Learn More
A new method for molecular structure description is presented in which both electronic and topological characteristics are combined. The method makes use of the hydrogen-suppressed graph to represent the structure. The focus of the method is on the individual atoms and hydride groups of the molecular skeleton. An intrinsic atom value is assigned to each(More)
Four modeling techniques, using topological descriptors to represent molecular structure, were employed to produce models of human serum protein binding (% bound) on a data set of 1008 experimental values, carefully screened from publicly available sources. To our knowledge, this data is the largest set on human serum protein binding reported for QSAR(More)
The derivation of a new 3D QSAR field based on the electrotopological state (E-state) formalism is described. A complementary index and its associated field, the HE-state, describing the polarity of hydrogens is also defined. These new fields are constructed from a nonempirical index that incorporates electronegativity, the inductive influence of(More)
The connectivity index, easily computed by arithmetic and based upon the degree of connectedness at each vertex in the molecular skeleton, is shown to give highly significant correlations with water solubility of branched, cyclic, and straight-chain alcohols and hydrocarbons as well as with boiling points of alcohols. These correlations are superior to(More)
Three QSAR methods, artificial neural net (ANN), k-nearest neighbors (kNN), and Decision Forest (DF), were applied to 3363 diverse compounds tested for their Ames genotoxicity. The ratio of mutagens to non-mutagens was 60/40 for this dataset. This group of compounds includes >300 therapeutic drugs. All models were developed using the same initial set of 148(More)