Nitroaromatic compounds, consisting of at least one nitro group attached to an aromatic ring, are potentially mutagenic and/or carcinogenic.  Therefore, it is of practical importance to develop an in silico mode to predict their mutagenicity.  An in silico model was developed using the novel hierarchical support vector regression scheme to establish quantitative structure-activity relationship of a series of mutagenicity data (TA98 - S9).  The predictions by the HSVR model were found to be in good agreement with the experimental observations for those molecules in the training set, test set, and even outlier set.  When subjected to a variety of statistical validations, the developed HSVR model completely fulfilled the most stringent criteria.  In addition, various model cross-comparisons were also conducted.  The results indicate that this HSVR model is highly accurate, robust, and consistent.  Thus, it can be employed as a tool for predicting mutagenicity of nitroaromatic compounds.

Predicting mutagenicity of nitroaromatic compounds using hierarchical support vector regression approach

248th National Meeting (2014)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.