DOI 10.1186/s40170-026-00427-4
Leveraging untargeted metabolomics in combination with machine learning to uncover novel insights into bladder cancer.
Аннотация
BACKGROUND
Untargeted metabolomics has emerged as a powerful approach to uncover metabolic dysregulation associated with cancer progression. When integrated with a machine learning strategy it facilitates the discovery of key metabolic pathways and predictive biomarkers with high diagnostic and prognostic value.
METHODS
In this study, we employed liquid chromatography coupled to high-resolution Tribrid Orbitrap mass spectrometry to perform comprehensive metabolic profiling of bladder cancer (BLCA) as well as predict invasiveness of the disease.
RESULTS
By leveraging both in-house retention time-based MS/MS spectral libraries and commercial databases, we robustly identify over 2000 metabolites. In addition, this platform allows identification of novel pathways highlighting metabolic vulnerabilities in BLCA. The application of machine learning algorithms and advanced computational modeling uncovered metabolic signatures that differentiate BLCA from adjacent normal/benign samples and distinguish muscle-invasive from non-muscle-invasive bladder cancer. Our integrative analytical pipeline addresses key challenges in metabolomics-including high dimensionality, metabolite annotation, and biological variability-through feature selection and predictive modeling. We identify candidate metabolic markers with strong potential for early detection and characterize invasiveness of the disease and identify potential therapeutic target pathways.
CONCLUSIONS
This work highlights the power of combining untargeted metabolomics with machine learning to map the metabolic landscape of BLCA and to accelerate the development of precision diagnostics and future therapeutic strategies.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.