Metabolomic machine learning predictor for diagnosis and prognosis of gastric cancer.

Gastric cancer (GC) represents a significant burden of cancer-related mortality worldwide, underscoring an urgent need for the development of early detection strategies and precise postoperative interventions. However, the identification of non-invasive biomarkers for early diagnosis and patient risk stratification remains underexplored. Here, we conduct a targeted metabolomics analysis of 702 plasma samples from multi-center participants to elucidate the GC metabolic reprogramming. Our machine learning analysis reveals a 10-metabolite GC diagnostic model, which is validated in an external test set with a sensitivity of 0.905, outperforming conventional methods leveraging cancer protein markers (sensitivity < 0.40). Additionally, our machine learning-derived prognostic model demonstrates superior performance to traditional models utilizing clinical parameters and effectively stratifies patients into different risk groups to guide precision interventions. Collectively, our findings reveal the metabolic landscape of GC and identify two distinct biomarker panels that enable early detection and prognosis prediction respectively, thus facilitating precision medicine in GC.

Metabolic characterization of hypertrophic cardiomyopathy in human heart.

Hypertrophic cardiomyopathy (HCM) is a common inherited cardiovascular disease with heterogeneous clinical presentations, governed by multiple molecular mechanisms. Metabolic perturbations underlie most cardiovascular diseases; however, the metabolic alterations and their function in HCM are unknown. Here, we describe the metabolome and lipidome of heart and plasma samples from individuals with and without HCM. Correlation analyses showed strong association between metabolic alterations and cardiac function and prognosis of patients with HCM. Using machine learning we identified metabolite panels as potential HCM diagnostic markers or predictors of survival. Clustering based on metabolome and lipidome of heart enabled stratification of patients with HCM into three subgroups with distinct cardiac function and survival. Integration of metabolomics and proteomics data identified metabolic pathways significantly altered in patients with HCM, with the pentose phosphate pathway and oxidative stress being particularly upregulated. Thus, targeting the pentose phosphate pathway and oxidative stress may serve as potential therapeutic strategies for HCM.