You are here:
DEVELOPMENT OF QUANTITATIVE STRUCTURE ACTIVITY RELATIONSHIPS (QSARS) TO PREDICT TOXICITY FOR A VARIETY OF HUMAN AND ECOLOGICAL ENDPOINTS
Citation:
YOUNG, D. M., T. M. MARTIN, P. F. HARTEN, R. VENKATAPATHY, AND S. DAS. DEVELOPMENT OF QUANTITATIVE STRUCTURE ACTIVITY RELATIONSHIPS (QSARS) TO PREDICT TOXICITY FOR A VARIETY OF HUMAN AND ECOLOGICAL ENDPOINTS. Presented at Society of Toxicology Annual Meeting, Charlotte, NC, March 25 - 29, 2007.
Impact/Purpose:
present information
Description:
In general, the accuracy of a predicted toxicity value increases with increase in similarity between the query chemical and the chemicals used to develop a QSAR model. A toxicity estimation methodology employing this finding has been developed. A hierarchical based clustering technique (based on Ward's method) will be used to generate a series of structurally similar groups of chemicals from a toxicity data set. The structural similarity will be defined in terms of more than 3000 physicochemical descriptors which include 2-dimensional descriptors (such as connectivity and E-state indices) and 3-dimensional descriptors (such as surface area and partial charges). A genetic algorithm based technique will be used to generate statistically valid QSAR models for each cluster (using the pool of descriptors described above). The toxicity for a given query compound will be estimated using the model generated from the cluster whose chemicals are the most structurally similar to the query compound. Initially the methodology described above will be used to develop QSAR models for the acute oral rat toxicity end point. Upon successful validation, the tool is expected to predict toxicities of chemicals for other cancer and non-cancer endpoints. The descriptor generation, clustering, and model building algorithms have been validated against commercial software. The toxicity models developed using the methodology in this study will be incorporated into a web-based software tool (written in Java). The tool will enable a user to easily predict the toxicity of a query compound by simply entering its structure in a 2-D chemical sketcher, entering a SMILES string, or entering a CAS number.