(569g) 3D Molecular Descriptors Relating Solvent Structure to Crystal Morphology: An Efficiency Study of PCA, GA and Ann Algorithms in QSPR Model Development

Datta, S., Auburn University
Herring, III, R., Auburn University
Eden, M., Auburn University

The paper outlines the development of a quantitative structure-property relationship (QSPR) that relates solvent structure to the morphology of ibuprofen crystals grown within that solvent. Morphology can be quantified by aspect ratio, and ibuprofen aspect ratio data was obtained for crystals grown in 16 different organic solvents. To provide a quantitative representation of the geometry optimized solvent molecules, 3D molecular descriptors were generated. Three different empirical force fields were used to estimate the three-dimensional structure of the solvent molecules while their effect on the developed models is analyzed. The descriptor data matrix, containing a multitude of descriptor types, is reduced in size, using Principal Component Analysis (PCA), Genetic algorithm (GA), Artificial Neural Network (ANN), and also combination of such algorithms for regression into linear models. The Singular Value Decomposition (SVD) procedure was used for PCA due to its increased stability in primary component prediction. The predictive capabilities of these models were also analyzed through means of internal and external validation methods.