Neural networks coefficient

Another approach employing the autocorrelation coefficients as descriptors was suggested by Gasteiger et al, [22]. They used the neural networks as a working tool for solving a similarity problem. 

Molnar, L, Keserii, G. M., Papp A., Gulyas, Z., Darvas, F. A neural network based prediction of octanol-water partition coefficients using atomicS fragmental descriptors. Bioorg. Med. Chtm. Lett. 2004, 14, 851-853. 

Breindl, A., Beck, B., Qark, T., Glen, R. C. Prediction of the n-octanol/water partition coefficient, log P, using a combination of semiempirical MO-calculations and a neural network. J. Mol. Model. 1997, 3, 142-155. 

Chapter 17 - Vapor-liquid equilibrium (VLE) data are important for designing and modeling of process equipments. Since it is not always possible to carry out experiments at all possible temperatures and pressures, generally thermodynamic models based on equations on state are used for estimation of VLE. In this paper, an alternate tool, i.e. the artificial neural network technique has been applied for estimation of VLE for the binary systems viz. tert-butanol+2-ethyl-l-hexanol and n-butanol+2-ethyl-l-hexanol. The temperature range in which these models are valid is 353.2-458.2K at atmospheric pressure. The average absolute deviation for the temperature output was in range 2-3.3% and for the activity coefficient was less than 0.009%. The results were then compared with experimental data. 

Two neural networks have been used in this research. In the first network, the ANN input data is the mole fractions of liquid and vapor phases and the output is the activity coefficient of binary system. The experimental data and the estimated results of the activity coefficient are given in tables 3 and 4. 

The recurrent network models assume that the structure of the network, as well as the values of the weights, do not change in time. Moreover, only the activation values (i.e., the output of each processor that is used in the next iteration) changes in time. In the biochemical network one cannot separate outputs and weights. The outputs of one biochemical neurons are time dependent and enter the following biochemical neurons as they are. However, the coefficients involved in these biochemical processes are the kinetic constants that appear in the rate equations, and these constants are real numbers. The inputs considered in biochemical networks are continuous analog numbers that change over time. The inputs to the recurrent neural networks are sets of binary numbers. 

Coefficient of determination for a given training set standard error coefficient of determination for a given test set F-value number of observations and neural network. 

Another QSAR study utilizing 14 flavonoid derivatives in the training set and 5 flavonoid derivatives in the test set was performed by Moon et al. (211) using both multiple linear regression analysis and neural networks. Both statistical methods identified that the Hammett constant a, the HOMO energy, the non-overlap steric volume, the partial charge of C3 carbon atom, and the HOMO -coefficient of C3, C3, and C4 carbon atoms of flavonoids play an important role in inhibitory activity (Eqs. 3-5, Table 5). 

KNN)13 14 and potential function methods (PFMs).15,16 Modeling methods establish volumes in the pattern space with different bounds for each class. The bounds can be based on correlation coefficients, distances (e.g. the Euclidian distance in the Pattern Recognition by Independent Multicategory Analysis methods [PRIMA]17 or the Mahalanobis distance in the Unequal [UNEQ] method18), the residual variance19,20 or supervised artificial neural networks (e.g. in the Multi-layer Perception21). 

Gao, C., R. Govind, and H.H. Tabak. 1996. Prediction soil sorption coefficients of organic chemicals using a neural network model. Environ. Toxicol. Chem. 15(7) 1089-1096. 

When an accurate model of the reaction kinetics is not available (e.g., due to the lack of reliable data for identification), the previously developed approach may be ineffective and model-free strategies for the estimation of the effect of the heat released by the reaction, aq, must be adopted. In detail, the approach in [27] can be considered, where aq is estimated, together with the heat transfer coefficient, via a suitably designed nonlinear observer [24], Other model-free approaches can be adopted, e.g., those based on the adoption of universal interpolators (neural networks, polynomials) for the direct online estimation of the heat [16] and purely neural approaches [11], Approaches based on the combination of neural and model-based paradigms [2] or on tendency models [25] can be considered as well. 

Zheng, G., Huang, W.H., Lu, X.H. (2003) Prediction of n-octanol/water partition coefficients for polychlorinated dibenzo-p-dioxins using a general regression neural network. AnalBioanal. Chem. 376, 680-685. 

Quinones et al. (2000) reported the successful use of neural networks to predict the half-life of a series of 30 antihistamines. The input for the network was derived from the output of CODES, a routine that generates descriptors for a structure based on atom nature, bonding, and connectivity. Attempts to correlate the half-life with the physicochemical parameters log Kow, pKa, molecular weight, molar refractivity, molar volume, parachor, and polarity were unsuccessful. In a subsequent study by Quinones-Torrelo et al. (2001), the authors correlated the half-life of 18 antihistamines with their retention in a biopartitioning micellar chromatography system with a resultant correlation coefficient (R2adj) value of 0.89. The correlation is explained in that the retention in this system is dependent on hydrophobic, electronic, and steric properties, which are also important in determining half-life. 

Pedersen and Engelbrecht (1995) devised a neural network to analyze E. coli promoters. They predicted the transcriptional start point, measured the information content, and identified new features signals correlated with the start site. They accomplished these tasks by using two different encoding schemes, one with windows of 1 to 51 nucleotides, the other with a 65-nucleotide window containing a 7-nucleotide hole. An interesting idea in the study was to measure the relative information content of the input data by using the ability of the neural network to learn correctly, as evaluated by the maximum test correlation coefficient. 

Estimation of log P by using quantitative structure property relationships (QSPR) modeling and molecular descriptors (described above) has resulted in a number of highly accurate methods. Methods involving MLR, PLS, and artificial neural network ensembles (ANNE) modeling have been reviewed.In summary, estimation of partition coefficient has now reached a stage where the error associated with estimation is approximately equal to experimental error and reliable estimates can be obtained in silico. 

Chemometric methods such as analysis of correlation coefficients, cluster analysis or neural network analysis are used, for example, in the classification of fragments of glass on the basis of their elemental composition or refractive index. Such methods allow the test material to be classified into the appropriate group of products on the basis of the measured parameter. 

Duffythe group contribution approach of Klopman and the neural network model of Huuskonen. " The PCCHEM program used at the US Environmental Protection Agency (EPA) incorporates three different equations. All of them are similar to GSE but have different coefficients to predict aqueous solubility depending on the range of log P values. " Meylan and Howard used a database of 817 (RMSE = 0.62) compounds to derive a heuristic equation ... 

Bodor, N., Huang, M.-J. and Harget, A. (1994). Neural Network Studies. Part 3. Prediction of Partition Coefficients. J.Mol.Struct.(Theochem), 309,259-266. 

Grunenberg, J. and Herges, R. (1995). Prediction of Chromatographic Retention Values (Rm) and Partition Coefficients (log OCt) Using a Combination of Semiempirical Self-Consistent Reaction Field Calculations and Neural Networks. J.Chem.lnf.Comput.ScL,35, 905-911. 

The multiple linear regression models are validated using standard statistical techniques. These techniques include inspection of residual plots, standard deviation, and multiple correlation coefficient. Both regression and computational neural network models are validated using external prediction. The prediction set is not used for descriptor selection, descriptor reduction, or model development, and it therefore represents a true unknown data set. In order to ascertain the predictive power of a model the rms error is computed for the prediction set. 

The previous considered methods usually depend on linear methods (MLR, PLS) to establish structure-solubility correlations for prediction of solubility of molecules. The work of Goller et al. [51] used a neural network ensemble to predict the apparent solubility of Bayer in-house organic compounds. The solubility was measured in buffer at pH 6.5, which mimics the medium in the human gastrointestinal tract. The authors used the calculated distribution coefficient log/1 (at several pH values), a number of 3D COSMO-derived parameters and some 2D descriptors. The final model was developed using 4806 compounds (RMSE = 0.72) and provided a similar accuracy (RMSE = 0.73) for the prediction of 7222 compounds that were not used to develop the model. The method, however, is quite slow, and it takes about 15 seconds to screen one molecule on an Intel Xeon 2.8 GHz CPU. 

Huuskonen JJ, Livingstone DJ, Tetko IV. Neural network modeling for estimation of partition coefficient based on atom-type electrotopological state indices. I Chem Inf Comput Sci 2000 40 947-55. 

Tetko IV, Tanchuk VY, Villa AE. Prediction of H-octanol/water partition coefficients from PHYSPROP database using artificial neural networks and E-state indices. J Chem Inf Comput Sci 2001 41 1407-21. 

Figure 13 A two-layer neural network to solve the discriminant problem illustated in Figure 12. The weighting coefficients are shown adjacent to each connection and the threshold or bias for each neuron is given above each unit...

Figure 18 A neural network, comprising an input layer (I), a hidden layer (H), and an output layer (O). This is capable of correctly classifying the analytical data from Table 1. The required weighting coefficients are shown on each connection and the bias values for a sigmoidal threshold function are shown above each neuron...

Apparent error, of classification, 126 Artificial neural networks, 147 Assiociation coefficients, 96... 

---