SteroidXtract: Deep Learning-Based Pattern Recognition Enables Comprehensive and Rapid Extraction of Steroid-Like Metabolic Features for Automated Biology-Driven Metabolomics.

Despite the vast amount of metabolic information that can be captured in untargeted metabolomics, many biological applications are looking for a biology-driven metabolomics platform that targets a set of metabolites that are relevant to the given biological question. Steroids are a class of important molecules that play critical roles in many physiological systems and diseases. Besides known steroids, there are a large number of unknown steroids that have not been reported in the literature. The ability to rapidly detect and quantify both known and unknown steroid molecules in a biological sample can greatly accelerate a broad range of steroid-focused life science research. This work describes the development and application of SteroidXtract, a convolutional neural network (CNN)-based bioinformatics tool that can recognize steroid molecules in mass spectrometry (MS)-based untargeted metabolomics using their unique tandem MS (MS2) spectral patterns. SteroidXtract was trained using a comprehensive set of standard MS2 spectra from MassBank of North America (MoNA) and an in-house steroid library. Data augmentation strategies, including intensity thresholding and Gaussian noise addition, were created and applied to minimize data overfitting caused by the limited number of standard steroid MS2 spectra. The CNN model embedded in SteroidXtract was further compared with random forest and XGBoost using nested cross-validations to demonstrate its performance. Finally, SteroidXtract was applied in several metabolomics studies to demonstrate its sensitivity, specificity, and robustness. Compared to conventional statistics-driven metabolomics data interpretation, our work offers a novel automated biology-driven approach to interpreting untargeted metabolomics data, prioritizing biologically important molecules with high throughput and sensitivity.

Pharmacokinetic variations of tetramethylpyrazine phosphate after oral administration in hepatic precancerous mice and its hepatoprotective effects.

CONTEXT: Pharmacokinetics of drug may be altered by abnormal physiological functions in illness, which will affect its pharmacodynamic efficacy in turn. OBJECTIVE: To assess the preventive effects of tetramethylpyrazine (TMPZ) phosphate on hepatocarcinogenesis and its pharmacokinetic differentiations in model mice. METHODS: Diethylnitrosamine (DEN) was adopted to induce hepatic precancerous model in mice through intraperitoneal injection, and prevention efficacy of TMPZ at a dose of 162 mg/kg was examined by liver histological analysis and activities of serum marker enzymes. Pharmacokinetic variations of TMPZ between control and model mice were measured for single oral administration. RESULTS: DEN initiation led to a remarkable increase of serum marker enzymes, and abnormality such as bile canaliculi hyperplasia and presence of tumor cells were observed in liver histopathological examination in model mice, while the control ones revealed normal architecture. Oral treatment of TMPZ resulted in a marked reduction in serum marker enzymes and improvement in liver histopathology compared with model ones. In pharmacokinetic study, values of AUC and Tmax of TMPZ became significantly greater with increase of doses in both control and model mice, which elucidated the absorption was enhanced and delayed; meanwhile, its elimination was not affected markedly. When the mice were treated at same dose, the adsorption of TMPZ in model mice was greatly improved than that in control ones, while Tmax and MRT had no significant difference. CONCLUSION: TMPZ was partly effective to protect liver from carcinogenesis initiated by DEN, and hepatic insufficiency could change its pharmacokinetics.