Impact of three different peak picking software tools on the quality of untargeted metabolomics data.

Data quality and control parameters are becoming more important in metabolomics. For peak picking, open-source or commercial solutions are used. Other publications consider different software solutions or data acquisition types for peak picking, a combination, including proposed and new quality parameters for the process of peak picking, does not exist. This study tries to examine the performance of three different software in terms of reproducibility and quality of their output while also considering new quality parameters to gain a better understanding of resulting feature lists in metabolomics data. We saw best recovery of spiked analytes in MS-DIAL. Reproducibility over multiple projects was good among all software. The total number of features found was consistent for DDA and full scan acquisition in MS-DIAL but full scan data leading to considerably more features in MZmine and Progenesis Qi. Feature linearity proved to be a good quality parameter. Features in MS-DIAL and MZmine, showed good linearity while Progenesis Qi produced large variation, especially in full scan data. Peak width proved to be a very powerful filtering criteria revealing many features in MZmine and Progenesis Qi to be of questionable peak width. Additionally, full scan data appears to produce a disproportionally higher number of short features. This parameter is not yet available in MS-DIAL. Finally, the manual classification of true positive features proved MS-DIAL to perform significantly better in DDA data (62 % true positive) than the two other software in either mode. We showed that currently popular solutions MS-DIAL and MZmine perform well in targeted analysis of spiked analytes as well as in classic untargeted analysis. The commercially available solution Progenesis Qi does not hold any advantage over the two in terms of quality parameters, of which we proposed peak width as a new parameter and showed that already proposed parameters such as feature linearity in samples of increasing concentration are advisable to use.

Postmortem metabolomics: influence of time since death on the level of endogenous compounds in human femoral blood. Necessary to be considered in metabolome study planning?

INTRODUCTION: The (un)targeted analysis of endogenous compounds has gained interest in the field of forensic postmortem investigations. The blood metabolome is influenced by many factors, and postmortem specimens are considered particularly challenging due to unpredictable decomposition processes. OBJECTIVES: This study aimed to systematically investigate the influence of the time since death on endogenous compounds and its relevance in designing postmortem metabolome studies. METHODS: Femoral blood samples of 427 authentic postmortem cases, were collected at two time points after death (854 samples in total; t1: admission to the institute, 1.3-290 h; t2: autopsy, 11-478 h; median ∆t = 71 h). All samples were analyzed using an untargeted metabolome approach, and peak areas were determined for 38 compounds (acylcarnitines, amino acids, phospholipids, and others). Differences between t2 and t1 were assessed by Wilcoxon signed-ranked test (p < 0.05). Moreover, all samples (n = 854) were binned into time groups (6 h, 12 h, or 24 h intervals) and compared by Kruskal-Wallis/Dunn's multiple comparison tests (p < 0.05 each) to investigate the effect of the estimated time since death. RESULTS: Except for serine, threonine, and PC 34:1, all tested analytes revealed statistically significant changes between t1 and t2 (highest median increase 166%). Unpaired analysis of all 854 blood samples in-between groups indicated similar results. Significant differences were typically observed between blood samples collected within the first and later than 48 h after death, respectively. CONCLUSIONS: To improve the consistency of comprehensive data evaluation in postmortem metabolome studies, it seems advisable to only include specimens collected within the first 2 days after death.

Postmortem Metabolomics: Strategies to Assess Time-Dependent Postmortem Changes of Diazepam, Nordiazepam, Morphine, Codeine, Mirtazapine and Citalopram.

Postmortem redistribution (PMR) can result in artificial drug concentration changes following death and complicate forensic case interpretation. Currently, no accurate methods for PMR prediction exist. Hence, alternative strategies were developed investigating the time-dependent postmortem behavior of diazepam, nordiazepam, morphine, codeine, mirtazapine and citalopram. For 477 authentic postmortem cases, femoral blood samples were collected at two postmortem time-points. All samples were quantified for drugs of abuse (targeted; liquid chromatography-tandem mass spectrometry LC-MS/MS) and characterized for small endogenous molecules (untargeted; gas chromatography-high resolution MS (GC-HRMS). Trends for significant time-dependent concentration decreases (diazepam (n = 137), nordiazepam (n = 126)), increases (mirtazapine (n = 55), citalopram (n = 50)) or minimal median postmortem changes (morphine (n = 122), codeine (n = 92)) could be observed. Robust mathematical mixed effect models were created for the generalized postmortem behavior of diazepam and nordiazepam, which could be used to back-calculate drug concentrations towards a time-point closer to the estimated time of death (caution: inter-individual variability). Significant correlations between time-dependent concentration changes of morphine, mirtazapine and citalopram with individual endogenous molecules could be determined; no correlation was deemed strong enough for successful a posteriori estimation on the occurrence of PMR for specific cases. The current dataset did successfully lead to a significant knowledge gain in further understanding the time-dependent postmortem behavior of the studied drugs (of abuse).