Prediction of some important physical properties of sulfur compounds using quantitative structure-properties relationships

Mol Divers. Aug-Nov 2008;12(3-4):143-55. doi: 10.1007/s11030-008-9088-6. Epub 2008 Sep 20.

Abstract

In this work, physical properties of sulfur compounds (critical temperature (Tc), critical pressure (Pc), and Pitzer's acentric factor (omega)) are predicted using quantitative structure-property relationship technique. Sulfur compounds present in petroleum cuts are considered environmental hazards. Genetic algorithm based multivariate linear regression (GA-MLR) is used to select most statistically effective molecular descriptors on the properties. Using the selected molecular descriptors, feed forward neural networks (FFNNs) are applied to develop some molecular-based models to predict the properties. The presented models are quite accurate and can be used to predict the properties of sulfur compounds.

MeSH terms

  • Algorithms
  • Chemistry, Physical
  • Environmental Pollutants / chemistry
  • Linear Models
  • Molecular Structure
  • Multivariate Analysis
  • Neural Networks, Computer
  • Petroleum / analysis
  • Pressure
  • Sulfhydryl Compounds / chemistry
  • Sulfur Compounds / chemistry*
  • Temperature

Substances

  • Environmental Pollutants
  • Petroleum
  • Sulfhydryl Compounds
  • Sulfur Compounds