Yaser Alkhalifah, Iain Phillips, Andrea Soltoggio. Kareen Darnley, William H Nailon, Duncan McLaren, Michael Eddleston, C. L. Paul Thomas and Dahlia Salman.
Department of Chemistry, Loughborough University, United Kingdom.
First Published: Analytical Chemistry December 2nd 2019. (https://doi.org/10.1021/acs.analchem.9b03084).
Metabolic profiling of breath analysis involves processing, alignment, scaling and clustering of thousands of features ex-tracted from Gas Chromatography Mass spectrometry (GC-MS) data from hundreds of participants. The multi-step data processing is complicated, operator error-prone and time-consuming. Automated algorithmic clustering methods that are able to cluster features in a fast and reliable way are necessary. These accelerate metabolic profiling and discovery plat-forms for next generation medical diagnostic tools.
Our unsupervised clustering technique, VOCCluster, prototyped in Py-thon, handles features of deconvolved GC-MS breath data. VOCCluster was created from a heuristic ontology based on the observation of experts undertaking data processing with a suite of software packages. VOCCluster identifies and clusters groups of volatile organic compounds (VOCs) from deconvolved GC-MS breath with similar mass spectra and retention index profiles. VOCCluster was used to cluster more than 15,000 features extracted from 74 GC-MS clinical breath samples obtained from participants with cancer before and after a radiation therapy.
Results were evaluated against a panel of ground truth compounds and compared to other clustering methods (DBSCAN and OPTICS) that were used in previous metabolomics studies. VOCCluster was able to cluster those features into 1081 groups (including endogenous, exogenous compounds and instrumental artefacts) with an accuracy rate of 96% (± 0.04 at 95% confidence interval).
View the full article at https://doi.org/10.1021/acs.analchem.9b03084.