Compositionality, sparsity, spurious heterogeneity, and other data-driven challenges for machine learning algorithms within plant microbiome studies

Order among chaos: High throughput MYCroplanters can distinguish interacting drivers of host infection in a highly stochastic system

The likelihood that a host will be susceptible to infection is influenced by the interaction of diverse biotic and abiotic factors. As a result, substantial experimental replication and scalability are required to identify the contributions of and interactions between the host, the environment, and biotic factors such as the microbiome. For example, pathogen infection success is known to vary by host genotype, bacterial strain identity and dose, and pathogen dose. Elucidating the interactions between these factors in vivo has been challenging because testing combinations of these variables quickly becomes experimentally intractable. Here, we describe a novel high throughput plant growth system (MYCroplanters) to test how multiple host, non-pathogenic bacteria, and pathogen variables predict host health. Using an Arabidopsis-Pseudomonas host-microbe model, we found that host genotype and bacterial strain order of arrival predict host susceptibility to infection, but pathogen and non-pathogenic bacterial dose can overwhelm these effects. Host susceptibility to infection is therefore driven by complex interactions between multiple factors that can both mask and compensate for each other. However, regardless of host or inoculation conditions, the ratio of pathogen to non-pathogen emerged as a consistent correlate of disease. Our results demonstrate that high-throughput tools like MYCroplanters can isolate interacting drivers of host susceptibility to disease. Increasing the scale at which we can screen drivers of disease, such as microbiome community structure, will facilitate both disease predictions and treatments for medicine and agricultural applications.

Engineering agricultural soil microbiomes and predicting plant phenotypes

Plant growth-promoting rhizobacteria (PGPR) can improve crop yields, nutrient use efficiency, plant tolerance to stressors, and confer benefits to future generations of crops grown in the same soil. Unlocking the potential of microbial communities in the rhizosphere and endosphere is therefore of great interest for sustainable agriculture advancements. Before plant microbiomes can be engineered to confer desirable phenotypic effects on their plant hosts, a deeper understanding of the interacting factors influencing rhizosphere community structure and function is needed. Dealing with this complexity is becoming more feasible using computational approaches. In this review, we discuss recent advances at the intersection of experimental and computational strategies for the investigation of plant-microbiome interactions and the engineering of desirable soil microbiomes.

Nine (not so simple) steps: a practical guide to using machine learning in microbial ecology

Due to the complex nature of microbiome data, the field of microbial ecology has many current and potential uses for machine learning (ML) modeling. With the increased use of predictive ML models across many disciplines, including microbial ecology, there is extensive published information on the specific ML algorithms available and how those algorithms have been applied. Thus, our goal is not to summarize the breadth of ML models available or compare their performances. Rather, our goal is to provide more concrete and actionable information to guide microbial ecologists in how to select, run, and interpret ML algorithms to predict the taxa or genes associated with particular sample categories or environmental gradients of interest. Such microbial data often have unique characteristics that require careful consideration of how to apply ML models and how to interpret the associated results. This review is intended for practicing microbial ecologists who may be unfamiliar with some of the intricacies of ML models. We provide examples and discuss common opportunities and pitfalls specific to applying ML models to the types of data sets most frequently collected by microbial ecologists.

Unveiling the Connection between Microbiota and Depressive Disorder through Machine Learning

In the last few years, investigation of the gut-brain axis and the connection between the gut microbiota and the human nervous system and mental health has become one of the most popular topics. Correlations between the taxonomic and functional changes in gut microbiota and major depressive disorder have been shown in several studies. Machine learning provides a promising approach to analyze large-scale metagenomic data and identify biomarkers associated with depression. In this work, machine learning algorithms, such as random forest, elastic net, and You Only Look Once (YOLO), were utilized to detect significant features in microbiome samples and classify individuals based on their disorder status. The analysis was conducted on metagenomic data obtained during the study of gut microbiota of healthy people and patients with major depressive disorder. The YOLO method showed the greatest effectiveness in the analysis of the metagenomic samples and confirmed the experimental results on the critical importance of a reduction in the amount of Faecalibacterium prausnitzii for the manifestation of depression. These findings could contribute to a better understanding of the role of the gut microbiota in major depressive disorder and potentially lead the way for novel diagnostic and therapeutic strategies.