Reducing versus Embracing Variation as Strategies for Reproducibility: The Microbiome of Laboratory Mice

Abstract

Irreproducibility is a well-recognized problem in biomedical animal experimentation. Phenotypic variation in animal models is one of the many challenging causes of irreproducibility. How to deal with phenotypic variation in experimental designs is a topic of debate. Both reducing and embracing variation are highlighted as strategies for reproducibility. In this theoretical review, we use variation in mouse microbiome composition as an example to analyze this ongoing discussion, drawing on both animal research and philosophy of science. We provide a conceptual explanation of reproducibility and analyze how the microbiome affects mouse phenotypes to demonstrate that the role of the microbiome in irreproducibility can be understood in two ways: (i) the microbiome can act as a confounding factor, and (ii) the result may not be generalizable to mice harboring a different microbiome composition. We elucidate that reducing variation minimizes confounding, whereas embracing variation ensures generalizability. These contrasting strategies make dealing with variation in experimental designs extremely complex. Here, we conclude that the most effective strategy depends on the specific research aim and question. The field of biomedical animal experimentation is too broad to identify a single optimal strategy. Thus, dealing with variation should be considered on a case-by-case basis, and awareness amongst researchers is essential.

Keywords: animal experiments; mouse microbiomes; reproducibility; variation.

Figure 1

Complex interactions between environment, mouse genotype and mouse microbiome might affect mouse phenotype.

Figure 2

Comparisons between wild-type and knockout mice are at risk of bias due to differences in microbiome composition resulting from separate breeding.

Figure 3

Variation in mouse microbiome composition can explain irreproducibility between (and also within) facilities as the effectiveness of a treatment might be specific to a certain microbiome composition and not generalizable to mice harboring different microbes.

Figure 4

Littermate-controlled experiments and cohousing to standardize mouse microbiome composition within an experiment to avoid confounding.