Towards an automatic method for clustering volatile organic compounds in breath samples

It has been known for some time that vapours and odours produced by the body and breath can have some diagnostic value. This knowledge has been confirmed in recent history within clinical trial studies where animals have been successfully trained to detect diseases, through the sniffing of precise volatile organic profiles. Such metabolites can also be captured using analytical technologies. The term 'breathomics' is used to denote the science of analysing all the metabolites that are found in an organism’s breath. Studies in non-targeted metabolites with breathomics make use of Gas Chromatography-Mass Spectrometry (GC-MS) as the most advisable analytical method. Generally, the metabolic profiling of breath analysis encompasses the handling, configuration, scaling and bundling of thou-sands of features obtained from the GC-MS data obtained from hundreds of participating individuals. Also, as is the case with other technologies used in diagnosis,there are many random and systematic noises that influence breathomics. It is for this reason that multi-step data processing (deconvoluted) is needed. However,this is a process that is not only complex; it is also time-consuming and prone to operator errors. [Continues]