Recent advances in high-throughput microbiome profiling have generated expansive data sets that offer unprecedented opportunities to investigate the role of microbes in human health. However, the complexity and high dimensionality of these data present significant analytical challenges that often exceed the capabilities of traditional computational methods. Artificial intelligence (AI), encompassing both classical machine learning and modern deep learning approaches, has emerged as a powerful solution to these challenges. In this review, we systematically explore AI-driven methodologies in microbiome research, including clustering algorithms, dimensionality reduction techniques, convolutional and recurrent neural networks, and emerging large language models. We assess how these approaches enable the extraction of meaningful biological patterns from complex microbial data from a multiscale perspective, facilitating insights into community dynamics, host-microbe interactions and functional genomics. Additionally, we explore the transformative impact of AI on translational applications across both academic research and real-world clinical settings, including disease diagnostics, therapeutic development and precision microbiome engineering. By critically evaluating the current capabilities and limitations of AI in this context, this review aims to chart a path forward for the integration of AI into microbiome research, ultimately accelerating innovations in personalised medicine and deepening our understanding of host-microbiome relationships.

The cholecystokinin-2/gastrin receptor (Cck2r) is expressed in corpus isthmus progenitor, enterochromaffin-like and parietal cells, regulating acid secretion and cell turnover. However, the role of gastrin on Cck2r progenitors during mucosal regeneration remains unexplored.

Combining chemotherapy with anti-programmed cell death protein-1 (PD-1) improves clinical outcomes in oesophageal squamous cell carcinoma (ESCC), yet the underlying synergistic mechanism remains obscured. Moreover, 30-50% of patients still derive no therapeutic benefit from the combination strategy, highlighting the need to decipher and overcome resistance.

Effect of glycaemic control on pancreatic cancer (PC) development in patients with long-standing type 2 diabetes (T2D) remains unclear.

Current microbiome-based therapeutics face two prominent issues: the limited clinical efficacy of probiotics and the significant variability in the efficacy of microbiota transplantation across different diseases. Although washed microbiota transplantation (WMT) is a new faecal microbiota transplantation, a single therapeutic agent cannot be universally effective for multiple dysbiosis-related diseases.

Cancers of the oesophagus and stomach are a major cause of morbidity and mortality. Research is crucial to improving outcomes. However, to maximise value and impact, areas of focus should be prioritised in partnership with patients.

Fructose has been identified as a potential alternative energy source for cancer cells, facilitated by the fructose-specific transporter GLUT5. Elevated GLUT5 expression in cancer cells has been associated with increased tumour aggressiveness. However, the role of fructose in remodelling the tumour microenvironment, particularly in modulating cancer-associated fibroblast (CAF) behaviour, remains underexplored.

To convene a global consensus on Helicobacter pylori (H pylori) screening and eradication strategies for gastric cancer prevention, identify key knowledge gaps and outline future research directions.