The gut microbiota is a potentially modifiable risk factor for various health complications. Therefore, advanced techniques are warranted to understand the relationship between gut microbiota, disease, and clinical relevance. This chapter focuses on the emerging application of artificial intelligence (AI) techniques in the studies of gut microbiota. It opens with a discussion on the role of gut microbiota in health, mentions an overview of AI techniques, and provides information on the application of AI in the study of the gut microbiome and its role in the diagnosis and treatment of diseases. It also gives a glimpse into the challenges and future direction of artificial intelligence in gut microbiome research. The chapter provides new insights into the extraordinary applications of AI in the study of the gut microbiome.
TopIntroduction
The importance of the human gut microbiome to human health has drawn more attention in healthcare in recent years. Notably, the significant rise in research on gut microbiome is potentially due to a greater knowledge of the pivotal role of gut microbiome in human health. The human intestinal tract harbours a diverse community of microorganisms including archaea, bacteria, viruses and fungi. They coexist in the human gastrointestinal system in a symbiotic relationship with the host. The microbiome is the collective term for a group of bacteria, also known as the microbiota (Turnbaugh et al., 2007). The genome of the human host is 150 times smaller than that of the gut microbiome, which contains about 100 trillion bacteria (3 million vs. roughly 23,000 genes, respectively) (Altveş et al., 2020). Eubiosis, the term for the good balance between the host and microbiome in healthy people, can be changed to dysbiosis (an aberrant shift in microbiota compositions) in a number of clinical situations (Giuffrè et al., 2020; Hrncir, 2022; Nallappan et al., 2021).
The diagnosis of the precise relationship between dysbiosis and the emergence of the disease gained attention in scientific investigations. Omic studies including metabolomics, metagenomics and metatranscriptomics are frequently employed to examine the gut microbiome owing to the high-throughput and high-resolution data (Aguiar-Pulido et al., 2016; Zhang et al., 2019). Metabolomics measures the concentrations of various compounds produced by a particular microbial community, whereas metagenomics techniques (such as whole-genome shotgun sequencing or 16S rRNA gene sequencing) provide detailed information pertaining to the community of interest’s general genetic makeup of microbes (Aguiar-Pulido et al., 2016; Zhang et al., 2019). A lot of data has been produced by the use of omics studies, which has led to the invention of computational techniques and programmes like machine learning to help handle and evaluate this data for the study of the human gut microbiota (Ghannam & Techtmann, 2021; Goodswen et al., 2021; Marcos-Zambrano et al., 2021). The enormous volume of data produced by these techniques has prompted the advancement of computer techniques for processing and analysis of data, with machine learning emerging as a potent and popular tool in this area.