This comprehensive review synthesizes the wealth of scientific literature pertaining to the application of Artificial Intelligence (AI) in the field of metabolomics. Over the past decade, AI has played an increasingly pivotal role in deciphering the complexities of metabolomic data, offering novel insights into the molecular underpinnings of biological systems. Through an extensive examination of relevant research papers, we provide a comprehensive overview of the diverse AI techniques and methodologies, from data preprocessing and feature selection to predictive modeling and pathway analysis, employed in metabolomics studies. The review dissects key trends and advancements in AI-driven metabolomics, shedding light on its pivotal role in biomarker discovery, disease diagnosis, and personalized medicine. In addition to highlighting the significant contributions of AI to metabolomics, emerging frontiers will be explored, such as the incorporation of multi-omics data integration and the growing importance of explainable AI in biological research. Ultimately, this review underscores the transformative impact of AI on metabolomics, emphasizing its potential to reshape our understanding of metabolic pathways, disease mechanisms, and therapeutic interventions. The combination of AI and metabolomics stands as a powerful paradigm shift with far-reaching implications for advancing both fundamental scientific knowledge and practical applications across diverse domains.
Unlocking the secrets of metabolomics with Artificial Intelligence: a comprehensive literature review
Cannas F.;Piras C.;Spada M.;Noto A.;Atzori L.;Fanos V.
2024-01-01
Abstract
This comprehensive review synthesizes the wealth of scientific literature pertaining to the application of Artificial Intelligence (AI) in the field of metabolomics. Over the past decade, AI has played an increasingly pivotal role in deciphering the complexities of metabolomic data, offering novel insights into the molecular underpinnings of biological systems. Through an extensive examination of relevant research papers, we provide a comprehensive overview of the diverse AI techniques and methodologies, from data preprocessing and feature selection to predictive modeling and pathway analysis, employed in metabolomics studies. The review dissects key trends and advancements in AI-driven metabolomics, shedding light on its pivotal role in biomarker discovery, disease diagnosis, and personalized medicine. In addition to highlighting the significant contributions of AI to metabolomics, emerging frontiers will be explored, such as the incorporation of multi-omics data integration and the growing importance of explainable AI in biological research. Ultimately, this review underscores the transformative impact of AI on metabolomics, emphasizing its potential to reshape our understanding of metabolic pathways, disease mechanisms, and therapeutic interventions. The combination of AI and metabolomics stands as a powerful paradigm shift with far-reaching implications for advancing both fundamental scientific knowledge and practical applications across diverse domains.File | Dimensione | Formato | |
---|---|---|---|
JPNIM_2024.pdf
accesso aperto
Tipologia:
versione editoriale (VoR)
Dimensione
3.28 MB
Formato
Adobe PDF
|
3.28 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.