Cross-validation strategies in QSPR modelling of chemical reactions.

In this article, we consider cross-validation of the quantitative structure-property relationship models for reactions and show that the conventional k-fold cross-validation (CV) procedure gives an 'optimistically' biased assessment of prediction performance. To address this issue, we suggest two strategies of model cross-validation, 'transformation-out' CV, and 'solvent-out' CV. Unlike the conventional k-fold cross-validation approach that does not consider the nature of objects, the proposed procedures provide an unbiased estimation of the predictive performance of the models for novel types of structural transformations in chemical reactions and reactions going under new conditions. Both the suggested strategies have been applied to predict the rate constants of bimolecular elimination and nucleophilic substitution reactions, and Diels-Alder cycloaddition. All suggested cross-validation methodologies and tutorial are implemented in the open-source software package CIMtools (https://github.com/cimm-kzn/CIMtools).

Autoignition temperature: comprehensive data analysis and predictive models.

Here we report a new predictive model for autoignition temperature (AIT), an important physical parameter widely used to assess potential safety hazards of combustible materials. Available structure-AIT data extracted from different sources were critically analysed. Support vector regression (SVR) models on different data subsets were built in order to identify a reliable compound set on which a realistic model could be built. This led to a selection of the dataset containing 875 compounds annotated with AIT values. The thereupon-based SVR model performs reasonably well in cross-validation with the determination coefficient r 2 = 0.77 and mean absolute error MAE = 37.8°C. External validation on 20 industrial compounds missing in the training set confirmed its good predictive power (MAE = 28.7°C).

Assessment of tautomer distribution using the condensed reaction graph approach.

We report the first direct QSPR modeling of equilibrium constants of tautomeric transformations (logK T ) in different solvents and at different temperatures, which do not require intermediate assessment of acidity (basicity) constants for all tautomeric forms. The key step of the modeling consisted in the merging of two tautomers in one sole molecular graph ("condensed reaction graph") which enables to compute molecular descriptors characterizing entire equilibrium. The support vector regression method was used to build the models. The training set consisted of 785 transformations belonging to 11 types of tautomeric reactions with equilibrium constants measured in different solvents and at different temperatures. The models obtained perform well both in cross-validation (Q2 = 0.81 RMSE = 0.7 logK T units) and on two external test sets. Benchmarking studies demonstrate that our models outperform results obtained with DFT B3LYP/6-311 ++ G(d,p) and ChemAxon Tautomerizer applicable only in water at room temperature.

GTM-Based QSAR Models and Their Applicability Domains.

In this paper we demonstrate that Generative Topographic Mapping (GTM), a machine learning method traditionally used for data visualisation, can be efficiently applied to QSAR modelling using probability distribution functions (PDF) computed in the latent 2-dimensional space. Several different scenarios of the activity assessment were considered: (i) the "activity landscape" approach based on direct use of PDF, (ii) QSAR models involving GTM-generated on descriptors derived from PDF, and, (iii) the k-Nearest Neighbours approach in 2D latent space. Benchmarking calculations were performed on five different datasets: stability constants of metal cations Ca(2+) , Gd(3+) and Lu(3+) complexes with organic ligands in water, aqueous solubility and activity of thrombin inhibitors. It has been shown that the performance of GTM-based regression models is similar to that obtained with some popular machine-learning methods (random forest, k-NN, M5P regression tree and PLS) and ISIDA fragment descriptors. By comparing GTM activity landscapes built both on predicted and experimental activities, we may visually assess the model's performance and identify the areas in the chemical space corresponding to reliable predictions. The applicability domain used in this work is based on data likelihood. Its application has significantly improved the model performances for 4 out of 5 datasets.

Combined QSAR studies of inhibitor properties of O-phosphorylated oximes toward serine esterases involved in neurotoxicity, drug metabolism and Alzheimer's disease.

Oxime reactivation of serine esterases (EOHs) inhibited by organophosphorus (OP) compounds can produce O-phosphorylated oximes (POXs). Such oxime derivatives are of interest, because some of them can have greater anti-EOH potencies than the OP inhibitors from which they were derived. Accordingly, inhibitor properties of 58 POXs against four EOHs, along with pair-wise selectivities between them, have been analysed using different QSAR approaches. EOHs (with their abbreviations and consequences of inhibition in parentheses) comprised acetylcholinesterase (AChE: acute neurotoxicity; cognition enhancement), butyrylcholinesterase (BChE: inhibition of drug metabolism or stoichiometric scavenging of EOH inhibitors; cognition enhancement), carboxylesterase (CaE: inhibition of drug metabolism or stoichiometric scavenging of EOH inhibitors), and neuropathy target esterase (NTE: delayed neurotoxicity). QSAR techniques encompassed linear regression and backpropagation neural networks in conjunction with fragmental descriptors containing labelled atoms, Molecular Field Topology Analysis (MFTA), Comparative Molecular Similarity Index Analysis (CoMSIA), and molecular modelling. All methods provided mostly consistent and complementary information, and they revealed structural features controlling the 'esterase profiles', i.e. patterns of anti-EOH activities and selectivities of the compounds of interest. In addition, MFTA models were used to design a library of compounds having a cognition-enhancement esterase profile suitable for potential application to the treatment of Alzheimer's disease.

Generative Topographic Mapping (GTM): Universal Tool for Data Visualization, Structure-Activity Modeling and Dataset Comparison.

Here, the utility of Generative Topographic Maps (GTM) for data visualization, structure-activity modeling and database comparison is evaluated, on hand of subsets of the Database of Useful Decoys (DUD). Unlike other popular dimensionality reduction approaches like Principal Component Analysis, Sammon Mapping or Self-Organizing Maps, the great advantage of GTMs is providing data probability distribution functions (PDF), both in the high-dimensional space defined by molecular descriptors and in 2D latent space. PDFs for the molecules of different activity classes were successfully used to build classification models in the framework of the Bayesian approach. Because PDFs are represented by a mixture of Gaussian functions, the Bhattacharyya kernel has been proposed as a measure of the overlap of datasets, which leads to an elegant method of global comparison of chemical libraries.

Kinetics and mechanism of inhibition of serine esterases by fluorinated aminophosphonates.

This paper reviews previously published data and presents new results to address the hypothesis that fluorinated aminophosphonates (FAPs), (RO)(2)P(O)C(CF(3))(2)NHS(O)(2)C(6)H(5), R=alkyl, inhibit serine esterases by scission of the P-C bond. Kinetics studies demonstrated that FAPs are progressive irreversible inhibitors of acetylcholinesterase (AChE, EC 3.1.1.7.), butyrylcholinesterase (BChE, EC 3.1.1.8.), carboxylesterase (CaE, EC 3.1.1.1.), and neuropathy target esterase (NTE, EC 3.1.1.5.), consistent with P-C bond breakage. Chemical reactivity experiments showed that diMe-FAP and diEt-FAP react with water to yield the corresponding dialkylphosphates and (CF(3))(2)CHNHS(O)(2)C(6)H(5), indicating lability of the P-C bond. X-ray crystallography of diEt-FAP revealed an elongated (and therefore weaker) P-C bond (1.8797 (13)A) compared to P-C bonds in dialkylphosphonates lacking alpha-CF(3) groups (1.805-1.822A). Semi-empirical and non-empirical molecular modeling of diEt-FAP and (EtO)(2)P(O)C(CH(3))(2)NHS(O)(2)C(6)H(5) (diEt-AP), which lacks CF(3) groups, indicated lengthening and destabilization of the P-C bond in diEt-FAP compared to diEt-AP. Active site peptide adducts formed by reacting diEt-FAP with BChE and diBu-FAP with NTE catalytic domain (NEST) were identified using peptide mass mapping with mass spectrometry (MS). Mass shifts (mean+/-SE, average mass) for peaks corresponding to active site peptides with diethylphosphoryl and monoethylphosphoryl adducts on BChE were 136.1+/-0.1 and 108.0+/-0.1Da, respectively. Corresponding mass shifts for dibutylphosphoryl and monobutylphosphoryl adducts on NEST were 191.8+/-0.2 and 135.5+/-0.1Da, respectively. Each of these values was statistically identical to the theoretical mass shift for each dialkylphosphoryl and monoalkylphosphoryl species. The MS results demonstrate that inhibition of BChE and NEST by FAPs yields dialkylphosphoryl and monoalkylphosphoryl adducts, consistent with phosphorylation via P-C bond cleavage and aging by net dealkylation. Taken together, predictions from enzyme kinetics, chemical reactivity, X-ray crystallography, and molecular modeling were confirmed by MS and support the hypothesis that FAPs inhibit serine esterases via scission of the P-C bond.

Molecular modeling of modified peptides, potent inhibitors of the xWNT8 and hWNT8 proteins.

Signaling pathways of Wnt-proteins and Fzd-receptors play important role in processes of growth and development of stem cells and in many types of cancers. The binding of the Wnt-proteins and Fzd-receptors is a complicated process, in which 19 Wnt-proteins and 10 Fzd-receptors are involved. Such a large number of combinations of Wnt-Fzd pairs leads to many different influences of Fzd-Wnt-complexes on the development and differentiation of stem cells. The molecular models of xWnt8, hWnt8, mFzd8, hFzd8-proteins and their complexes were constructed and studied in the present work. The amino acids of the binding sites of proteins which participate in these complexes formation and the protein-protein interactions were studied. The pharmacophoric model of the binding site on the xWnt8 and hWnt8-proteins was constructed. In this work we suggested the peptidomimetic ligands, which can be used for the inhibition of the xWnt8-mFzd8 and hWnt8-hFzd8 proteins formation. The de novo design method of Allegrow software was used for the predictions of most prospective functional groups of the peptidomimetic ligands. These ligands can be used as inhibitors of xWnt8-mFzd8 and hWnt8-hFzd8 complex formation and also can be used for drug design by other methods.

Role of two chloride-binding sites in functioning of testicular angiotensin-converting enzyme.

Modeling the structure of the C-domain of bovine angiotensin-converting enzyme revealed two putative chloride-binding sites. The kinetic parameters, K(m) and k(cat), of hydrolysis of the substrate Cbz-Phe-His-Leu catalyzed by the testicular (C-domain) enzyme were determined over a wide range of chloride concentrations. Chloride anions were found to be enzyme activators at relatively low concentrations, but they inhibit enzymatic activity at high concentrations. A general scheme for the effect of chloride anions on activity of the C-domain of bovine angiotensin-converting enzyme accounting for binding the "activating" and "inhibiting" anions is suggested.

[Structure-functional features of homologous domains of angiotensin-converting enzyme]. / Strukturno-funktsional'nye osobennosti gomologichnykh domenov angiotenzinprevrashchaiushchego fermenta.

Somatic angiotensin-converting enzyme (ACE) consists of two homologous domains, each of them containing an active site. Differences in substrate specificities and affinity to inhibitors of the active sites of the two domains of bovine ACE are described. The ACE domains demonstrate different thermostability, and the reasons for this difference are analyzed. A structural model of the ACE domains is suggested, which allows us to reveal the structural subdomain important for the protein stability and localize the hydrophobic and the carbohydrate-binding sites.