Predicting the structures of metabolites formed in humans can provide advantageous insights for the development of drugs and other compounds. Here we present GLORYx, which integrates machine learning-based site of metabolism (SoM) prediction with reaction rule sets to predict and rank the structures of metabolites that could potentially be formed by phase 1 and/or phase 2 metabolism. GLORYx extends the approach from our previously developed tool GLORY, which predicted metabolite structures for cytochrome P450-mediated metabolism only. A robust approach to ranking the predicted metabolites is attained by using the SoM probabilities predicted by the FAME 3 machine learning models to score the predicted metabolites. On a manually curated test data set containing both phase 1 and phase 2 metabolites, GLORYx achieves a recall of 77% and an area under the receiver operating characteristic curve (AUC) of 0.79. Separate analysis of performance on a large amount of freely available phase 1 and phase 2 metabolite data indicates that achieving a meaningful ranking of predicted metabolites is more difficult for phase 2 than for phase 1 metabolites. GLORYx is freely available as a web server at https://nerdd.zbh.uni-hamburg.de/ and is also provided as a software package upon request. The data sets as well as all the reaction rules from this work are also made freely available.

• MeSH
• Biotransformation * MeSH
• Humans MeSH
• Molecular Structure MeSH
• Machine Learning * MeSH
• Toxicity Tests * MeSH
• Xenobiotics chemistry   metabolism   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Names of Substances
• Xenobiotics MeSH

New psychoactive substances (NPSs) are associated with a significant number of intoxications. With the number of readily available forms of these drugs rising every year, there are even risks for the general public. Consequently, there is a high demand for methods sufficiently sensitive to detect NPSs in samples found at the crime scene. Infrared (IR) and Raman spectroscopies are commonly used for such detection, but they have limitations; for example, fluorescence in Raman can overlay the signal and when the sample is a mixture sometimes neither Raman nor IR is able to identify the compounds. Here, we investigate the potential of X-ray powder diffraction (XRPD) to analyse samples seized on the black market. A series of psychoactive substances (heroin, cocaine, mephedrone, ephylone, butylone, JWH-073, and naphyrone) was measured. Comparison of their diffraction patterns with those of the respective standards showed that XRPD was able to identify each of the substances. The same samples were analyzed using IR and Raman, which in both cases were not able to detect the compounds in all of the samples. These results suggest that XRPD could be a valuable addition to the range of forensic tools used to detect these compounds in illicit drug samples.

• Keywords
• Raman spectroscopy, X-ray powder diffraction, drug detection, infrared spectroscopy, new psychoactive substances,
• Publication type
• Journal Article MeSH