Augmented three-mode MIA-QSAR Modeling for a series of anti-HIV-1 compounds

The bioactivities of a series of 2-amino-6-arylsulfonylbenzonitriles and their thio- and sulfinyl congeners have been previously modeled by using the MIA-QSAR approach and the PLS regression method [10]. The present work reports the significant improvement in the predication ability of the Multivariate Image Analysis applied to Quantitative Stucture-Activity Relationship (MIA-QSAR) model by applying Parallel Factor Analysis (PARAFAC) and Artificial Neural Network (ANN) directly to the three-way array built. This perspective represents an important advance for the accurate predication of potential drug candidates.