RESUMEN
Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.
RESUMEN
Poorer sleep is associated with poorer bone health among older adults but the role of sleep in bone health during younger adulthood is understudied. In this observational study, the averages and variability in total sleep time (TST), sleep efficiency (SE), and sleep midpoint of university students were examined in relation to levels of bone turnover markers (BTMs) and bone mineral density (BMD) at the lumbar spine and femur. A sample of healthy, university students (N = 59, aged 18-25 years, 51.8% female, body mass index <30 kg/m2 ), wore a wrist actigraph for 7 days, completed a dual-energy X-ray absorptiometry scan, and underwent blood sampling to assess serum BTM concentrations of osteocalcin (OC) and N-terminal telopeptide of type 1 collagen. A sub-sample (n = 14) completed a one-year follow-up. Multiple regression models examined the associations between each sleep metric and bone health outcome at baseline and 1-year follow-up. At baseline, greater variability in sleep midpoint was cross-sectionally associated with greater OC (ß = 0.21, p = 0.042). In the exploratory, follow-up sub-sample, lower average TST (ß = -0.66, p = 0.013) and SE (ß = -0.68, p = 0.01) at baseline were associated with greater increases in OC at follow-up. Greater delays in mean sleep midpoint over follow-up were significantly associated with decreases in lumbar spine BMD (ß = -0.49, p = 0.03). In a sample of young adults, variable sleep schedules were associated with greater bone turnover suggesting the potential importance of regular sleep for optimising bone health into early adulthood.
RESUMEN
T-lymphocytes are prevalent in the tumor microenvironment of follicular lymphoma (FL). However, the phenotype of T-cells may vary, and the prevalence of certain T-cell subsets may influence tumor biology and patient survival. We therefore analyzed a cohort of 82 FL patients using CyTOF to determine whether specific T-cell phenotypes were associated with distinct tumor microenvironments and patient outcome. We identified four immune subgroups with differing T-cell phenotypes and the prevalence of certain T-cell subsets was associated with patient survival. Patients with increased T cells with early differentiation stage tended to have a significantly better survival than patients with increased T-cells of late differentiation stage. Specifically, CD57+ TFH cells, with a late-stage differentiation phenotype, were significantly more abundant in FL patients who had early disease progression and therefore correlated with an inferior survival. Single cell analysis (CITE-seq) revealed that CD57+ TFH cells exhibited a substantially different transcriptome from CD57- TFH cells with upregulation of inflammatory pathways, evidence of immune exhaustion and susceptibility to apoptosis. Taken together, our results show that different tumor microenvironments among FL patients are associated with variable T-cell phenotypes and an increased prevalence of CD57+ TFH cells is associated with poor patient survival.