Neural Network Analysis of Chemical Compounds in Nonrebreathing Fisher-344 RatBreath

摘要

This research applies statistical and artificial neural network analysis to dataobtained from measurement of organic compounds in the breath of a Fisher-344 rat. The Research Triangle Institute (RTI) developed a breath collection system for use with rats in order to collect and determine volatile organic compounds (VOCs) exhaled. The RTI study tested the hypothesis that VOCs, including endogenous compounds, in breath can serve as markers to exposure to various chemical compounds such as drugs, pesticides, or carcinogens normally foreign to living organisms. From a comparative analysis of chromatograms, it was concluded that the administration of carbon tetrachloride dramatically altered the VOCs measured in breath; both the compounds detected and their amounts were greatly impacted using the data supplied by RTI. This research will show that neural network analysis and classification can be used to discriminate between exposure to carbon tetrachloride versus no exposure and find the chemical compounds in rat breath that best discriminate between a dosage of carbon tetrachloride and either a vehicle control or no dose at all. For the data set analyzed, 100 percent classification accuracy was achieved in classifying two cases of exposure versus no exposure. The top three marker compounds were identified for each of three classification cases. The results obtained show that neural networks can be effectively used to analyze complex chromatographic data.