Predicting how the gut microbiome will change over time

A new tool shows that changes in the microbiota can be accurately predicted based on the current microbial community.

Jul 01, 2019
1
0

A new study presents a tool for accurately predicting how microbial communities will change over time. The work was developed by Liat Shenhav, Leah Briscoe and Mike Thompson from the Halperin lab, University of California Los Angeles, as well as researchers at the Mizrahi lab at Ben-Gurion University, Israel, and was published in PLOS Computational Biology.

Given the prevalence of AI and machine learning, you could be forgiven for thinking that was the approach taken here. However, the research team used a linear model to generate the predictions which outperformed several other methods currently available. This is a welcome finding at a time when complex data are routinely thrown into the AI machine and expected to deliver some kind of insight, often without explanation. That is not to say that AI and machine learning are not incredibly powerful methods. However, there is a tendency to use them in modern research without considering if they are the best tool for the job. This publication is a refreshing and much needed reminder of the power of different prediction tools such as linear models. 


“Our approach provides multiple methodological advancements, but this is still just the tip of the iceberg.” - Liat Shenhav. 

In the future, she and her colleagues will work to further improve the prediction accuracy of the model and explore additional applications. 

“Modeling the temporal behavior of the microbiome is a fundamental scientific question, with potential applications in medicine and beyond.”

Abstract

Given the highly dynamic and complex nature of the human gut microbial community, the ability to identify and predict time-dependent compositional patterns of microbes is crucial to our understanding of the structure and functions of this ecosystem. One factor that could affect such time-dependent patterns is microbial interactions, wherein community composition at a given time point affects the microbial composition at a later time point. However, the field has not yet settled on the degree of this effect. Specifically, it has been recently suggested that only a minority of taxa depend on the microbial composition in earlier times. To address the issue of identifying and predicting temporal microbial patterns we developed a new model, MTV-LMM (Microbial Temporal Variability Linear Mixed Model), a linear mixed model for the prediction of microbial community temporal dynamics. MTV-LMM can identify time-dependent microbes (i.e., microbes whose abundance can be predicted based on the previous microbial composition) in longitudinal studies, which can then be used to analyze the trajectory of the microbiome over time. We evaluated the performance of MTV-LMM on real and synthetic time series datasets, and found that MTV-LMM outperforms commonly used methods for microbiome time series modeling. Particularly, we demonstrate that the effect of the microbial composition in previous time points on the abundance of taxa at later time points is underestimated by a factor of at least 10 when applying previous approaches. Using MTV-LMM, we demonstrate that a considerable portion of the human gut microbiome, both in infants and adults, has a significant time-dependent component that can be predicted based on microbiome composition in earlier time points. This suggests that microbiome composition at a given time point is a major factor in defining future microbiome composition and that this phenomenon is considerably more common than previously reported for the human gut microbiome.

Reference

Shenhav L, Furman O, Briscoe L, Thompson M, Silverman JD, Mizrahi I, et al. (2019) Modeling the temporal dynamics of the gut microbial community in adults and infants. PLoS Comput Biol 15(6): e1006960. https://doi.org/10.1371/journal.pcbi.1006960

Ben Libberton

Science Communicator, Freelance

I'm a freelance science communicator, formerly a Postdoc in the biofilm field. I'm interested in how bacteria cause disease and look to technology to produce novel tools to study and ultimately prevent infection.

No comments yet.