Showing papers by "Gerardo M. Casañola-Martin published in 2011"

Vanilloid derivatives as tyrosinase inhibitors driven by virtual screening-based QSAR models.

Abstract: A number of vanilloids have been tested as tyrosinase inhibitors using Ligand-Based Virtual Screening (LBVS) driven by QSAR (Quantitative Structure-Activity Relationship) models as the multi-agent classification system. A total of 81 models were used to screen this family. Then, a preliminary cluster analysis of the selected chemicals was carried out based on their bioactivity to detect possible similar substructural features among these compounds and the active database used in the QSAR model construction. The compounds identified were tested in vitro to corroborate the results obtained in silico. Among them, two chemicals, isovanillin (K(M) (app) = 1.08 mM) near to kojic acid (reference drug) in one cluster and isovanillyl alcohol (K(M) (app) = 0.88 mM) at the same distance as hydroquinone (reference drug) in another cluster showed inhibitory activity against tyrosinase. The algorithm proposed here could result in a suitable approach for faster and more effective identification of hit and/or lead compounds with tyrosinase inhibitory activity, helping to shorten the long pipeline in the research of novel depigmenting agents to treat skin disorders.

Novel coumarin-based tyrosinase inhibitors discovered by OECD principles-validated QSAR approach from an enlarged, balanced database

Abstract: The present work is devoted to the development and application of a multi-agent Quantitative Structure-Activity Relationship (QSAR) classification system for tyrosinase inhibitor identification, in which the individual QSAR outputs are the inputs of a fusion approach based on the voting mechanism The individual models are based on TOMOCOMD-CARDD (TOpological Molecular COMputational Design-Computer Aided Rational Drug Design) atom-based bilinear descriptors and Linear Discriminant Analysis (LDA) on a novel enlarged, balanced database of 1,429 compounds within 701 greatly dissimilar molecules presenting anti-tyrosinase activity A total of 21 adequate models are obtained taking into account the requirements of the Organization for Economic Cooperation and Development (OECD) principles for QSAR validation and present global accuracies (Q) above 8450 and 7927% in the training and test sets, respectively The resulted fusion system is used for the in silico identification of synthesized coumarin derivatives as novel tyrosinase inhibitors The 7-hydroxycoumarin (compound C07) shows potent activity for the inhibition of monophenolase activity of mushroom tyrosinase giving a value of inhibition percentage close to 100% in vitro assays, by means of spectrophotometric analysis The current report could help to shed some clues in the identification of new chemicals that inhibit tyrosinase enzyme, for entering in the pipeline of drug discovery development

A Comparative Study of Nonlinear Machine Learning for the "In Silico" Depiction of Tyrosinase Inhibitory Activity from Molecular Structure

Abstract: In the preset report, for the first time, support vector machine (SVM), artificial neural network (ANN), Baye- sian networks (BNs), k-nearest neighbor (k-NN) are applied and compared on two "in-house" datasets to describe the tyrosinase inhibitory activity from the molecular structure. The data set Data I is used for the identification of tyrosi- nase inhibitors (TIs) including 701 active and 728 inactive compounds. Data II consists of active chemicals for potency estimation of TIs. The 2D TOMOCOMD-CARDD atom-based quadratic indices are used as molecular descriptors. The de- rived models show rather encouraging results with the areas under the Receiver Operating Characteristic (AURC) curve in the test set above 0.943 and 0.846 for the Data I and Data II, respectively. Multiple comparison tests are car- ried out to compare the performance of the models and reveal the improvement of machine learning (ML) tech- niques with respect to statistical ones (see Chemometr. Intell. Lab. Syst. 2010, 104, 249). In some cases, these ameli- orations are statistically significant. The tests also demo- strate that k-NN, despite being a rather simple approach, presents the best behavior in both data. The obtained re- sults suggest that the ML-based models could help to im- prove the virtual screening procedures and the confluence of these different techniques can increase the practicality of data mining procedures of chemical databases for the discovery of novel TIs as possible depigmenting agents.

Bond-extended stochastic and nonstochastic bilinear indices. I. QSPR/QSAR applications to the description of properties/activities of small-medium size organic compounds

Abstract: Bond-extended stochastic and nonstochastic bilinear indices are introduced in this article as novel bond-level molecular descriptors (MDs). These novel totals (whole-molecule) MDs are based on bilinear maps (forms) similar to use defined in linear algebra. The proposed nonstochastic indices try to match molecular structure provided by the molecular topology by using the kth Edge(Bond)-Adjacency Matrix (Ek, designed here as a nonstochastic E matrix). The stochastic parameters are computed by using the kth stochastic edge-adjacency matrix, ESk, as matrix operators of bilinear transformations. This new edge (bond)-adjacency relationship can be obtained directly from Ek and can be considered like a new matrix-transformation strategic to obtain new relations for a molecular graph. In both set of MDs, chemical information is codified by using different pair combinations of atomic weightings (in this case four atomic-labels: atomic mass, polarizability, van der Waals volume, and electronegativity). In addition, a local-fragment (bond-type) formalism was also developed. The kth bond-type bilinear indices are calculated by summing the kth bond bilinear indices of all bonds of the same bond type in the molecules. The new set of MDs can be easily and quickly calculated in our in house software TOMOCOMD-CARDD (topological molecular computational design computer-aided-rational-drug design). The reported application and utilization of these MDs for predictive capability correlations of structure with physicochemical and pharmacological properties are reviewed. Three benchmark datasets have been used to evaluate the QSPR/QSAR behavior of the new bond-level TOMOCOMD-CARDD MDs. We developed the QSPR models to describe several physicochemical properties of octane isomers (First Case) and, to analyze of the boiling point of 28 alkyl-alcohols (Second Case) and to examine of the specific rate constant (log k), the partition coefficient (log P), as well as the antibacterial activity of 34 derivatives of 2-furylethylenes (Third Case). For these three rounds, the quantitative models found are significant from a statistical point of view and permit a clear interpretation of the studied properties in terms of the structural features of molecules. A leave-one-out cross-validation procedure revealed that the regression models had a good predictability. The comparison with other approaches reveals good performance of the method proposed. Therefore, it is clearly demonstrated that this suitability is higher than that shown by other 2D/3D well-known sets of MDs. The approach described here appears to be a very promising structural invariant, useful for QSPR/QSAR studies and shown to provide an excellent alternative or guides for discovery and optimization of new lead compounds, reducing the time and cost of the traditional procedure. © 2009 Wiley Periodicals, Inc. Int J Quantum Chem, 2011