Droplet microfluidics for single-cell studies: a frontier in ecological understanding of microbiomes

Abstract

Recent advances in single-cell technologies have profoundly impacted our understanding of microbial communities-shedding light on cell-to-cell variability in gene expression, regulatory dynamics, and metabolic potential. These approaches have shown that microbial populations are more heterogeneous and functionally complex than previously thought. However, direct probing of single-cell physiology-arguably more ecologically relevant by focusing on functional traits such as growth, metabolic activity, and enzymatic activity-remains underexplored. Droplet microfluidics provides a practical and high-throughput approach to address this gap, allowing functional characterization of individual microbial cells within complex communities and offering new opportunities to study ecological processes at high resolution. In this review, we look at the state of droplet microfluidics for single-cell microbial ecology. We revisit the fundamentals of microbial droplet workflows, we overview the current capabilities of droplet microfluidics that exist for microbial ecology and we look at the phenomena these workflows have uncovered and understanding they have generated. Finally, we integrate these capabilities to envision future droplet workflows that could enhance our understanding of single-cell physiology and discuss the fundamental limitations that go together with the droplet format.

Keywords: bacterial interactions; cultivation; double emulsion; droplet microfluidics; functionality; microbial ecology; microbiology; single-cell technologies.

Figure 1.

Visualization of droplet generation, the parameter lambda and Poisson distribution. (a)-(f) Schematics of flow-focusing droplet generation chips with varying cell concentrations (C_cell) and droplet volumes (V_drop). The schematics show droplets being generated, of which the microbial load is described by the Poisson distribution and the parameter lambda. (g) Poisson distributions of different lambda values. The x-axis represents the number of microbial cells per droplet (k) and the y-axis represents the fraction of droplets that contain k microbial cells. There are 4 different λ-values with each their Poisson distribution plotted and a schematic of a sample of the droplet population. The Poisson distributions from most left-skewed to most right-skewed are λ = 0.05 (blue), λ = 0.5 (orange), λ = 2 (yellow) and λ = 5 (green). E.g. for lambda = 0.05, there are 95% empty droplets, 5% of droplets contain 1 microbial cell per droplet, more than 1 microbial cells per droplet is a negligible fraction.

Figure B1

Overview of droplet assay terminology as used in this review. Schematic representation of the combinations of key parameters determining the terminology of dropletbased microbiology assays: (1) the number of cells per droplet (single-cell vs. multi-cell inoculation), (2) the number of genotypes per droplet (single genotype vs. co-inoculation of multiple genotypes), and (3) whether or not outgrowth occurs prior to measurement (direct measurement vs. outgrowth measurement).

Figure 2.

Fluorescent functionality screening methods in droplet microfluidics. Schematic overview of various approaches to assess cellular functions at the single-cell level (or of single-cell outgrowth) within droplets: (a) Fluorogenic substrates detect specific enzymatic activities by producing a fluorescent signal upon substrate conversion. (b) Fluorescent metabolites allow for direct detection of secreted or accumulated fluorescent products. (c) Bioreporters involve engineered cells that emit a fluorescence signal in response to a target metabolite. (d) Enzymatic assays couple cellular metabolite production to the production of a fluorescent signal through a double enzymatic reaction scheme. The metabolite of interest is oxidized, producing hydrogen peroxide. This hydrogen peroxide is then used by horseradish peroxidase to reduce a fluorogenic compound which in turn turns fluorescent. (e) Aptamer-based sensors use oligonucleotides that bind specific metabolites, inducing a conformational change that results in fluorescence.

Figure 3.

Overview of droplet-based interaction screening strategies. (a) kChip pairwise screening: A library of n microbial isolates is prepared, where in each of n experiments a different isolate is fluorescently tagged (e.g. with green fluorescent protein). The remaining isolates are identified by their droplet colour code. Multi-cell inoculated droplet populations for each isolate are generated, randomly paired and fused. After incubation, the growth of the tagged strain is quantified via fluorescent protein expression, serving as a proxy for biomass. By systematically switching the tagged isolate across experiments, all pairwise interactions between strains can be mapped. (b) Multi-fluorescent labelling approach: Microbial species are labelled with distinct fluorescent proteins, allowing their identification. They are randomly co-encapsulated, incubated, and monitored over time. Growth trajectories for each initial combination reveal single-cell interaction dynamics. (c) Focal species community screening: A single fluorescently tagged focal species is randomly co-encapsulated with community-derived microbial cells. After incubation, droplets are screened based on focal species fluorescence intensity, measuring single-cell interaction effects on the focal species enabling downstream sorting and sequencing to associate droplet compositions with focal species growth outcomes. (d) Random co-encapsulation: Community members are randomly encapsulated. Post-incubation, droplets are sorted based on overall biomass or functionality. Sequencing identifies the microbial consortia associated with specific endpoint phenotypes.

Figure 4.

Dissecting functional dynamics in a simple cellulose-degrading community using droplet-based single-cell screening. (a) Time-resolved schematic of a cellulose-degrading community composed of four members: the mutualistic pair A (green curved rod) and B (magenta bacillus), a prototrophic degrader C (orange bacillus), and the emergent non-cellulase-producing mutant A° (magenta curved rod). (b) Key ecological events driving system dynamics, including the emergence of A° at t0, its takeover at t1, and the collapse of mutualism leading to the rise of C at t2. (c) 16S rRNA-based taxonomic profiles over time illustrate shifts in community composition but fail to resolve functional changes such as the rise of A°, as it is indistinguishable from A in standard taxonomic data. (d) Density distribution of flow cytometry measurements of double emulsions reporting on cellulase activity (left) and tryptophan secretions (right). The y-axis reflects the fluorescence signal corresponding to the functional readout and the x-axis shows the relative amount of droplets that show that level of fluorescence. This enables detection of functional guilds and the emergence of A°, which are invisible to bulk approaches. Functional clusters are sorted and sequenced, linking phenotype to genotype.