Polynomial neural network for linear and non-linear model selection in quantitative-structure activity relationship studies on the internet

An Artificial Neural Network for Simulation of an Upflow Anaerobic Filter Wastewater Treatment Process

The purpose of this work was to develop a problem-solving approach and a simulation tool that is useful for the specification of wastewater treatment process equipment design parameters. The proposition of using an artificial neural network (ANN) numerical model for supervised learning of a dataset and then for process simulation on a new dataset was investigated. The effectiveness of the approach was assessed by evaluating the capacity of the model to distinguish differences in the equipment design parameters. To demonstrate the approach, a mock dataset was derived from experimentally acquired data and physical effects reported in the literature. The mock dataset comprised the influent flow rate, the bed packing material dimension, the type of packing material and the packed bed height-to-diameter ratio as predictors of the calorific value reduction. The multilayer perceptron (MLP) ANN was compared to a polynomial model. The validation test results show that the MLP model has four hidden layers, each having 256 units (nodes), accurately predicts calorific value reduction. When the model was fed previously unseen test data, the root-mean-square error (RMSE) of the predicted responses was 0.101 and the coefficient of determination (R2) was 0.66. The results of simulation of all 125 possible combinations of the 3 mechanical parameters and identical influent wastewater flow profiles were ranked according to total calorific value reduction. A t-test of the difference between the mean calorific value reduction of the two highest ranked experiments showed that the means are significantly different (p-value = 0.011). Thus, the model has the capacity to distinguish differences in the equipment design parameters. Consequently, the values of the three mechanical feature parameters from the highest ranked simulated experiment are recommended for use in the design of the industrial scale upflow anaerobic filter (UAF) for wastewater treatment.

Web-Based Quantitative Structure-Activity Relationship Resources Facilitate Effective Drug Discovery

Traditional drug discovery effectively contributes to the treatment of many diseases but is limited by high costs and long cycles. Quantitative structure-activity relationship (QSAR) methods were introduced to evaluate the activity of compounds virtually, which saves the significant cost of determining the activities of the compounds experimentally. Over the past two decades, many web tools for QSAR modeling with various features have been developed to facilitate the usage of QSAR methods. These web tools significantly reduce the difficulty of using QSAR and indirectly promote drug discovery. However, there are few comprehensive summaries of these QSAR tools, and researchers may have difficulty determining which tool to use. Hence, we systematically surveyed the mainstream web tools for QSAR modeling. This work may guide researchers in choosing appropriate web tools for developing QSAR models, and may also help develop more bioinformatics tools based on these existing resources. For nonprofessionals, we also hope to make more people aware of QSAR methods and expand their use.

Flame: an open source framework for model development, hosting, and usage in production environments

This article describes Flame, an open source software for building predictive models and supporting their use in production environments. Flame is a web application with a web-based graphic interface, which can be used as a desktop application or installed in a server receiving requests from multiple users. Models can be built starting from any collection of biologically annotated chemical structures since the software supports structural normalization, molecular descriptor calculation, and machine learning model generation using predefined workflows. The model building workflow can be customized from the graphic interface, selecting the type of normalization, molecular descriptors, and machine learning algorithm to be used from a panel of state-of-the-art methods implemented natively. Moreover, Flame implements a mechanism allowing to extend its source code, adding unlimited model customization. Models generated with Flame can be easily exported, facilitating collaborative model development. All models are stored in a model repository supporting model versioning. Models are identified by unique model IDs and include detailed documentation formatted using widely accepted standards. The current version is the result of nearly 3 years of development in collaboration with users from the pharmaceutical industry within the IMI eTRANSAFE project, which aims, among other objectives, to develop high-quality predictive models based on shared legacy data for assessing the safety of drug candidates.

Public (Q)SAR Services, Integrated Modeling Environments, and Model Repositories on the Web: State of the Art and Perspectives for Future Development

Thousands of (Quantitative) Structure-Activity Relationships (Q)SAR models have been described in peer-reviewed publications; however, this way of sharing seldom makes models available for the use by the research community outside of the developer's laboratory. Conversely, on-line models allow broad dissemination and application representing the most effective way of sharing the scientific knowledge. Approaches for sharing and providing on-line access to models range from web services created by individual users and laboratories to integrated modeling environments and model repositories. This emerging transition from the descriptive and informative, but "static", and for the most part, non-executable print format to interactive, transparent and functional delivery of "living" models is expected to have a transformative effect on modern experimental research in areas of scientific and regulatory use of (Q)SAR models.

In silico investigation of agonist activity of a structurally diverse set of drugs to hPXR using HM-BSM and HM-PNN

The human pregnane X receptor (hPXR) plays a critical role in the metabolism, transport and clearance of xenobiotics in the liver and intestine. The hPXR can be activated by a structurally diverse of drugs to initiate clinically relevant drug-drug interactions. In this article, in silico investigation was performed on a structurally diverse set of drugs to identify critical structural features greatly related to their agonist activity towards hPXR. Heuristic method (HM)-Best Subset Modeling (BSM) and HM-Polynomial Neural Networks (PNN) were utilized to develop the linear and non-linear quantitative structure-activity relationship models. The applicability domain (AD) of the models was assessed by Williams plot. Statistically reliable models with good predictive power and explain were achieved (for HM-BSM, r (2)=0.881, q LOO (2) =0.797, q EXT (2) =0.674; for HM-PNN, r (2)=0.882, q LOO (2) =0.856, q EXT (2) =0.655). The developed models indicated that molecular aromatic and electric property, molecular weight and complexity may govern agonist activity of a structurally diverse set of drugs to hPXR.

A GMDH-type neural network with multi-filter feature selection for the prediction of transition temperatures of bent-core liquid crystals

The QSPR study on transition temperatures of five-ring bent-core LCs was performed using GMDH-type neural networks. A novel multi-filter approach, which combines chi square ranking, v-WSH and GMDH algorithm was used for the selection of descriptors.

Material depth reconstruction method of multi-energy X-ray images using neural network

With the advent of technology, multi-energy X-ray imaging is promising technique that can reduce the patient's dose and provide functional imaging. Two-dimensional photon-counting detector to provide multi-energy imaging is under development. In this work, we present a material decomposition method using multi-energy images. To acquire multi-energy images, Monte Carlo simulation was performed. The X-ray spectrum was modeled and ripple effect was considered. Using the dissimilar characteristics in energy-dependent X-ray attenuation of each material, multiple energy X-ray images were decomposed into material depth images. Feedforward neural network was used to fit multi-energy images to material depth images. In order to use the neural network, step wedge phantom images were used for training neuron. Finally, neural network decomposed multi-energy X-ray images into material depth image. To demonstrate the concept of this method, we applied it to simulated images of a 3D head phantom. The results show that neural network method performed effectively material depth reconstruction.

Logical Analysis of Data in Structure-Activity Investigation of Polymeric Gene Delivery

To date semi-empirical or surrogate modeling has demonstrated great success in the prediction of the biologically relevant properties of polymeric materials. For the first time, a correlation between the chemical structures of poly(β-amino esters) and their efficiency in transfecting DNA was established using the novel technique of logical analysis of data (LAD). Linear combination and explicit representation models were introduced and compared in the framework of the present study. The most successful regression model yielded satisfactory agreement between the predicted and experimentally measured values of transfection efficiency (Pearson correlation coefficient, 0.77; mean absolute error, 3.83). It was shown that detailed analysis of the rules provided by the LAD algorithm offered practical utility to a polymer chemist in the design of new biomaterials.

Classification of drug molecules considering their IC50 values using mixed-integer linear programming based hyper-boxes method

BACKGROUND

A priori analysis of the activity of drugs on the target protein by computational approaches can be useful in narrowing down drug candidates for further experimental tests. Currently, there are a large number of computational methods that predict the activity of drugs on proteins. In this study, we approach the activity prediction problem as a classification problem and, we aim to improve the classification accuracy by introducing an algorithm that combines partial least squares regression with mixed-integer programming based hyper-boxes classification method, where drug molecules are classified as low active or high active regarding their binding activity (IC50 values) on target proteins. We also aim to determine the most significant molecular descriptors for the drug molecules.

RESULTS

We first apply our approach by analyzing the activities of widely known inhibitor datasets including Acetylcholinesterase (ACHE), Benzodiazepine Receptor (BZR), Dihydrofolate Reductase (DHFR), Cyclooxygenase-2 (COX-2) with known IC50 values. The results at this stage proved that our approach consistently gives better classification accuracies compared to 63 other reported classification methods such as SVM, Naïve Bayes, where we were able to predict the experimentally determined IC50 values with a worst case accuracy of 96%. To further test applicability of this approach we first created dataset for Cytochrome P450 C17 inhibitors and then predicted their activities with 100% accuracy.

CONCLUSION

Our results indicate that this approach can be utilized to predict the inhibitory effects of inhibitors based on their molecular descriptors. This approach will not only enhance drug discovery process, but also save time and resources committed.

Virtual computational chemistry laboratory--design and description

Internet technology offers an excellent opportunity for the development of tools by the cooperative effort of various groups and institutions. We have developed a multi-platform software system, Virtual Computational Chemistry Laboratory, http://www.vcclab.org, allowing the computational chemist to perform a comprehensive series of molecular indices/properties calculations and data analysis. The implemented software is based on a three-tier architecture that is one of the standard technologies to provide client-server services on the Internet. The developed software includes several popular programs, including the indices generation program, DRAGON, a 3D structure generator, CORINA, a program to predict lipophilicity and aqueous solubility of chemicals, ALOGPS and others. All these programs are running at the host institutes located in five countries over Europe. In this article we review the main features and statistics of the developed system that can be used as a prototype for academic and industry models.

Neural network studies. 4. Introduction to associative neural networks

Associative neural network (ASNN) represents a combination of an ensemble of feed-forward neural networks and the k-nearest neighbor technique. This method uses the correlation between ensemble responses as a measure of distance amid the analyzed cases for the nearest neighbor technique. This provides an improved prediction by the bias correction of the neural network ensemble. An associative neural network has a memory that can coincide with the training set. If new data becomes available, the network further improves its predictive ability and provides a reasonable approximation of the unknown function without a need to retrain the neural network ensemble. This feature of the method dramatically improves its predictive ability over traditional neural networks and k-nearest neighbor techniques, as demonstrated using several artificial data sets and a program to predict lipophilicity of chemical compounds. Another important feature of ASNN is the possibility to interpret neural network results by analysis of correlations between data cases in the space of models. It is shown that analysis of such correlations makes it possible to provide "property-targeted" clustering of data. The possible applications and importance of ASNN in drug design and medicinal and combinatorial chemistry are discussed. The method is available on-line at http://www.vcclab.org/lab/asnn.

Internet software for the calculation of the lipophilicity and aqueous solubility of chemical compounds

In this paper we describe an Internet Java-based technology that allows scientists to make their analytical software available worldwide. The implementation of this technology is exemplified by programs for the calculation of the lipophilicity and water solubility of chemical compounds available at http://www.lnh.unil.ch/~itetko/logp. Both these molecular properties are key parameters in quantitative structure-activity relationship studies and are used to provide invaluable information for the overall understanding of the uptake distribution, biotransformation, and elimination of a wide variety of chemicals. The compounds can be analyzed in batch or single-compound mode. The single-compound analysis offers the possibility to compare our results with several popular lipophilicity calculation methods, including CLOGP, KOWWIN, and XLOGP. The chemical compounds are analyzed according to SMILES line notation that can be prepared with the JME molecular editor of Peter Ertl. Conversion to SMILES from 56 formats is also available using the molecular structure information interchange hub developed by Pat Walters and Matt Stahl.