energy (CE) at which the survival yield is 50% (CE(50)) and, further, provides slope and intercept values for each survival yield curve. In initial experiments using a defined set of homologous compounds, we found that CE(50) values were easily determined, quantitative, highly reproducible, and could discriminate between structural and even positional isomers. Further analysis demonstrated that CE(50) values were independent of cone potential and orthogonal to compound mass. Experimentally determined CE(50) values for a diverse set of 54 compounds were correlated to Molconn molecular structure descriptors. The resulting model yielded a statistically significant linear correlation between experimental and calculated CE(50) values and identified several structural characteristics related to precursor ion stability and fragmentation mechanism. Thus, the CE(50) is a promising method for compound identification and discrimination.

Overcoming tumor drug resistance with C2-modified 10-deacetyl-7-propionyl cephalomannines: a QSAR study

The microtubule-stabilizing taxanes such as paclitaxel and docetaxel are the two most important anticancer drugs currently used in clinics for the treatment of various types of cancers. However, the major common drawbacks of these two drugs are drug resistance, neurotoxicity, substrate for drug transporter P-gp, cross-resistance with other chemotherapeutic agents, low oral bioavailability, and no penetration in the blood-brain barrier (BBB). These limitations have led to the search for new taxane derivatives with improved biological activity. In the present paper, we discuss the quantitative structure-activity relationship (QSAR) studies on a series of C2-modified 10-deacetyl-7-propionyl cephalomannines (IV) with respect to their binding affinities toward beta-tubulin and cytotoxic activities against both drug-sensitive and drug-resistant tumor cells, in which resistance is mediated through either P-gp overexpression or beta-tubulin mutation mechanisms, by the formulation of five QSARs. Hydrophobicity and molar refractivity of the substituents (pi(X) and MR(X)) are found to be the most important determinants for the activity. Parabolic correlations in terms of MR(X) (eqs 2 and 4 ) are encouraging examples in which the optimum values of MR(X) are well-defined. We believe that these two QSAR models may prove to be adequate predictive models that can help to provide guidance in design and synthesis, and subsequently yield very specific cephalomannine derivatives (IV) that may have high biological activities. On the basis of these two QSAR models, 10 cephalomannine analogues (IV-21 to IV-30) are suggested as potential synthetic targets. Internal (cross-validation (q(2)), quality factor (Q), Fischer statistics (F), and Y-randomization) and external validation tests have validated all the QSAR models.

Taxane analogues against lung cancer: a quantitative structure-activity relationship study

Lung cancer is the second most common cancer in both men (after prostate cancer) and women (after breast cancer). The microtubule-stabilizing taxane such as docetaxel is the only agent currently approved for both first- and second-line treatment of advanced non-small cell lung cancer. Although docetaxel has made significant progress in the treatment of lung cancers either using alone or in combination with various novel targeted agents, its use often results in various undesired side-effects. These limitations have led to the search for new taxane derivatives with fewer side-effects, superior pharmacological properties, and improved anticancer activity to maximize the induced benefits for lung cancer patients. Herein, four series of taxane derivatives were used to correlate their inhibitory activities against lung cancer cells with hydrophobic and steric descriptors to gain a better understanding of their chemical-biological interactions. A parabolic correlation with MR(Y) is the most encouraging example, in which the optimum value of this parameter is well defined. On the basis of this quantitative structure-activity relationship model, six compounds (3-23 to 3-28) are suggested as potential synthetic targets. Internal (cross-validation (q(2)), quality factor (Q), Fischer statistics (F ) and Y-randomization) and external validation tests have validated all the quantitative structure-activity relationship models.

Prediction of HPLC retention index using artificial neural networks and IGroup E-state indices

A back-propagation artificial neural network (ANN) was used to create a 10-fold leave-10%-out cross-validated ensemble model of high performance liquid chromatography retention index (HPLC-RI) for a data set of 498 diverse druglike compounds. A 10-fold multiple linear regression (MLR) ensemble model of the same data was developed for comparison. Molecular structure was described using IGroup E-state indices, a novel set of structure-information representation (SIR) descriptors, along with molecular connectivity chi and kappa indices and other SIR descriptors previously reported. The same input descriptors were used to develop models by both learning algorithms. The MLR model yielded marginally acceptable statistics with training correlation r(2) = 0.65, mean absolute error (MAE) = 83 RI units. External validation of 104 compounds not used for model development yielded validation v(2) = 0.49 and MAE = 73 RI units. The distribution of residuals for the fit and validate data sets suggest a nonlinear relationship between retention index and molecular structure as described by the SIR indices. Not surprisingly, the ANN model was significantly more accurate for both training and validation with training set r(2) = 0.93, MAE = 30 RI units and validation v(2) = 0.84, MAE = 41 RI units. For the ANN model, a total of 91% of validation predictions were within 100 RI units of the experimental value.

Bioactivity and structure of biophenols as mediators of chronic diseases

Biophenols and their associated activity have generated intense interest. Current topics of debate are their bioavailability and bioactivity. It is generally assumed that their plasma concentrations are insufficient to produce the health benefits previously attributed to their consumption. However, data on localized in vivo concentrations are not available and many questions remain unanswered. Potential mechanisms by which they may exert significant bioactivity are discussed together with structure activity relationships. Biophenols are highly reactive species and they can react with a range of other compounds. Products of their reaction when functioning as antioxidants are examined.

QSAR models for P450 (2D6) substrate activity

Human Cytochrome P450 (CYP) is a large group of enzymes that possess an essential function in metabolising different exogenous and endogenous compounds. Humans have more than 50 different genes encoding CYP enzymes, among these a gene encoding for the CYP isoenzyme 2D6, a CYP able to metabolise drugs and other chemicals. A training set of 747 chemicals primarily based on in vivo human data for the CYP isoenzyme 2D6 was collected from the literature. QSAR models focusing on substrate/non-substrate activity were constructed by the use of MultiCASE, Leadscope and MDL quantitative structure-activity relationship (QSAR) modelling systems. They cross validated (leave-groups-out) with concordances of 71%, 81% and 82%, respectively. Discrete organic European Inventory of Existing Commercial Chemical Substances (EINECS) chemicals were screened to predict an approximate percentage of CYP 2D6 substrates. These chemicals are potentially present in the environment. The biological importance of the CYP 2D6 and the use of the software mentioned above were discussed.

Prediction of PAH mutagenicity in human cells by QSAR classification

Polycyclic aromatic hydrocarbons (PAHs) are ubiquitous pollutants of high environmental concern. The experimental data of a mutagenicity test on human B-lymphoblastoid cells (alternative to the Ames bacterial test) for a set of 70 oxo-, nitro- and unsubstituted PAHs, detected in particulate matter (PM), were modelled by Quantitative Structure-Activity Relationships (QSAR) classification methods (k-NN, k-Nearest Neighbour, and CART, Classification and Regression Tree) based on different theoretical molecular descriptors selected by Genetic Algorithms. The best models were validated for predictivity both externally and internally. For external validation, Self Organizing Maps (SOM) were applied to split the original data set. The best models, developed on the training set alone, show good predictive performance also on the prediction set chemicals (sensitivity 69.2-87.1%, specificity 62.5-87.5%). The classification of PAHs according to their mutagenicity, based only on a few theoretical molecular descriptors, allows a preliminary assessment of the human health risk, and the prioritisation of these compounds.

Predictive toxinology: an initial foray using calculated molecular descriptors to describe toxicity using saxitoxins as a model

Molecular descriptors and their mathematical combination have been used for predictive toxicology and risk assessments of environmental pollutants and pharmaceutical leads. However, this approach has not yet been used for natural toxins and may contribute to health and environmental risk assessments of newly discovered toxins without having to undertake whole animal toxicology. To explore this approach, over 3000 descriptors were calculated for each of the 30 saxitoxins for which mouse toxicities have been reported. This dataset was reduced to only 87 descriptors by firstly eliminating descriptors that were the same for all toxins or could not be calculated for all 30 toxins, and then removing those descriptors that did not have a statistically significant linear relationship with toxicity values. From the remaining 87 descriptors, a subset of seven descriptors was identified upon which various mathematical approaches were assessed for their ability to fit the dataset both with and without leave-one-out cross-validation. K-nearest neighbours and support vector machine regression along with various combinations of these seven descriptors fit the toxicity data almost perfectly and also achieved high predictability as measured by leave-one-out cross-validation. Of these seven descriptors, five incorporated weighting by estimates of atomic polarizability and electronic states. Predicted toxicities of several saxitoxins of unknown toxicity bore similarities to the pattern of known potencies of these toxins on various isoforms of the voltage-gated sodium channel. Some of these predicted toxicity values however would not be expected if there was a direct relationship between mammalian sodium channel affinity of the saxitoxins and whole animal toxicity.

Evolutionary computation and multimodal search: a good combination to tackle molecular diversity in the field of peptide design

The awesome degree of structural diversity accessible in peptide design has created a demand for computational resources that can evaluate a multitude of candidate structures. In our specific case, we translate the peptide design problem to an optimization problem, and use evolutionary computation (EC) in tandem with docking to carry out a combinatorial search. However, the use of EC in huge search spaces with different optima may pose certain drawbacks. For example, EC is prone to focus a search in the first good region found. This is a problem not only because of the undesirable and automatic rejection of potentially good search space regions, but also because the found solution may be extremely difficult to synthesize chemically or may even be a false docking positive. In order to avoid rejecting potentially good solutions and to maximize the molecular diversity of the search, we have implemented evolutionary multimodal search techniques, as well as the molecular diversity metric needed by the multimodal algorithms to measure differences between various regions of the search space.