Signature-discovery approach for sample matching of a nerve-agent precursor using liquid chromatography-mass spectrometry, XCMS, and chemometrics

Abstract

This report demonstrates the use of bioinformatic and chemometric tools on liquid chromatography-mass spectrometry (LC-MS) data for the discovery of trace forensic signatures for sample matching of ten stocks of the nerve-agent precursor known as methylphosphonic dichloride (dichlor). XCMS, a software tool primarily used in bioinformatics, was used to comprehensively search and find candidate LC-MS peaks in a known set of dichlor samples. These candidate peaks were down selected to a group of 34 impurity peaks. Hierarchal cluster analysis and factor analysis demonstrated the potential of these 34 impurities peaks for matching samples based on their stock source. Only one pair of dichlor stocks was not differentiated from one another. An acceptable chemometric approach for sample matching was determined to be variance scaling and signal averaging of normalized duplicate impurity profiles prior to classification by K-nearest neighbors. Using this approach, a test set of seven dichlor samples were all correctly matched to their source stock. The sample preparation and LC-MS method permitted the detection of dichlor impurities quantitatively estimated to be in the parts-per-trillion (w/w). The detection of a common impurity in all dichlor stocks that were synthesized over a 14-year period and by different manufacturers was an unexpected discovery. Our described signature-discovery approach should be useful in the development of a forensic capability to assist investigations following chemical attacks.