Uncovering in vivo biochemical patterns from time-series metabolic dynamics

The metabolic clock of ketamine abuse in rats by a machine learning model

Ketamine has recently become an anesthetic drug used in human and veterinary clinical medicine for illicit abuse worldwide, but the detection of illicit abuse and inference of time intervals following ketamine abuse are challenging issues in forensic toxicological investigations. Here, we developed methods to estimate time intervals since ketamine use is based on significant metabolite changes in rat serum over time after a single intraperitoneal injection of ketamine, and global metabolomics was quantified by ultra-performance liquid chromatography-quadrupole-time-of-flight mass spectrometry (UPLC-Q-TOF-MS). Thirty-five rats were treated with saline (control) or ketamine at 3 doses (30, 60, and 90 mg/kg), and the serum was collected at 21 time points (0 h to 29 d). Time-dependent rather than dose-dependent features were observed. Thirty-nine potential biomarkers were identified, including ketamine and its metabolites, lipids, serotonin and other molecules, which were used for building a random forest model to estimate time intervals up to 29 days after ketamine treatment. The accuracy of the model was 85.37% in the cross-validation set and 58.33% in the validation set. This study provides further understanding of the time-dependent changes in metabolites induced by ketamine abuse.

SAND: Automated Time-Domain Modeling of NMR Spectra Applied to Metabolite Quantification

Developments in untargeted nuclear magnetic resonance (NMR) metabolomics enable the profiling of thousands of biological samples. The exploitation of this rich source of information requires a detailed quantification of spectral features. However, the development of a consistent and automatic workflow has been challenging because of extensive signal overlap. To address this challenge, we introduce the software Spectral Automated NMR Decomposition (SAND). SAND follows on from the previous success of time-domain modeling and automatically quantifies entire spectra without manual interaction. The SAND approach uses hybrid optimization with Markov chain Monte Carlo methods, employing subsampling in both time and frequency domains. In particular, SAND randomly divides the time-domain data into training and validation sets to help avoid overfitting. We demonstrate the accuracy of SAND, which provides a correlation of ∼0.9 with ground truth on cases including highly overlapped simulated data sets, a two-compound mixture, and a urine sample spiked with different amounts of a four-compound mixture. We further demonstrate an automated annotation using correlation networks derived from SAND decomposed peaks, and on average, 74% of peaks for each compound can be recovered in single clusters. SAND is available in NMRbox, the cloud computing environment for NMR software hosted by the Network for Advanced NMR (NAN). Since the SAND method uses time-domain subsampling (i.e., random subset of time-domain points), it has the potential to be extended to a higher dimensionality and nonuniformly sampled data.