Biomedical subjects

Marjan Vracko

Publications and source records attributed to Marjan Vracko.

9 recordsLinked to original sources

PubMed2004

Counter-propagation artificial neural network as a tool for the independent variable selection: structure-mutagenicity study on aromatic amines.

The counter-propagation artificial neural network (CP ANN) technique was applied for the independent variable selection and for structure-mutagenic potency modeling on a set of 95 aromatic and heteroaromatic amines with biological activity investigated experimentally by an in vitro assay. The molecular structures were represented by 275 independent variables classified as topostructural, topochemical, geometrical and quantum-chemical descriptors. As a result of the neural network modeling, the following descriptors were found to be the most important for structure-activity relationship: 5 chi -path connectivity index of order h = 5, 3chibC-bond cluster connectivity index of order h = 3, J(B)-Balaban's J index based on bond types, SHSNH2-electrotopological state index values for atoms, phia-flexibility index (kappa p1 x kappa p2/nvx), IC0-mean information content or complexity of a graph based on the 0 order neighborhood of vertices in a hydrogen-filled graph and ELUMO. The leave one out (LOO) method was used in order to test and select the models for mutagenicity prediction. The statistical parameters for the 7-descriptors model are R(Model) = 0.96 and Rcv = 0.85, respectively. In the next step, the number of variables was reduced and the 4-descriptors model was found (R(Model) = 0.95 and Rcv = 0.85) and classified as the best one.

Algorithms↗

PubMedDate not supplied

Modeling toxicity by using supervised kohonen neural networks.

Counterprogation neural network is shown to be a powerful and suitable tool for the investigation of toxicity. This study mined a data set of 568 chemicals. Two hundred eighty-two objects were used as the training set and 286 as the test set. The final model developed presents high performances on the data set R(2) = 0.83 (R(2) = 0.97 on the training set, R(2) = 0.59 on the test set). This technique distinguishes itself also for the ability to give to the expert two-dimensional maps suitable for the study of the distribution/clustering of the data and the identification of outliers.

Journal Article↗

PubMedDate not supplied

Classification of potential endocrine disrupters on the basis of molecular structure using a nonlinear modeling method.

A methodology for the classification of endocrine disruption chemicals is proposed. It is based on a data set of 106 substances extracted from the list of 553 chemicals that were inspected by the European Union Commission for the scientific evidence of their endocrine disruption activity. The substances belong to different categories defined in the EU Commission report: (i) literature evidence for certainly active as endocrine disrupters, (ii) for potentially active, (iii) for less probable active--lacking evidence, and (iv) for certainty nonactive. 3D molecular coordinates were calculated using the AM1or the PM3 optimization method. From 3D coordinates an extensive set of molecular descriptors was calculated. The classification model based on the counterpropagation neural network was constructed and evaluated. This is the first time that the counterpropagation neural network is applied for the classification of compounds regarding their literature evidence for the endocrine disruption activity. The developed classification model is proposed as a tool for a preliminary assessment of potential endocrine disrupters, which would help the assessors to make the priority list for a large amount of chemicals that have to be tested with more expensive in vitro and in vivo methods.

Journal Article↗

PubMedDate not supplied

Description of the electronic structure of organic chemicals using semiempirical and ab initio methods for development of toxicological QSARs.

The quality of quantitative structure-activity relationship (QSAR) models depends on the quality of their constitutive elements including the biological activity, statistical procedure applied, and the physicochemical and structural descriptors. The aim of this study was to assess the comparative use of ab initio and semiempirical quantum chemical calculations for the development of toxicological QSARs applied to a large and chemically diverse data set. A heterogeneous collection of 568 organic compounds with 96 h acute toxicity measured to the fish fathead minnow (Pimephales promelas) was utilized. A total of 162 descriptors were calculated using the semiempirical AM1 Hamiltonian, and 121 descriptors were compiled using an ab initio (B3LYP/6-31G**) method. The QSARs were derived using multiple linear regression (MLR) and partial least squares (PLS) analyses. Statistically similar models were obtained using AM1 and B3LYP calculated descriptors supported by the use of the logarithm of the octanol-water partition coefficient (log K(ow)). The main difference between the models derived by both MLR and PLS with the two sets of quantum chemical descriptors was concentrated on the type of descriptors selected. It was concluded that for large-scale predictions, irrespective of the mechanism of toxic action, the use of precise but time-consuming ab initio methods does not offer considerable advantage compared to the semiempirical calculations and could be avoided.

Animals↗

PubMedDate not supplied

Kohonen network study of aromatic compounds based on electronic and nonelectronic structure descriptors.

Atoms in Molecules (AIM) and Electron Localization Function (ELF) methodologies were applied to describe the electronic structure of 88 aromatic compounds. The analyzed database contains molecules substituted by nucleophilic and electrophilic groups which are responsible for electron density distribution in the molecule and further for its reactivity. Radial Distribution Function (RDF), Weighted Holistic Invariant Molecular (WHIM), Three-Dimensional Molecule Representation of Structures based on Electron Diffraction (3D-MoRSE) and Geometry, Topology and Atom-Weights Assembly (GETAWAY) descriptors were taken into account describing the structures of the analyzed molecules. According to generated descriptor space the classification of the molecules has been subsequently performed using unsupervised learning strategy and Kohonen network. The final step of descriptor space testing was supervised learning of Counter-Propagation Artificial Neural Network (CPANN) using n-octanol/water partition coefficient (logP), dipole moment (DM) and molecular refractivity (MR) as target values.

Journal Article↗

PubMedDate not supplied

Novel characterization of proteomics maps by sequential neighborhoods of protein spots.

We consider a characterization of proteomics maps based on an alternative kind of neighborhood graphs for the protein spots on 2-D gel. The novel approach considers for every protein spot only the nearest neighborhood consisting of protein spots of higher abundance. The approach has the simplicity and advantages of the recently introduced characterization of proteome maps based on considering the nearest neighborhoods of protein spots, but it also has important additional desirable computational features. The characterization of the nearest neighborhood graphs of 2-D gel proteomics maps is sensitive to the number of spots considered and may lead to changes in the degree of similarity of different maps when the number of points has been changed, thus imposing restrictions on the protocol used for comparison of maps. The novel approach presented in this work is less sensitive to the number of points used in the analysis because graphs are constructed in a stepwise process in which the role of more distant neighbors has been diminished by linking a new spot to the nearest spot that has been already part of the neighborhood graph. In this way a graph with N + 1 spots is obtained from the graph on N spots by adding a single new link, while in the case of the nearest neighborhood graphs adding a new spot introduces novel neighborhoods and generally results in a graph that may differ significantly from the neighborhood graph on N points.

Animals↗

PubMedDate not supplied

Proteomic maps-toxicity relationship of halocarbons studied with similarity index and genetic algorithm.

In this work we analyzed proteomic maps obtained from hepatocytes, which were treated with 14 halocarbons. A similarity index was introduced as a robust measure of similarity between two maps or between two selections of spots within the maps. A searching algorithm was used to identify the spots that may play an important role in toxicity mechanism. The highest correlation coefficients obtained between the similarity index and biological parameter were larger than 0.9.

Algorithms↗

PubMedDate not supplied

On characterization of dose variations of 2-D proteomics maps by matrix invariants.

We explore the characterization of 2-D electrophoresis proteomics maps by certain structural invariants derived from matrixes constructed by considering for all pairs of spots in a proteomics maps the shortest (Euclidean) distances and distances measured along zigzag lines connecting protein spots of the neighboring abundance. This paper is a sequel to previous papers in which we outlined the idea of characterizing 2-D proteomics maps by graph-theoretical descriptors. To illustrate the approach, we selected data of Anderson et al. (Anderson, N. L.; Esquer-Blasco, R.; Richardson, F.; Foxworthy, P.; Eacho, P. The effects of peroxisome proliferators on protein abundances in mouse liver. Toxicol. Appl. Pharmacol. 1996, 137, 75-89) on protein abundance in mouse liver under a series of dose of peroxisome proliferator LY1711883. We found strong linear correlation between the experimentally applied doses and the leading eigenvalue of a D/D-type matrix (Randić, M.; Kleiner, A. F.; DeAlba, L. M. Distance/ distance matrices. J. Chem. lnf. Comput. Sci. 1994, 34, 277-286) constructed for the experimental proteomics maps.

Acetophenones↗

PubMedDate not supplied

ANVAS: artificial neural variables adaptation system for descriptor selection.

A new algorithm model-oriented for variable selection is presented in this study. It is based on the combination of genetic algorithms (GA) for hyperspace exploration, and counterpropagation artificial neural network (CP ANN) for deriving the fitness score. The proposed method performed very well on both well defined synthetic data sets and real academic data sets.

Algorithms↗