Description of oxygen permeability in various high polymers using a graph theoretical approach

Graph theory methods are shown to complement group additivity methods of predicting oxygen permeability in certain types of polymers. Graph theory is a topological approach that assigns a set of indices to a molecule to describe its structure. Since many physical properties of molecules depend upon their structure, graph theory indices can be used to describe important properties of molecules. In this work a set of graph theory indices are used to describe the property of a polymer based on a modified representation of the monomer unit. More specifically, Randic indices are used to describe the log of the oxygen permeability with 3.2% average relative error. Polymers comprising the basis set contain backbones of sp², sp³, or aromatic carbons, oxygen, or silicon and have substituents that contain chloride, fluoride, alkyl groups, hydrogen, oxygen, aromatic carbons, or chloro and/or fluoro substituted alkyl groups. The correlation coefficient (R²) (0 ≤ R² ≤ 1) of a nonlinear model is 0.91. The graph theory method for describing the oxygen permeability of these selected groups of polymers is in good agreement with that predicted by the permachor model. The permachor method makes oxygen permeability predictions based upon group additivity and distinguishes the degree of crystallinity of a polymer by empirically assigning different permachor (π) values to identical groups based upon the polymer crystallinity. The inability of graph theory to explain the remaining 9% of the scatter in the data is probably due to failure to incorporate into the graph theory model terms which quantify crystallinity.     

Artificial neural system modeling of Monte Carlo simulations of polymers

In this work, a neural network was used to learn features in potential energy surfaces and relate those features to conformational properties of a series of polymers. Specifically, we modeled Monte Carlo simulations of 20 polymers in which we calculated the characteristic ratio and the temperature coefficient of the characteristic ratio for each polymer. We first created 20 rotational potential energy surfaces using MNDO procedures and then used these energy surfaces to produce 10000 chains, each chain 100 bonds long. From these results we calculated the mean-square end-to-end distance, the characteristic ratio and its corresponding temperature coefficient. A neural network was then used to model the results of these Monte Carlo calculations. We found that artificial neural network simulations were highly accurate in predicting the outcome of the Monte Carlo calculations for polymers for which it was not trained. The overall average error for prediction of the characteristic ratio was 4,82%, and the overall average error for prediction of the temperature coefficient was 0,89%.     

A NEURAL NETWORK STUDY ON GLASS TRANSITION TEMPERATURE OF POLYMERS

In this paper, an atificial neural network model is adopted to study the glass transition temperature of polymers. Inour artificial neural networks, the input nodes are the characteristic ratio C_∞, the average molecular weigh M_e betweenentanglement points and the molecular weigh M_(mon) of repeating unit. The output node is the glass transition temperature T_g,and the number of the hidden layer is 6. We found that the artificial neural network simulations are accurate in predicting theoutcome for polymers for which it is not trained. The maximum relative error for predicting of the glass transitiontemperature is 3.47%, and the overall average error is only 2.27%. Artificial neural networks may provide some new ideas toinvestigate other properties of the polymers.     

Boiling Point of a Set of Alkanes,Alcohols and Chloroalkanes: QSAR with Atom Type Electrotopological State Indices Using Artificial Neural Networks

Abstract

The normal boiling point is modeled for a set of 372 saturated compounds, including 154 alkanes, 108 alcohols and 110 (poly)chloroalkanes. The newly introduced atom type electrotopological state indices serve as the structure variables and artificial neural networks (with back propagation of error) are used for the analysis. A network with a 6:7:1 architecture produces an average relative error of 0.97% for the whole data set, including the 21% of the data used as the test set. The mean absolute error (MAE) for this model is 4.00 for the whole set, corresponding to an rms error of 5.41; for the test set the MAE is 4.03 with an rms of 5.23. The low error on the test set indicates that this model has predictive power.     

Estimation of aqueous solubility for a diverse set of organic compounds based on molecular topology

An accurate and generally applicable method for estimating aqueous solubilities for a diverse set of 1297 organic compounds based on multilinear regression and artificial neural network modeling was developed. Molecular connectivity, shape, and atom-type electrotopological state (E-state) indices were used as structural parameters. The data set was divided into a training set of 884 compounds and a randomly chosen test set of 413 compounds. The structural parameters in a 30-12-1 artificial neural network included 24 atom-type E-state indices and six other topological indices, and for the test set, a predictive r2 = 0.92 and s = 0.60 were achieved. With the same parameters the statistics in the multilinear regression were r2 = 0.88 and s = 0.71, respectively.     

Experimental investigation and modeling of thermal conductivity of CuO–water/EG nanofluid by FFBP-ANN and multiple regressions

The purpose of this study is to predict the thermal conductivity of copper oxide (CuO) nanofluid by using feed forward backpropagation artificial neural network (FFBP-ANN). Thermal conductivity of CuO nanofluid is measured experimentally using transient hot-wire technique in temperature range of 20–60 °C and in volume fractions of 0.00125, 0.0025, 0.005 and 0.01% for neural network training and modeling. In addition, in order to evaluate accuracy of modeling in predicting the coefficient of nanofluid thermal conductivity, indices of root-mean-square error, coefficient of determination (R ²) and mean absolute percentage error have been used. FFBP-ANN with two input parameters (volume fraction and nanofluid temperature) and one output parameter (nanofluid thermal conductivity) in addition to two hidden layers and one outer layer which purelin, logsig and tansig functions are used was considered as the most optimum structure for modeling with neuron number of 4–10–1. In this study, among common methods of theoretical modeling of nanofluid thermal conductivity, theoretical method of Maxwell and also multivariate linear regression model was used for explaining the importance of modeling and predicting the results using neural network. According to this research, the results of indices and predictions show high accuracy and certainty of ANN modeling in comparison with empirical results and theoretical models.     

Prediction of polymer PVT behavior using the group contribution lattice-fluid EOS

A scheme has been developed using the group contribution lattice-fluid equation of state (GCLF-EOS) to predict the pressure-volume-temperature (PVT) behavior of polymers in the amorphous state. The model requires only the structure of the molecule as input information. Prediction results with an average error of 2% have been obtained for a wide variety of polymers. A table of 23 different group contributions is presented. With this set of group parameters, the GCLF-EOS can be applied in the prediction of equation of state properties of a wide variety of homopolymers, random copolymers, and polymer blends. © 1995 John Wiley & Sons, Inc.     

Prediction of n-octanol/water partition coefficients from PHYSPROP database using artificial neural networks and E-state indices

A new method, ALOGPS v 2.0 (http://www.lnh.unil.ch/~itetko/logp/), for the assessment of n-octanol/water partition coefficient, log P, was developed on the basis of neural network ensemble analysis of 12 908 organic compounds available from PHYSPROP database of Syracuse Research Corporation. The atom and bond-type E-state indices as well as the number of hydrogen and non-hydrogen atoms were used to represent the molecular structures. A preliminary selection of indices was performed by multiple linear regression analysis, and 75 input parameters were chosen. Some of the parameters combined several atom-type or bond-type indices with similar physicochemical properties. The neural network ensemble training was performed by efficient partition algorithm developed by the authors. The ensemble contained 50 neural networks, and each neural network had 10 neurons in one hidden layer. The prediction ability of the developed approach was estimated using both leave-one-out (LOO) technique and training/test protocol. In case of interseries predictions, i.e., when molecules in the test and in the training subsets were selected by chance from the same set of compounds, both approaches provided similar results. ALOGPS performance was significantly better than the results obtained by other tested methods. For a subset of 12 777 molecules the LOO results, namely correlation coefficient r(2)= 0.95, root mean squared error, RMSE = 0.39, and an absolute mean error, MAE = 0.29, were calculated. For two cross-series predictions, i.e., when molecules in the training and in the test sets belong to different series of compounds, all analyzed methods performed less efficiently. The decrease in the performance could be explained by a different diversity of molecules in the training and in the test sets. However, even for such difficult cases the ALOGPS method provided better prediction ability than the other tested methods. We have shown that the diversity of the training sets rather than the design of the methods is the main factor determining their prediction ability for new data. A comparative performance of the methods as well as a dependence on the number of non-hydrogen atoms in a molecule is also presented.     

Optimization of artificial neural networks used for retention modelling in ion chromatography

The aim of this work is the development of an artificial neural network model, which can be generalized and used in a variety of applications for retention modelling in ion chromatography. Influences of eluent flow-rate and concentration of eluent anion (OH-) on separation of seven inorganic anions (fluoride, chloride, nitrite, sulfate, bromide, nitrate, and phosphate) were investigated. Parallel prediction of retention times of seven inorganic anions by using one artificial neural network was applied. MATLAB Neural Networks ToolBox was not adequate for application to retention modelling in this particular case. Therefore the authors adopted it for retention modelling by programming in MATLAB metalanguage. The following routines were written; the division of experimental data set on training and test set; selection of data for training and test set; Dixon's outlier test; retraining procedure routine; calculations of relative error. A three-layer feed forward neural network trained with a Levenberg-Marquardt batch error back propagation algorithm has been used to model ion chromatographic retention mechanisms. The advantage of applied batch training methodology is the significant increase in speed of calculation of algorithms in comparison with delta rule training methodology. The technique of experimental data selection for training set was used allowing improvement of artificial neural network prediction power. Experimental design space was divided into 8-32 subspaces depending on number of experimental data points used for training set. The number of hidden layer nodes, the number of iteration steps and the number of experimental data points used for training set were optimized. This study presents the very fast (300 iteration steps) and very accurate (relative error of 0.88%) retention model, obtained by using a small amount of experimental data (16 experimental data points in training set). This indicates that the method of choice for retention modelling in ion chromatography is the artificial neural network.     

QSAR with experimental and predictive distributions: an information theoretic approach for assessing model quality

We propose that quantitative structure–activity relationship (QSAR) predictions should be explicitly represented as predictive (probability) distributions. If both predictions and experimental measurements are treated as probability distributions, the quality of a set of predictive distributions output by a model can be assessed with Kullback–Leibler (KL) divergence: a widely used information theoretic measure of the distance between two probability distributions. We have assessed a range of different machine learning algorithms and error estimation methods for producing predictive distributions with an analysis against three of AstraZeneca’s global DMPK datasets. Using the KL-divergence framework, we have identified a few combinations of algorithms that produce accurate and valid compound-specific predictive distributions. These methods use reliability indices to assign predictive distributions to the predictions output by QSAR models so that reliable predictions have tight distributions and vice versa. Finally we show how valid predictive distributions can be used to estimate the probability that a test compound has properties that hit single- or multi- objective target profiles.     

Surface interpenetrating networks of polyacrylamide in poly(ethylene terephthalate) as a means of surface modification

Surface interpenetrating network (IPN) polymers are emerging hybrid materials in which the surface of existing polymers can be modified to preserve their chemical structure and bulk properties. A detailed structural characterization of poly(ethylene terephthalate) (PET) thin films on nanoscopically flat silicon wafers has been carried out by Scanning Probe Microscopy (SPM) and X-ray photoelectron spectroscopy (XPS). Examination of the surface of spin-coated annealed PET film by the SPM in tapping mode revealed a two-phase structure. One phase appeared as a dense crystalline fraction of the polymer while the other was identified as amorphous. These findings were supported by Differential Scanning Calorimetry (DSC), which recognized the crystallinity of annealed PET film at 30%. Modification of the PET surface with interpenetrating polyacrylamide (PAM) increased the roughness of the surface with uniform properties. The depth profiling with XPS revealed that PAM interpenetration extended down to 7.2 nm, confirming a three-dimensional character of the polymer modification, with a relative mass concentration of PAM at about 30.7% in the IPN interface.     

芳香族化合物生物降解性的QSBR研究

分别采用线性基团贡献法和人工神经网络法对芳香族化合物的生物降解最大去除率QTOD进行QSBR研究。得到不同基团对生物降解性的贡献顺序为 :C6H5>COOH >OH >CO >CH3 >C1 >NH2>NO2 。线性基团贡献法对于训练组和测试组的预测正确率分别为 86%和 80 % ,总的预测正确率达85 % ;而人工神经网络法的预测正确率分别为 94%、80 %和 92 %。结果表明 ,线性基团贡献法和神经网络法的预测效果均很好 ,而神经网络法的预测更精确。     

Predicting chain dimensions from an artificial neural network model

Artificial neural network models are used to investigate polymer chain dimensions. In our model, the input nodes are glass transition temperature (T_g), entanglement molecular weight (M_e), and melt density (ρ). The number of nodes in the hidden layer is eight. We found that the relative error for prediction of the characteristic ratio ranges from 0.77 to 7.5% and that the overall average error is 3.57%. Artificial neural network models may provide a new method for studying statistics properties of polymer chains. © 2000 John Wiley & Sons, Inc. J Polym Sci B: Polym Phys 38: 3163–3167, 2000     

Crosslinking Index,Molecular Weight Distribution and Rubber Equilibrium Shear Modulus During Polyfunctional Crosslinking of Existing Polymer, 6. Primary Polymer with a Schulz–Zimm Distribution of Molecular Weights

A network model for the crosslinking of already existing polymer molecules with a so‐called Schulz–Zimm distribution of their molecular weights is presented. It is an extension of previously developed statistical network models applied to the crosslinking of primary polymers with several other molecular weight distributions and with crosslinks of any functionality. The model results in the possibility to obtain more insight into the structure of polymers, especially those with narrow distributions of the molecular weight. In more detail, the model can give a perspective on structural network parameters such as the weight fractions of ideal network, of dangling polymer ends, and of those molecules not connected to the network, i. e., the sol fraction, the number of crosslinks in which a polymer molecule is bound, the functionality of the crosslinks, or the average molar mass of the polymer molecules in between the crosslinks M̄_c. Results of calculations are shown for a hypothetical crosslinking process of polymers with various molecular weight distributions. Moreover, the dependency of the network parameters on the polydispersity index and the type of molecular weight distribution is shown. Finally the increase of the functionality of the crosslinks during the ageing process of a 9.9% poly(vinyl chloride) gel as a function of the polydispersity index of the molecular weight distribution is presented.     

Polymers with advanced structural and supramolecular features synthesized through topochemical polymerization

Polymers are an integral part of our daily life. Hence, there are constant efforts towards synthesizing novel polymers with unique properties. As the composition and packing of polymer chains influence polymer''s properties, sophisticated control over the molecular and supramolecular structure of the polymer helps tailor its properties as desired. However, such precise control via conventional solution-state synthesis is challenging. Topochemical polymerization (TP), a solvent- and catalyst-free reaction that occurs under the confinement of a crystal lattice, offers profound control over the molecular structure and supramolecular architecture of a polymer and usually results in ordered polymers. In particular, single-crystal-to-single-crystal (SCSC) TP is advantageous as we can correlate the structure and packing of polymer chains with their properties. By designing molecules appended with suitable reactive moieties and utilizing the principles of supramolecular chemistry to align them in a reactive orientation, the synthesis of higher-dimensional polymers and divergent topologies has been achieved via TP. Though there are a few reviews on TP in the literature, an exclusive review showcasing the topochemical synthesis of polymers with advanced structural features is not available. In this perspective, we present selected examples of the topochemical synthesis of organic polymers with sophisticated structures like ladders, tubular polymers, alternating copolymers, polymer blends, and other interesting topologies. We also detail some strategies adopted for obtaining distinct polymers from the same monomer. Finally, we highlight the main challenges and prospects for developing advanced polymers via TP and inspire future directions in this area.

This perspective showcases the potential of topochemical polymerization as an effective tool for synthesizing polymers with advanced molecular and supramolecular structures.     

A polarizable force field for water using an artificial neural network

A force field for liquid water including polarization effects has been constructed using an artificial neural network (ANN). It is essential to include a many-body polarization effect explicitly into a potential energy function in order to treat liquid water which is dense and highly polar. The new potential energy function is a combination of empirical and nonempirical potentials. The TIP4P model was used for the empirical part of the potential. For the nonempirical part, an ANN with a back-propagation of error algorithm (BPNN) was introduced to reproduce the complicated many-body interaction energy surface from ab initio quantum mechanical calculations. BPNN, described in terms of a matrix, provides enough flexibility to describe the complex potential energy surface (PES). The structural and thermodynamic properties, calculated by isobaric-isothermal (constant-NPT) Monte Carlo simulations with the new polarizable force field for water, are compatible with experimental results. Thus, the simulation establishes the validity of using our estimated PES with a polarization effect for accurate predictions of liquid state properties. Applications of this approach are simple and systematic so that it can easily be applied to the development of other force fields besides the water-water system.