Predicting the Genotoxicity of Polycyclic Aromatic Compounds from Molecular Structure with Different Classifiers

• Published in: Chemical research in toxicology 2003-12, Vol.16 (12), p.1567-1580
• Main Authors: He, Linnan, Jurs, Peter C, Custer, Laura L, Durham, Stephen K, Pearl, Greg M
• Format: Article
• Language: English
• Subjects: Animals; Liver - drug effects; Liver - metabolism; Models, Chemical; Mutagens - chemistry; Mutagens - classification; Mutagens - metabolism; Mutagens - toxicity; Neural Networks (Computer); Polycyclic Aromatic Hydrocarbons - chemistry; Polycyclic Aromatic Hydrocarbons - classification; Polycyclic Aromatic Hydrocarbons - metabolism; Polycyclic Aromatic Hydrocarbons - toxicity; Probability; Rats; SOS Response (Genetics) - drug effects; SOS Response (Genetics) - genetics; Structure-Activity Relationship
• ISSN: 0893-228X; 1520-5010
• DOI: 10.1021/tx030032a

Classification models were developed to provide accurate prediction of genotoxicity of 277 polycyclic aromatic compounds (PACs) directly from their molecular structures. Numerical descriptors encoding the topological, geometric, electronic, and polar surface area properties of the compounds were calculated to represent the structural information. Each compound's genotoxicity was represented with IMAX (maximal SOS induction factor) values measured by the SOS Chromotest in the presence and absence of S9 rat liver homogenate. The compounds' class identity was determined by a cutoff IMAX value of 1.25compounds with IMAX > 1.25 in either test were classified as genotoxic, and the ones with IMAX ≤ 1.25 were nongenotoxic. Several binary classification models were generated to predict genotoxicity:  k-nearest neighbor (k-NN), linear discriminant analysis, and probabilistic neural network. The study showed k-NN to provide the highest predictive ability among the three classifiers with a training set classification rate of 93.5%. A consensus model was also developed that incorporated the three classifiers and correctly predicted 81.2% of the 277 compounds. It also provided a higher prediction rate on the genotoxic class than any other single model.