Paolini Alessandro, Baldassarre Antonella, Bruno Stefania Paola, Felli Cristina, Muzi Chantal, Ahmadi Badi Sara, Siadat Seyed Davar, Sarshar Meysam, Masotti Andrea
Research Laboratories, Bambino Gesù Children's Hospital-IRCCS, Rome, Italy.
Department of Science, University Roma Tre, Rome, Italy.
Front Microbiol. 2022 Jun 9;13:888414. doi: 10.3389/fmicb.2022.888414. eCollection 2022.
In recent years, the clinical use of extracellular miRNAs as potential biomarkers of disease has increasingly emerged as a new and powerful tool. Serum, urine, saliva and stool contain miRNAs that can exert regulatory effects not only in surrounding epithelial cells but can also modulate bacterial gene expression, thus acting as a "master regulator" of many biological processes. We think that in order to have a holistic picture of the health status of an individual, we have to consider comprehensively many "omics" data, such as miRNAs profiling form different parts of the body and their interactions with cells and bacteria. Moreover, Artificial Intelligence (AI) and Machine Learning (ML) algorithms coupled to other multiomics data (i.e., big data) could help researchers to classify better the patient's molecular characteristics and drive clinicians to identify personalized therapeutic strategies. Here, we highlight how the integration of "multiomic" data (i.e., miRNAs profiling and microbiota signature) with other omics (i.e., metabolomics, exposomics) analyzed by AI algorithms could improve the diagnostic and prognostic potential of specific biomarkers of disease.
近年来，细胞外微小RNA作为疾病潜在生物标志物的临床应用已日益成为一种新型且强大的工具。血清、尿液、唾液和粪便中含有的微小RNA不仅能在周围上皮细胞中发挥调节作用，还能调节细菌基因表达，从而成为许多生物过程的“主要调节因子”。我们认为，为全面了解个体的健康状况，必须综合考虑多种“组学”数据，比如来自身体不同部位的微小RNA谱及其与细胞和细菌的相互作用。此外，与其他多组学数据（即大数据）相结合的人工智能（AI）和机器学习（ML）算法，可帮助研究人员更好地对患者的分子特征进行分类，并促使临床医生确定个性化治疗策略。在此，我们着重介绍通过AI算法分析的“多组学”数据（即微小RNA谱和微生物群特征）与其他组学（即代谢组学、暴露组学）的整合，如何提高疾病特定生物标志物的诊断和预后潜力。
