Classification of estrogen receptor-beta ligands on the basis of their binding affinities using support vector machine and linear discriminant analysis.

Classification models of estrogen receptor-beta ligands were proposed using linear and nonlinear models. The data set was divided into active and inactive classes on the basis of their binding affinities. The two-class problem (active, inactive) was firstly explored by linear classifier approach, linear discriminant analysis (LDA). In order to get a more accurate prediction model, the nonlinear novel machine learning technique, support vectors machine (SVM), was subsequently used to investigate. The heuristic method (HM) was used to pre-select the whole descriptor sets. The model containing eight descriptors founded by SVM, showed better predictive ability than LDA. The accuracy in prediction for the training, test and overall data sets are 92.9%, 85.8% and 91.4% for SVM, 83.1%, 76.1% and 81.9% for LDA, respectively. The results indicate that SVM can be used as a powerful modeling tool for QSAR studies.

QSPR analysis of air-to-blood distribution of volatile organic compounds.

Quantitative structure property relationship (QSPR) models for the prediction of human blood:air partition coefficient (log K(blood)) of volatile organic compounds (VOCs) has been developed based on the linear heuristic method (HM) and non-linear radial basis function neural networks (RBFNNs). Molecular descriptors that are calculated from the structures alone were used to represent the characteristics of the compounds. HM was used both to pre-select the whole descriptor sets and to build the linear model. RBFNN was performed to obtain more accurate models. Both the linear and the non-linear models can give very satisfactory prediction results: the correlation coefficient R was 0.964 and 0.979, and the root-mean-square (RMS) error was 0.3303 and 0.2542 for the whole data set, respectively. The prediction result of the non-linear model is better than that obtained by the linear model. In addition, this paper provides an effective method for predicting log K(blood) from its structures and gives some insight into the structural features related to the solubility of VOCs in human blood.

Prevention of adhesions in the temporomandibular joint by the use of chitosan membrane in goats.

We evaluated the effects of chitosan membrane, a highly absorbable and viscous material, in the prevention of intra-articular adhesions after anchoring of the disc in the temporomandibular joints (TMJ) of six adult goats (12 joints). To simulate anterior displacement of the disc and TMJ trauma, we cut off the retrodiscal attachment and damaged the surface of the condylar bone, then randomly divided the goats into two groups: the control group (n=2) and the experimental group (n=4). In the experimental group we covered the condylar surfaces on both sides of the animals with chitosan membranes. Those in the control group had operations and no special treatment. We took magnetic resonance images (MRI) of all the animals before the operation and at three and six months postoperatively, and measured the interincisal opening and strength at the same time. We counted the number of adhesions macroscopically, and evaluated the adhesive tissues, cartilage, and subchondral bony changes histologically and immunohistochemically. Measurements of the interincisal opening and strength were significantly better in the experimental group than in the controls (p<0.05). Macroscopic evaluation (using a specific adhesion scoring system) showed a significant difference in the formation of adhesions between the groups (p<0.05). Although MRI showed no significant difference between the groups, the histological and immunohistochemical observations supported the hypothesis that chitosan membrane could prevent intra-articular adhesions. It seems to inhibit the formation of adhesions effectively and promote repair of the cartilage. It may therefore be considered a promising absorbable biomaterial to prevent adhesions after operations on the TMJ.

Application of support vector machine (SVM) for prediction toxic activity of different data sets.

As a new method, support vector machine (SVM) were applied for prediction of toxicity of different data sets compared with other two common methods, multiple linear regression (MLR) and RBFNN. Quantitative structure-activity relationships (QSAR) models based on calculated molecular descriptors have been clearly established. Among them, SVM model gave the highest q(2) and correlation coefficient R. It indicates that the SVM performed better generalization ability than the MLR and RBFNN methods, especially in the test set and the whole data set. This eventually leads to better generalization than neural networks, which implement the empirical risk minimization principle and may not converge to global solutions. We would expect SVM method as a powerful tool for the prediction of molecular properties.

Quantitative structure-activity relationship models for prediction of sensory irritants (logRD50) of volatile organic chemicals.

Quantitative classification and regression models for prediction of sensory irritants (logRD50) of volatile organic chemicals (VOCs) have been developed. Each compound was represented by the calculated structural descriptors to encode constitutional, topological, geometrical, electrostatic, and quantum-chemical features. The heuristic method (HM) was then used to search the descriptor space and select the descriptors responsible for activity. The best classification results were found using support vector machine (SVM): the accuracy for training, test and overall data set is 96.5%, 85.7% and 94.4%, respectively. The nonlinear regression models were built by radial basis function neural networks (RNFNN) and SVM, respectively. The root mean squared errors (RMS) in prediction for the training, test and overall data set are 0.4755, 0.6322 and 0.5009 for reactive group, 0.2430, 0.4798 and 0.3064 for nonreactive group by RBFNN. The comparative results obtained by SVM are 0.4415, 0.7430 and 0.5140 for reactive group, 0.3920, 0.4520 and 0.4050 for nonreactive group, respectively. This paper proposes an effective method for poisonous chemicals screening and considering.

Elucidation of chiral recognition processes of macrocyclic antibiotic vancomycin.

A theoretical investigation was carried out on the retention and separation of enantiomeric molecules including nonsteroidal anti-inflammatory drugs, anti-neoplastic compounds and N-derivatized amino acids by capillary electrophoresis using macrocyclic antibiotics, a new class of chiral selectors, as stationary phase. Firstly docking methods were used to study the enantiorecognition in chiral electrophoresis. The molecular dynamics simulations of the two diastereoisomer complexes were then performed in order to understand how these antibiotics recognize the enantiomers. Another approach was applied in this study to establish a quantitative structure-enantioselectivity relationship (QSER) model, able to describe the resolution of a series of chiral compounds in capillary electrophoresis using vancomycin as the resolving agent.

MolDIA: XML based system of molecular diversity analysis towards virtual screening and QSPR.

In this paper a new chemoinformatics tool for Molecular Diversity Analysis (MolDIA) is introduced. The objective of this system is the analysis of molecular similarity and diversity through the treatment of structural and physicochemical information. Current needs for chemical databases include the analysis, the management and the retrieval of chemical information. The implementation of eXtended Markup Languages (XML) is proposed as a basis for representing and structuring the chemical information contained in data structures and databases. The adequate descriptor vector and related physicochemical properties have been defined and constructed. The benefits of XML in chemoinformatics are discussed, as well as, the applications of this system in a virtual screening environment.

Quantitative structure-toxicity relationships (QSTRs): a comparative study of various non linear methods. General regression neural network, radial basis function neural network and support vector machine in predicting toxicity of nitro- and cyano- aromatics to Tetrahymena pyriformis.

Prediction of toxicity of 203 nitro- and cyano-aromatic chemicals to Tetrahymena pyriformis was carried out by radial basis function neural network, general regression neural network and support vector machine, in non-linear response surface methodology. Toxicity was predicted from hydrophobicity parameter (log Kow) and maximum superdelocalizability (Amax). Special attention was drawn to prediction ability and robustness of the models, investigated both in a leave-one-out and 10-fold cross validation (CV) processes. The influence that the corresponding changes in the learning sets during these CV processes could have on a common external test set including 41 compounds was also examined. This allowed us to establish the stability of the models. The non linear results slightly outperform (as expected) multilinear relationships (MLR) and also favourably compete with various other non linear approaches recently proposed by Ren (J. Chem. Inf. Comput. Sci., 43 1679 (2003)).

Potential study of basement membrane.

The membrane potential of a basement membrane (bovine-anterior-lens-capsule) was studied by use of the Gibbs-Donnan systems. The T.M.S. (Teorell, Meyer, Sievers) theory was applied to these systems for the treatment of experimental data. The results show that, in the basement membrane, the density of fixed charges such as ionogenic groups encountered in heparan sulfate proteoglycan is low. The ratios of the mobilities from the chloride anion and the alkaline cation are different to those in water. In this type of membrane, the mobility of Cl- is higher than the mobilities of K+, Na+ and Ca2+. This result leads us to investigate further the diffusion problem of electrolytes through basement membrane.

Study of probabilistic neural networks to classify the active compounds in medicinal plants.

Probabilistic neural networks (PNNs) were utilized for the classifications of 102 active compounds from diverse medicinal plants with anticancer activity against human rhinopharyngocele cell line KB. Molecular descriptors calculated from structure alone were used to represent molecular structures. A subset of the calculated descriptors selected using factor correlation analysis and forward stepwise regression was used to construct the prediction models. Linear discriminant analysis (LDA) was also utilized to construct the classification model to compare the results with those obtained by PNNs. The accuracy of the training set, the cross-validation set, and the test set given by PNNs and LDA were 100, 92.3, 90.9% and 71.8, 92.3, 54.5%, respectively, which indicated that the results obtained by PNNs agree well with the experimental values of these compounds and also revealed the superiority of PNNs over LDA approach for the classification of anticancer activities of compounds. The models built in this work would be of potential help in the design of novel and more potent anticancer agents.

QSAR study of natural, synthetic and environmental endocrine disrupting compounds for binding to the androgen receptor.

A large data set of 146 natural, synthetic and environmental chemicals belonging to a broad range of structural classes have been tested for their relative binding affinity (expressed as log (RBA)) to the androgen receptor (AR). These chemicals commonly termed endocrine disrupting compounds (EDCs) present a variety of adverse effects in humans and animals. As assays for binding affinity remains a time-consuming task, it is important to develop predictive methods. In this work, quantitative structure-activity relationships (QSARs) were determined using three methods, multiple linear regression (MLR), radical basis function neural network (RBFNN) and support vector machine (SVM). Five descriptors, accounting for hydrogen-bonding interaction, distribution of atomic charges and molecular branching degree, were selected from a heuristic method to build predictive QSAR models. Comparison of the results obtained from three models showed that the SVM method exhibited the best overall performances, with a RMS error of 0.54 log (RBA) units for the training set, 0.59 for the test set, and 0.55 for the whole set. Moreover, six linear QSAR models were constructed for some specific families based on their chemical structures. These predictive toxicology models, should be useful to rapidly identify potential androgenic endocrine disrupting compounds.

3D QSAR studies on antimalarial alkoxylated and hydroxylated chalcones by CoMFA and CoMSIA.

The 3D QSAR analyses of antimalarial alkoxylated and hydroxylated chalcones were first conducted by Comparative molecular field analysis (CoMFA) and Comparative similarity indices analysis (CoMSIA) to determine the factors required for the activity of these compounds. Satisfactory results were obtained after performing a leave-one-out (LOO) cross-validation study with cross-validation q(2) and conventional r(2) values of 0.740 and 0.972 by the CoMFA model, 0.714 and 0.976 by the CoMSIA model, respectively. The results provided the tools for predicting the affinity of related compounds, and for guiding the design and synthesis of novel and more potent antimalarial agents.

Predicting the standard enthalpy (deltaH0f) and entropy (S0) of alkanes by artificial neural networks.

Artificial Neural Networks (ANNs) with Extended Delta-Bar-Delta (EDBD) back propagation learning algorithm have been developed to predict the standard enthalpy and entropy of 87 acyclic alkanes. Molecular weight, boiling point and density of the compounds were used as input parameters. The network's architecture and parameters were optimized to give maximum performances. The best network was a 3-6-2 ANN, and the optimum learning epoch was about 1320. The results show that the maximum relative errors of enthalpy and entropy are less than 3%. They reveal that the performances of ANNs for predicting the enthalpy and entropy of alkanes are satisfying.

Comparative study of non nucleoside inhibitors with HIV-1 reverse transcriptase based on 3D-QSAR and docking.

The intermolecular interaction between two types of non nucleoside reverse transcriptase inhibitors (NNRTIs), HEPT and TIBO, and HIV reverse transcriptase receptor (HIVRT) was investigated. The result of docking study showed that two types of NNRTIs presented similar interaction mechanism with HIVRT. The most active compound of every type of inhibitors could form one hydrogen bond with the residue Lys101 and has hydrophobic interaction with residues Tyr181, Tyr188 and Tyr318, etc. Three 3D-QSAR models including two partial correlation models (one for each family of HEPT and TIBO) and a mixed model gathering two families were constructed. Comparative study of these models indicated that the mixed model offered the strongest prediction ability. For this model, the cross-validated q2 values were 0.720 and 0.675, non-cross-validated r2 values were 0.940 and 0.920 for CoMFA and CoMSIA, respectively. It has been validated by using a test set of 27 inhibitors. Compared with previously reported works, our model showed better prediction ability. It could help us to insight the interaction between NNRTIs and HIVRT, and to design new anti-HIV NNRTIs inhibitors.

Docking study of cistanoside C to telomeric DNA fragment.

Experiments show that the natural products phenyl propanoid glycosides (PPGs) extracted from the plant Pedicularis spicata are capable of repairing DNA damaged by oxygen radicals. Based on kinetic measurements and experiments on tumor cells, a theoretical study of the interaction between PPG molecule Cistanoside C and telomeric DNA fragment has been carried out. The docking calculations performed using JUMNA software showed that the Cistanoside C could be docked into the minor groove of telomeric DNA and form complexes with the geometry suitable for an electron transfer between guanine radical and the ligand. Such complexes can be formed without major distortions of DNA structure and are further stabilized by the interaction with the saccharide side-groups.

CISOC-PSCT: a predictive system for carcinogenic toxicity.

A SAR based carcinogenic toxicity prediction system, CISOC-PSCT, was developed. It consisted of two principal phases: the construction of relationships between structural descriptors and carcinogenic toxicity indices, and prediction of the toxicity from the SAR model. The training set included 2738 carcinogenic and 4130 non-carcinogenic compounds. Three predefined topological types of substructures termed Star, Path and Ring were used to generate the descriptors for each structure in the training set. In this system, the defined carcinogenic toxicity index (CTI) was obtained from the probability of a structural descriptor to either belong to the carcinogenic or non-carcinogenic compounds. Based on these structural descriptors and their CTI, a SAR model was derived. Then the carcinogenic possibility (CP) and the carcinogenic impossibility (CIP) of compounds were predicted. The model was tested from a testing set of 304 carcinogenic compounds (MDL toxicity database), 460 non-carcinogenic compounds (CMC database) and 94 compounds extracted from two traditional Chinese medicine herbs.

Virtual screening and rational drug design method using structure generation system based on 3D-QSAR and docking.

An efficient virtual and rational drug design method is presented. It combines virtual bioactive compound generation with 3D-QSAR model and docking. Using this method, it is possible to generate a lot of highly diverse molecules and find virtual active lead compounds. The method was validated by the study of a set of anti-tumor drugs. With the constraints of pharmacophore obtained by DISCO implemented in SYBYL 6.8, 97 virtual bioactive compounds were generated, and their anti-tumor activities were predicted by CoMFA. Eight structures with high activity were selected and screened by the 3D-QSAR model. The most active generated structure was further investigated by modifying its structure in order to increase the activity. A comparative docking study with telomeric receptor was carried out, and the results showed that the generated structures could form more stable complexes with receptor than the reference compound selected from experimental data. This investigation showed that the proposed method was a feasible way for rational drug design with high screening efficiency.

Prediction of programmed-temperature retention values of naphthas by artificial neural networks.

It is proposed for the first time a method of prediction of the programmed-temperature retention times of components of naphthas in capillary gas chromatography using artificial neural networks. People are used to predict the programmed-temperature retention time using many formulas such as the integral formula, which requires that four parameters must be determined by calculation or experiments. However the results obtained by the formula are not so good to meet the demand of industry. In order to predict retention time accurately and conveniently, artificial neural networks using five-fold cross-validation and leave-20%-out methods have been applied. Only two parameters: density and isothermal retention index were used as input vectors. The average RMS error for predicted values of five different networks was 0.18, whereas the RMS error of predictions by the integral formula was 0.69. Obviously, the predictions by neural networks were much better than predictions by the formula, and neural networks need fewer parameters than the formula. So neural networks can successfully and conveniently solve the problem of predictions of programmed-temperature retention times, and provide useful data for analysis of naphthas in petrochemical industry.

Theoretical study of fast repair of DNA damage by cistanoside C and analogs: mechanism and docking.

Experiments show that the natural substances phenylpropanoid glycosides (PPGs) extracted from pelicularis spicata are capable of repairing DNA damaged by oxygen radicals. Based on kinetic measurements and experiments on tumor cells, a theoretical study of the interaction between PPG molecules and isolated DNA bases, as well as a DNA fragment has been performed. An interaction mechanism reported early has been refined. The docking calculations performed using junction minimization of nucleic acids (JUMNA) software showed that the PPG molecules can be docked into the minor groove of DNA and form complexes with the geometry suitable for an electron transfer between guanine radical and the ligand. Such complexes can be formed without major distortions of DNA structure and are further stabilized by the interaction with the rhamnosyl side-groups.

Scavenging effects of natural phenols on oxidizing intermediates of peroxynitrite.

Most of peroxynitrite (ONOO-/ONOOH) is formed via the diffusion-limited reaction between nitric oxide and superoxide. In biological systems, the decomposition of ONOO- yields 30-35% of carbonate radical (CO3*-) and nitrogen dioxide (NO2*), which are strongly oxidizing intermediates and are suggested to take a part of the responsibility for the toxicity of nitric oxide (NO*) or ONOO-. Therefore, the current study focuses on the scavenging activities of phenols toward CO3*- and NO2* to protect biomolecules from damage caused by NO* or ONOO- using the technique of pulse radiolysis. From the build-up kinetic of the phenoxyl radicals and the decay kinetic of CO3*- radical, the rate constants of scavenging reactions were determined to be 1.9-3.4 x 10(8) M(-1) x s(-1) and 0.11-1.9 x 10(8) M(-1) x s(-1) for CO3*- and NO2* respectively. The results indicated that the tested phenols are the efficient scavengers of CO3*- and NO2*.