Vitaly P. Solov'ev

ISIDA - Platform for Virtual Screening Based on Fragment and Pharmacophoric Descriptors

In this paper we illustrate the application of the ISIDA (In SIlico design and Data Analysis) software to perform virtual screening of large databases of compounds and reactions and to assess some ADME/Tox properties. ISIDA represents an ensemble of tools allowing users to store, search and analyze the data, to perform similarity searches in large databases of molecules and reactions, to build and validate QSAR models, and to generate and screen virtual combinatorial libraries. It uses its own descriptors (substructural molecular fragments and fuzzy pharmacophore triplets). Workflow can be easily organized by combining different ISIDA modules. Several examples of ISIDA applications (similarity search of potent benzodiazepine ligands with FPT, QSAR modeling of aqueous solubility, aquatic toxicity, tissue-air partition coefficients, anti-HIV activity, and screening of the “Chimiotheque Nationale” Database), are discussed. Particular attention is paid to mining reaction databases using Condensed Reaction Graphs approach.

Exhaustive QSPR Studies of a Large Diverse Set of Ionic Liquids: How Accurately Can We Predict Melting Points?

Several popular machine learning methods--Associative Neural Networks (ANN), Support Vector Machines (SVM), k Nearest Neighbors (kNN), modified version of the partial least-squares analysis (PLSM), backpropagation neural network (BPNN), and Multiple Linear Regression Analysis (MLR)--implemented in ISIDA, NASAWIN, and VCCLAB software have been used to perform QSPR modeling of melting point of structurally diverse data set of 717 bromides of nitrogen-containing organic cations (FULL) including 126 pyridinium bromides (PYR), 384 imidazolium and benzoimidazolium bromides (IMZ), and 207 quaternary ammonium bromides (QUAT). Several types of descriptors were tested: E-state indices, counts of atoms determined for E-state atom types, molecular descriptors generated by the DRAGON program, and different types of substructural molecular fragments. Predictive ability of the models was analyzed using a 5-fold external cross-validation procedure in which every compound in the parent set was included in one of five test sets. Among the 16 types of developed structure--melting point models, nonlinear SVM, ASNN, and BPNN techniques demonstrate slightly better performance over other methods. For the full set, the accuracy of predictions does not significantly change as a function of the type of descriptors. For other sets, the performance of descriptors varies as a function of method and data set used. The root-mean squared error (RMSE) of prediction calculated on independent test sets is in the range of 37.5-46.4 degrees C (FULL), 26.2-34.8 degrees C (PYR), 38.8-45.9 degrees C (IMZ), and 34.2-49.3 degrees C (QUAT). The moderate accuracy of predictions can be related to the quality of the experimental data used for obtaining the models as well as to difficulties to take into account the structural features of ionic liquids in the solid state (polymorphic effects, eutectics, glass formation).

Substructural fragments: an universal language to encode reactions, molecular and supramolecular structures.

SummarySubstructural fragments are proposed as a simple and safe way to encode molecular structures in a matrix containing the occurrence of fragments of a given type. The knowledge retrieved from QSPR modelling can also be stored in that matrix in addition to the information about fragments. Complex supramolecular systems (using special bond types) and chemical reactions (represented as Condensed Graphs of Reactions, CGR) can be treated similarly. The efficiency of fragments as descriptors has been demonstrated in QSPR studies of aqueous solubility for a diverse set of organic compounds as well as in the analysis of thermodynamic parameters for hydrogen-bonding in some supramolecular complexes. It has also been shown that CGR may be an interesting opportunity to perform similarity searches for chemical reactions. The relationship between the density of information in descriptors/knowledge matrices and the robustness of QSPR models is discussed.

Quantitative structure-property relationship modeling of beta-cyclodextrin complexation free energies.

CODESSA-PRO was used to model binding energies for 1:1 complexation systems between 218 organic guest molecules and beta-cyclodextrin, using a seven-parameter equation with R2 = 0.796 and Rcv2 = 0.779. Fragment-based TRAIL calculations gave a better fit with R2 = 0.943 and Rcv2 = 0.848 for 195 data points in the database. The advantages and disadvantages of each approach are discussed, and it is concluded that a combination of the two approaches has much promise from a practical viewpoint.

Benchmarking of linear and nonlinear approaches for quantitative structure-property relationship studies of metal complexation with ionophores.

A benchmark of several popular methods, Associative Neural Networks (ANN), Support Vector Machines (SVM), k Nearest Neighbors (kNN), Maximal Margin Linear Programming (MMLP), Radial Basis Function Neural Network (RBFNN), and Multiple Linear Regression (MLR), is reported for quantitative-structure property relationships (QSPR) of stability constants logK1 for the 1:1 (M:L) and logbeta2 for 1:2 complexes of metal cations Ag+ and Eu3+ with diverse sets of organic molecules in water at 298 K and ionic strength 0.1 M. The methods were tested on three types of descriptors: molecular descriptors including E-state values, counts of atoms determined for E-state atom types, and substructural molecular fragments (SMF). Comparison of the models was performed using a 5-fold external cross-validation procedure. Robust statistical tests (bootstrap and Kolmogorov-Smirnov statistics) were employed to evaluate the significance of calculated models. The Wilcoxon signed-rank test was used to compare the performance of methods. Individual structure-complexation property models obtained with nonlinear methods demonstrated a significantly better performance than the models built using multilinear regression analysis (MLRA). However, the averaging of several MLRA models based on SMF descriptors provided as good of a prediction as the most efficient nonlinear techniques. Support Vector Machines and Associative Neural Networks contributed in the largest number of significant models. Models based on fragments (SMF descriptors and E-state counts) had higher prediction ability than those based on E-state indices. The use of SMF descriptors and E-state counts provided similar results, whereas E-state indices lead to less significant models. The current study illustrates the difficulties of quantitative comparison of different methods: conclusions based only on one data set without appropriate statistical tests could be wrong.

TOWARDS AN INFORMATION SYSTEM ON SOLVENT EXTRACTION

This article concerns the design of a prototype information system for solvent extraction of metals including a comprehensive factual database and an expert system to analyse experimental extraction data. A demonstration version of the solvent extraction database is described. Each database record corresponds to one extraction equilibrium and contains three information parts (bibliographic, extraction system description and extraction properties) including chemical structural 2D and 3D information for extractants, as well as thermodynamic and kinetic data in textual, numerical and graphical forms. As expert system we use the Substructural Molecular Fragments method which models structure-property relationships using information retrieved from the database. Its performance is assessed on the distribution ratios of Hg, In and Pt extracted by 26 phosphoryl-containing monopodands, and of uranium extracted by 32 mono- and tripodands or by 22 monoamides.

QSPR Modeling of the AmIII/EuIII Separation Factor: How Far Can we Predict ?

Abstract Exhaustive quantitative structure‐property relationship (QSPR) modeling of the separation factor logSF for 46 polyazaheterocyclic ligands extracting Am3+ and Eu3+ from nitric acid aqueous solution to the 1,1,2,2–tetrachloroethane phase has been done using different computational approaches. Modeling methods included Multiple Linear Regression, Radial Basis Function Neural Networks, and Associated Neural Networks; two types of descriptors (substructural molecular fragments and molecular descriptors) and different techniques of variable selection have been employed. The developed QSPR models applied for novel t‐Bu‐hemi‐BTP ligand resulted in logSF=1.07−1.46; these predicted values somewhat exceed the experimental value logSF=1.0. Several hypothetical extractants potentially possessing high logSF values are proposed. An influence of uncertainties in initial experimental data as well as the choice of the theoretical approach on the performance of QSPR models is discussed.

Computer-aided design of new metal binders

Summary Chemoinformatics approaches open new opportunities for computer-aided design of new efficient metal binders. Here, we demonstrate performances of ISIDA and COMET software tools to predict stability constants (log K) of the metal ion/organic ligand complexes in solution and to design in silico new molecules possessing desirable properties. The predictive models for log K of lanthanides complexation in water have been developed. Some new uranyl binders based on monoamides and on phosphoryl-containing podands were suggested theoretically, then synthesized and tested experimentally. Reasonable agreement between experimental uranyl distribution coefficients and theoretically predicted values has been observed.

Individual Hydrogen‐Bond Strength QSPR Modelling with ISIDA Local Descriptors: a Step Towards Polyfunctional Molecules

Here, we introduce new ISIDA fragment descriptors able to describe “local” properties related to selected atoms or molecular fragments. These descriptors have been applied for QSPR modelling of the H‐bond basicity scale pKBHX, measured by the 1 : 1 complexation constant of a series of organic acceptors (H‐bond bases) with 4‐fluorophenol as the reference H‐bond donor in CCl4 at 298 K. Unlike previous QSPR studies of H‐bond complexation, the models based on these new descriptors are able to predict the H‐bond basicity of different acceptor centres on the same polyfunctional molecule. QSPR models were obtained using support vector machine and ensemble multiple linear regression methods on a set of 537 organic compounds including 5 bifunctional molecules. They were validated with cross‐validation procedures and with two external test sets. The best model displays good predictive performance on a large test set of 451 mono‐ and bifunctional molecules: a root‐mean squared error RMSE=0.26 and a determination coefficient R2=0.91. It is implemented on our website (http://infochim.u‐strasbg.fr/webserv/VSEngine.html) together with the estimation of its applicability domain and an automatic detection of potential H‐bond acceptors.

Predictive Models for Halogen-Bond Basicity of Binding Sites of Polyfunctional Molecules

Halogen bonding (XB) strength assesses the ability of an electron‐enriched group to be involved in complexes with polarizable electrophilic halogenated or diatomic halogen molecules. Here, we report QSPR models of XB of particular relevance for an efficient screening of large sets of compounds. The basicity is described by pKBI2, the decimal logarithm of the experimental 1 : 1 (B : I2) complexation constant K of organic compounds (B) with diiodine (I2) as a reference halogen‐bond donor in alkanes at 298 K. Modeling involved ISIDA fragment descriptors, using SVM and MLR methods on a set of 598 organic compounds. Developed models were then challenged to make predictions for an external test set of 11 polyfunctional compounds for which unambiguous assignment of the measured effective complexation constant to specific groups out of the putative acceptor sites is not granted. At this stage, developed models were used to predict pKBI2 of all putative acceptor sites, followed by an estimation of the predicted effective complexation constant using the ChemEqui program. The best consensus models perform well both in cross‐validation (root mean squared error RMSE=0.39–0.47 logKBI2 units) and external predictions (RMSE=0.49). The SVM models are implemented on our website (http://infochim.u‐strasbg.fr/webserv/VSEngine.html) together with the estimation of their applicability domain and an automatic detection of potential halogen‐bond acceptor atoms.