PhenoGMM: Gaussian mixture modelling of microbial cytometry data enables efficient predictions of biodiversity

Microbial flow cytometry allows to rapidly characterize microbial communities. Recent research has demonstrated a moderate to strong connection between the cytometric diversity and taxonomic diversity based on 16S rRNA gene amplicon sequencing data. This creates the opportunity to integrate both types of data to study and predict the microbial community diversity in an automated and efficient way. However, microbial flow cytometry data results in a number of unique challenges that need to be addressed. The results of our work are threefold: i) We expand current microbial cytometry fingerprinting approaches by proposing and validating a model-based fingerprinting approach based upon Gaussian Mixture Models, which we called PhenoGMM. ii) We show that microbial diversity can be rapidly estimated by PhenoGMM. In combination with a supervised machine learning model, diversity estimations based on 16S rRNA gene amplicon sequencing data can be predicted. iii) We evaluate our method extensively by using multiple datasets from different ecosystems and compare its predictive power with a generic binning fingerprinting approach that is commonly used in microbial flow cytometry. These results demonstrate the strong connection between the genetic make-up of a microbial community and its phenotypic properties as measured by flow cytometry. Our workflow facilitates the study of microbial diversity and community dynamics using flow cytometry in a fast and quantitative way.ImportanceMicroorganisms are vital components in various ecoystems on Earth. In order to investigate the microbial diversity, researchers have largely relied on the analysis of 16S rRNA gene sequences from DNA. Flow cytometry has been proposed as an alternative technique to characterize microbial community diversity and dynamics. It is an optical technique, able to rapidly characterize a number of phenotypic properties of individual cells. So-called fingerprinting techniques are needed in order to describe microbial community diversity and dynamics based on flow cytometry data. In this work, we propose a more advanced fingerprinting strategy based on Gaussian Mixture Models. When samples have been analyzed by both flow cytometry and 16S rRNA gene amplicon sequencing, we show that supervised machine learning models can be used to find the relationship between the two types of data. We evaluate our workflow on datasets from different ecosystems, illustrating its general applicability for the analysisof microbial flow cytometry data. PhenoGMM facilitates the rapid characterization and predictive modelling of microbial diversity using flow cytometry.