This letter is devoted to the application of machine learning, namely, convolutional neural networks to solve problems in the initial steps of the common pipeline for data analysis in metabolomics. These steps are the peak detection and the peak integration in raw liquid chromatography–mass spectrometry (LC–MS) data. Widely used algorithms suffer from rather poor precision for these tasks, yielding many false positive signals. In the present work, we developed an algorithm named peakonly, which has high flexibility for the detection or exclusion of low-intensity noisy peaks, and shows excellent quality in the detection of true positive peaks, approaching the highest possible precision. The current approach was developed for the analysis of high-resolution LC–MS data for the purposes of metabolomics, but potentially it can be applied with several adaptations in other fields, which utilize high-resolution GC− or LC–MS techniques. Peakonly is freely available on GitHub () under an MIT license.

This work represents the first comprehensive report on quantitative metabolomic composition of tissues of pike-perch (Sander lucioperca) and Siberian roach (Rutilus rutilus lacustris). The total of 68 most abundant metabolites are identified and quantified in the fish lenses and gills by the combination of LC-MS and NMR. It is shown that the concentrations of some compounds in the lens are much higher than that in the gills; that indicates the importance of these metabolites for the adaptation to the specific living conditions and maintaining the homeostasis of the fish lens. The lens metabolome undergoes significant seasonal changes due to the variations of dissolved oxygen level and fish feeding activity. The most season-affected metabolites are osmolytes and antioxidants, and the most affected metabolic pathway is the histidine pathway. In late autumn, the major lens osmolytes are N-acetyl-histidine and threonine phosphoethanolamine (Thr-PETA), while in winter the highest concentrations were observed for serine phosphoethanolamine (Ser-PETA) and myo-inositol. The presence of Thr-PETA and Ser-PETA in fish tissues and their role in cell osmotic protection are reported for the first time. The obtained concentrations can be used as baseline levels for studying the influence of environmental factors on fish health.

No abstract