ABSTRACT
Holographic quantitative structure-activity relationship (HQSAR) is an emerging QSAR technique with the combined application of molecular hologram, which encoded the frequency of occurrence of various molecular fragment types, and the subsequent partial least squares (PLS) regression analysis. In this paper, the acute toxicity data to the guppy (Poecilia reticulata) for a series of 56 substituted benzenes, phenols, aromatic amines and nitro-aromatics were subjected and this resulted in a model with a high predictive ability. The influence of fragment size and fragment distinction parameters on the quality of HQSAR model was investigated. The robustness and predictive ability of the model were also validated by leave-one-out (LOO) cross-validation procedure and external testing data set.