Microbial Dark Matter: from Discovery to Applications

Abstract

With the rapid increase of the microbiome samples and sequencing data, more and more knowledge about microbial communities has been gained. However, there is still much more to learn about microbial communities, including billions of novel species and genes, as well as countless spatiotemporal dynamic patterns within the microbial communities, which together form the microbial dark matter. In this work, we summarized the dark matter in microbiome research and reviewed current data mining methods, especially artificial intelligence (AI) methods, for different types of knowledge discovery from microbial dark matter. We also provided case studies on using AI methods for microbiome data mining and knowledge discovery. In summary, we view microbial dark matter not as a problem to be solved but as an opportunity for AI methods to explore, with the goal of advancing our understanding of microbial communities, as well as developing better solutions to global concerns about human health and the environment.

Keywords: Application; Artificial intelligence; Dark matter; Knowledge discovery; Microbiome.

Figure 1

The microbial dark matter and the techniques to better understand such dark matter toward better solutions in applications There are three key steps for microbiome knowledge discovery from millions of microbiome samples, including the development of AI technologies and microbiome analysis tools, the sets of microbial dark matter to be unearthed, and countless applications. Among these, the microbial dark matter represents the core resource to be discovered. The major types of microbial dark matter introduced in this review include: more than a million context-dependent biomes in which microbial communities could reside; more than a million species, including bacteria, archaea, viruses, and protists; more than a billion functional genes; and the countless number of dynamic ecological and evolutionary patterns. AI, artificial intelligence.

Figure 2

The longitudinal dynamics of the human gut microbial communities have certain patterns For short-term intervention, it has been demonstrated that dietary intervention is the main driver of the rapid change in the gut microbial community. For mid-term intervention, it has been demonstrated that the dietary intervention could become stable after a month. For long-term intervention, even the enterotype might be changed after one year. The dynamic patterns are based on human gut microbial community samples. And the community profile of each sample is based on the combination of species with different relative abundances.

Figure 3

The deep learning approaches for solving the microbial dark matter mining problems Compared with traditional methods, deep learning methods have enabled high-throughput screening, thus is good for unknown knowledge discovery and has high efficiency.

Figure 4

Applications based on computational tools for microbial dark matter mining