Simplified,interpretable graph convolutional neural networks for small molecule activity prediction

Journal of Computer-Aided Molecular Design - We here present a streamlined, explainable graph convolutional neural network (gCNN) architecture for small molecule activity prediction. We first...     

Prediction of the antimicrobial activity of quaternary ammonium salts against Staphylococcus aureus using artificial neural networks

The study of the quantitative structure–activity relationship (QSAR) on antibacterial activity in a series of new imidazole derivatives against Staphylococcus aureus was conducted using artificial neural networks (ANNs). Antibacterial activity against S. aureus was associated with a number of physicochemical and structural parameters of the examined imidazole derivatives. The designed regression and classification models were useful in determining the antibacterial properties of quaternary ammonium salts against S. aureus. The developed models of artificial neural networks were characterized by high predictability (93.57% accuracy of classification, regression model: training data R = 0.92, test data R = 0.92, validation data R = 0.91). ANNs are considered to be a useful tool in supporting the design of synthesis and further biological experiments in the logical search for new antimicrobial substances. Data analysis using ANNs enables the optimization and reduction of labor costs by narrowing the compound synthesis to achieve the desired properties.     

Exploration of 3D activity cliffs on the basis of compound binding modes and comparison of 2D and 3D cliffs

Activity cliffs are formed by pairs or groups of structurally similar compounds having large differences in potency and are focal points of structure-activity relationship (SAR) analysis. The choice of molecular representations is a critically important aspect of activity cliffs analysis. Thus far, activity cliffs have predominantly been defined on the basis of molecular graph or fingerprint representations. Herein we introduce 3D activity cliffs derived from comparisons of experimentally determined compound binding modes. The analysis of 3D activity cliffs is generally applicable to target proteins for which structures of multiple ligand complexes are available. For two popular targets, β-secretase 1 (BACE1) and factor Xa (FXa), public domain X-ray structures with bound inhibitors were collected. Crystallographic binding modes of inhibitors were systematically compared using a 3D similarity method taking conformational, positional, and atomic property differences into account. In addition, standard 2D similarity relationships were also determined. SAR information associated with individual compounds substantially changed when either bioactive conformations or 2D molecular graphs were used for similarity evaluation. 3D activity cliffs were identified for BACE1 and FXa inhibitor sets and systematically compared to 2D cliffs. It was found that less than 40% of 3D activity cliffs were conserved when 2D similarity was applied. The limited conservation of 3D and 2D cliffs provides further evidence for the strong molecule representation dependence of activity cliffs. Moreover, 3D cliffs represent a new class of activity cliffs that convey SAR information in ways that differ from graph-based similarity measures. In cases where sufficient structural information is available, the comparison of 3D and 2D cliffs is expected to aid in SAR analysis and mapping of critical binding determinants.     

Prediction of gas chromatographic retention indices by the use of radial basis function neural networks

A new method for the prediction of retention indices for a diverse set of compounds from their physicochemical parameters has been proposed. The two used input parameters for representing molecular properties are boiling point and molar volume. Models relating relationships between physicochemical parameters and retention indices of compounds are constructed by means of radial basis function neural networks. To get the best prediction results, some strategies are also employed to optimize the topology and learning parameters of the RBFNNs. For the test set, a predictive correlation coefficient R=0.9910 and root mean squared error of 14.1 are obtained. Results show that radial basis function networks can give satisfactory prediction ability and its optimization is less-time consuming and easy to implement.     

Fast predictions of liquid-phase acid-catalyzed reaction rates using molecular dynamics simulations and convolutional neural networks

The rates of liquid-phase, acid-catalyzed reactions relevant to the upgrading of biomass into high-value chemicals are highly sensitive to solvent composition and identifying suitable solvent mixtures is theoretically and experimentally challenging. We show that the complex atomistic configurations of reactant–solvent environments generated by classical molecular dynamics simulations can be exploited by 3D convolutional neural networks to enable accurate predictions of Brønsted acid-catalyzed reaction rates for model biomass compounds. We develop a 3D convolutional neural network, which we call SolventNet, and train it to predict acid-catalyzed reaction rates using experimental reaction data and corresponding molecular dynamics simulation data for seven biomass-derived oxygenates in water–cosolvent mixtures. We show that SolventNet can predict reaction rates for additional reactants and solvent systems an order of magnitude faster than prior simulation methods. This combination of machine learning with molecular dynamics enables the rapid, high-throughput screening of solvent systems and identification of improved biomass conversion conditions.

Solvent-mediated, acid-catalyzed reaction rates relevant to the upgrading of biomass into high-value chemicals are accurately predicted using a combination of molecular dynamics simulations and 3D convolutional neural networks.     

人工神经网络预测煤炭成浆浓度的研究

考虑煤炭的多种理化特性建立了成浆浓度的神经网络预测模型,对其数据预处理方法、学习率和中间层节点数等进行了深入讨论。水分、挥发分、分析基碳、灰分和氧等五个因子对于煤炭成浆性的预测起到主导作用。五因子、七因子和八因子神经网络模型对煤炭成浆浓度的预测误差分别为：0.53%、0.50%和0.74%,而现有回归分析方程的误差为1.15%,故神经网络模型比回归分析方程有更好的预测能力,尤以七因子模型最佳。     

Prediction of the activity concentrations of 232Th, 238U and 40K in geological materials using radial basis function neural network

In this paper, three individual models and one generalized radial basis function neural network (RBFNN) model were developed for the prediction of the activity concentrations of primordial radionuclides, namely, ²³²Th, ²³⁸U and ⁴⁰K. To achieve this, gamma spectrometry measurements of 126 different geological materials were used in the development of the RBFNN models. The results indicated that individual and generalized RBFNN models are quite efficient in predicting the activity concentrations of ²³²Th, ²³⁸U and ⁴⁰K of geological materials.

     

Prediction of electrophoretic mobilities of sulfonamides in capillary zone electrophoresis using artificial neural networks

Artificial neural networks (ANNs) were successfully developed for the modeling and prediction of electrophoretic mobility of a series of sulfonamides in capillary zone electrophoresis. The cross-validation method was used to evaluate the prediction ability of the generated networks. The mobility of sulfonamides as positively charged species at low pH and negatively charged species at high pH was investigated. The results obtained using neural networks were compared with the experimental values as well as with those obtained using the multiple linear regression (MLR) technique. Comparison of the results shows the superiority of the neural network models over the regression models.     

The recognition of selected burning liquids by convolutional neural networks under laboratory conditions

Journal of Thermal Analysis and Calorimetry - This paper deals with the recognition of selected burning liquids by convolutional neural networks (CNNs). Three CNNs (AlexNet, GoogLeNet and...     

Prediction of electrophoretic mobilities of alkyl- and alkenylpyridines in capillary electrophoresis using artificial neural networks

A gas chromatographic method to determine thymol, eucalyptol (cineole), menthol and camphor residues in honey and beeswax is proposed. To isolate the compounds, three methods involving liquid-liquid extraction with methylene chloride, distillation, or solid-phase extraction on octadecylsilica cartridges can be used. The GC separation is carried out on a 60 m x 0.53 mm Stabilwax DA capillary column, using a flame ionization detector. The method is applied to the analysis of natural honey and also honey and beeswax samples from beehives treated with the above compounds.     

Systematic identification and classification of three-dimensional activity cliffs

Activity cliffs were systematically extracted from public domain X-ray structures of targets for which complexes with multiple ligands were available, following the concept of three-dimensional (3D) cliffs. Binding modes of ligands with well-defined potency measurements were compared in a pairwise manner, and their 3D similarity was calculated using a previously reported property density function-based method taking conformational, positional, and chemical differences into account. Requiring the presence of at least 80% 3D similarity and a potency difference of at least 2 orders of magnitude as cliff criteria, a total of 216 well-defined 3D activity cliffs were detected in the Protein Data Bank (PDB). These 3D-cliffs involved a total of 269 ligands active against 38 different targets belonging to 17 protein families. For 255 of these compounds, binding modes were available at high crystallographic resolution. All 3D-cliffs were analyzed in detail and assigned to different categories on the basis of crystallographic interaction patterns. In many instances, differences in ligand-target interactions suggested plausible causes for origins of 3D-cliffs. In other cases, short-range interactions seen in X-ray structures were insufficient to deduce possible reasons for cliff formation. The 3D-cliffs described herein further advance the rationalization of activity cliffs at the level of ligand-target interactions and should also be useful for other applications such as the calibration of energy functions for structure-based design. The pool of identified activity cliffs is provided to enable subsequent structure-based analyses of cliffs.