A radial-distribution-function approach for predicting rodent carcinogenicity

Carcinogenic activity has been investigated using the Radial-Distribution-Function (RDF) approach. A discriminant model was developed to predict the carcinogenic and non-carcinogenic activity on a data set of 188 compounds. The percentage of overall classification was 76.4% for the carcinogenic chemicals and 72.5% for the non-carcinogenic chemicals. The predictive power of the model was validated by two tests: a cross-validation by the resubstitution technique and a test set (compounds not used in the development of the model) with 79.3 and 72.5% good classification, respectively. The RDF descriptors were compared with eight other methodologies; Constitutional, Molecular walks counts, Galvez topological charge indices, 2D autocorrelations, Randić molecular profiles, Geometrical, 3D-MORSE, and WHIM, demonstrating that the RDF descriptors are better to the rest of the approaches used.