Advancements in omics technologies and artificial intelligence (AI) methodologies are fuelling our progress towards personalised diagnosis, prognosis and treatment strategies in hepatology. This review provides a comprehensive overview of the current landscape of AI methods used for analysis of omics data in liver diseases. We present an overview of the prevalence of different omics levels across various liver diseases, as well as categorise the AI methodology used across the studies. Specifically, we highlight the predominance of transcriptomic and genomic profiling and the relatively sparse exploration of other levels such as the proteome and methylome, which represent untapped potential for novel insights. Publicly available database initiatives such as The Cancer Genome Atlas and The International Cancer Genome Consortium have paved the way for advancements in the diagnosis and treatment of hepatocellular carcinoma. However, the same availability of large omics datasets remains limited for other liver diseases. Furthermore, the application of sophisticated AI methods to handle the complexities of multiomics datasets requires substantial data to train and validate the models and faces challenges in achieving bias-free results with clinical utility. Strategies to address the paucity of data and capitalise on opportunities are discussed. Given the substantial global burden of chronic liver diseases, it is imperative that multicentre collaborations be established to generate large-scale omics data for early disease recognition and intervention. Exploring advanced AI methods is also necessary to maximise the potential of these datasets and improve early detection and personalised treatment strategies.
Background: The microbiota is emerging as a key factor in the predisposition to insulin resistance and obesity.
Objective: To understand the interplay among gut microbiota and insulin sensitivity in multiple tissues.
Design: Integrative multiomics and multitissue approach across six studies, combining euglycaemic clamp measurements (used in four of the six studies) with other measurements of glucose metabolism and insulin resistance (glycated haemoglobin (HbA1c) and fasting glucose).
Results: Several genera and species from the Proteobacteria phylum were consistently negatively associated with insulin sensitivity in four studies (ADIPOINST, n=15; IRONMET, n=121, FLORINASH, n=67 and FLOROMIDIA, n=24). Transcriptomic analysis of the jejunum, ileum and colon revealed T cell-related signatures positively linked to insulin sensitivity. Proteobacteria in the ileum and colon were positively associated with HbA1c but negatively with the number of T cells. Jejunal deoxycholic acid was negatively associated with insulin sensitivity. Transcriptomics of subcutaneous adipose tissue (ADIPOMIT, n=740) and visceral adipose tissue (VAT) (ADIPOINST, n=29) revealed T cell-related signatures linked to HbA1c and insulin sensitivity, respectively. VAT Proteobacteria were negatively associated with insulin sensitivity. Multiomics and multitissue integration in the ADIPOINST and FLORINASH studies linked faecal Proteobacteria with jejunal and liver deoxycholic acid, as well as jejunal, VAT and liver transcriptomic signatures involved in the actin cytoskeleton, insulin and T cell signalling. Fasting glucose was consistently linked to interferon-induced genes and antiviral responses in the intestine and VAT. Studies in Drosophila melanogaster validated these human insulin sensitivity-associated changes.
Conclusion: These data provide comprehensive insights into the microbiome-gut-adipose-liver axis and its impact on systemic insulin action, suggesting potential therapeutic targets.Cite Now.