Characterization of Mixtures Part 1: Prediction of Infinite‐Dilution Activity Coefficients Using Neural Network‐Based QSPR Models

The major problem in building QSAR/QSPR models for mixtures lies in their characterization. It has been shown that it is possible to construct QSPR models for the density of binary liquid mixtures using simple mole fraction weighted physicochemical descriptors. Such parameters are unsatisfactory; however, from the point of view of interpretation of the resultant models. In this paper, an alternative mechanism-based approach to the characterization of mixtures has been investigated. It has been shown that while it is not possible to build significant linear models using these descriptors, it has been possible to construct satisfactory artificial neural network models. The performance of these models and the importance of the individual descriptors are discussed.

[1]  David J. Livingstone,et al.  Application of QSPR to Mixtures , 2006, J. Chem. Inf. Model..

[2]  Gibbs Ensemble Simulations of Vapor/Liquid Equilibrium Using the Flexible RWK2 Water Potential , 2004 .

[3]  R. Carbó-Dorca,et al.  Estimation of infinite dilution activity coefficients of organic compounds in water with neural classifiers , 2004 .

[4]  A. Klamt,et al.  Prediction of infinite dilution activity coefficients using COSMO-RS , 2003 .

[5]  A. Tropsha,et al.  Development and validation of k-nearest-neighbor QSPR models of metabolic stability of drug candidates. , 2003, Journal of medicinal chemistry.

[6]  Chongli Zhong,et al.  A QSPR study of infinite dilution activity coefficients of organic compounds in aqueous solutions , 2003 .

[7]  Alexander Golbraikh,et al.  QSAR Modeling Using Chirality Descriptors Derived from Molecular Topology , 2003, J. Chem. Inf. Comput. Sci..

[8]  I. Economou.  Monte Carlo simulation of phase equilibria of aqueous systems , 2001 .

[9]  John N. Weinstein,et al.  Comparison of a Neural Net-Based QSAR Algorithm (PCANN) with Hologram- and Multiple Linear Regression-Based QSAR Approaches: Application to 1, 4-Dihydropyridine-Based Calcium Channel Antagonists , 2001, J. Chem. Inf. Comput. Sci..

[10]  Erich A. Müller,et al.  Molecular-Based Equations of State for Associating Fluids: A Review of SAFT and Related Approaches , 2001 .

[11]  J. Gmehling,et al.  Measurement of Activity Coefficients at Infinite Dilution in Solvent Mixtures Using the Dilutor Technique , 2000 .

[12]  Molecular Simulation of Phase Equilibria for Water−n-Butane and Water−n-Hexane Mixtures , 2000 .

[13]  J. Gmehling,et al.  Measurement of Activity Coefficients at Infinite Dilution Using Gas−Liquid Chromatography. 11. Results for Various Solutes with the Stationary Phases ε-Caprolactone and Ethyl Benzoate , 2000 .

[14]  Alexander Tropsha,et al.  Novel Variable Selection Quantitative Structure-Property Relationship Approach Based on the k-Nearest-Neighbor Principle , 2000, J. Chem. Inf. Comput. Sci..

[15]  P. Ghosh.  Prediction of Vapor‐Liquid Equilibria Using Peng‐Robinson and Soave‐Redlich‐Kwong Equations of State , 1999 .

[16]  Alexander P. Bünz,et al.  Application of quantitative structure-performance relationship and neural network models for the prediction of physical properties from molecular structure , 1998 .

[17]  Alan R. Katritzky,et al.  Correlation of the Aqueous Solubility of Hydrocarbons and Halogenated Hydrocarbons with Molecular Structure , 1998, J. Chem. Inf. Comput. Sci..

[18]  Peter C. Jurs,et al.  Prediction of Infinite Dilution Activity Coefficients of Organic Compounds in Aqueous Solution from Molecular Structure , 1998, J. Chem. Inf. Comput. Sci..

[19]  Jürgen Gmehling,et al.  Present status of group-contribution methods for the synthesis and design of chemical processes , 1998 .

[20]  A. Galindo,et al.  Predicting the Phase Equilibria of Mixtures of Hydrogen Fluoride with Water, Difluoromethane (HFC-32), and 1,1,1,2-Tetrafluoroethane (HFC-134a) Using a Simplified SAFT Approach , 1997 .

[21]  Andrew J. Dallas,et al.  Compilation and Correlation of Limiting Activity Coefficients of Nonelectrolytes in Water , 1996 .

[22]  K. Gasem,et al.  DETERMINATION OF INFINITE DILUTION ACTIVITY COEFFICIENTS FOR ORGANIC-AQUEOUS SYSTEMS USING A DILUTE VAPOR-LIQUID EQUILIBRIUM METHOD , 1995 .

[23]  Hsinchun Chen,et al.  Using Backpropagation Networks for the Estimation of Aqueous Activity Coefficients of Aromatic Organic Compounds , 1995, J. Chem. Inf. Comput. Sci..

[24]  D. Manallack,et al.  Statistics using neural networks: chance effects. , 1993, Journal of medicinal chemistry.

[25]  C. Eckert,et al.  Space predictor for infinite dilution activity coefficients , 1993 .

[26]  T. A. Andrea,et al.  Applications of neural networks in quantitative structure-activity relationships of dihydrofolate reductase inhibitors. , 1991, Journal of medicinal chemistry.

[27]  A. Fredenslund,et al.  UNIFAC and related group-contribution models for phase equilibria , 1989 .

[28]  J. Gmehling,et al.  A modified UNIFAC model. 1. Prediction of VLE, hE, and .gamma..infin. , 1987 .

[29]  Michael H. Abraham,et al.  Linear solvation energy relations , 1985 .

[30]  S. Wold,et al.  The Collinearity Problem in Linear Regression. The Partial Least Squares (PLS) Approach to Generalized Inverses , 1984 .

[31]  Charles A. Eckert,et al.  Prediction of limiting activity coefficients by a modified separation of cohesive energy density model and UNIFAC , 1984 .

[32]  Aage Fredenslund,et al.  Group‐contribution estimation of activity coefficients in nonideal liquid mixtures , 1975 .

[33]  J. Prausnitz,et al.  Activity Coefficients of Aromatic Solutes in Dilute Aqueous Solutions , 1971 .

[34]  D. Ambrose,et al.  Thermodynamic properties of organic oxygen compounds XXV. Vapour pressures and normal boiling temperatures of aliphatic alcohols , 1970 .

[35]  G. C. Benson,et al.  Excess thermodynamic properties of isopropanol–n-decanol mixtures , 1969 .

[36]  M. V. Winkle,et al.  Prediction of Infinite Dilution Activity Coefficients for Polar-Polar Binary Systems , 1968 .