Quantifying cell densities and biovolumes of phytoplankton communities and functional groups using scanning flow cytometry, machine learning and unsupervised clustering

Abstract

Scanning flow cytometry (SFCM) is characterized by the measurement of time-resolved pulses of fluorescence and scattering, enabling the high-throughput quantification of phytoplankton morphology and pigmentation. Quantifying variation at the single cell and colony level improves our ability to understand dynamics in natural communities. Automated high-frequency monitoring of these communities is presently limited by the absence of repeatable, rapid protocols to analyse SFCM datasets, where images of individual particles are not available. Here we demonstrate a repeatable, semi-automated method to (1) rapidly clean SFCM data from a phytoplankton community by removing signals that do not belong to live phytoplankton cells, (2) classify individual cells into trait clusters that correspond to functional groups, and (3) quantify the biovolumes of individual cells, the total biovolume of the whole community and the total biovolumes of the major functional groups. Our method involves the development of training datasets using lab cultures, the use of an unsupervised clustering algorithm to identify trait clusters, and machine learning tools (random forests) to (1) evaluate variable importance, (2) classify data points, and (3) estimate biovolumes of individual cells. We provide example datasets and R code for our analytical approach that can be adapted for analysis of datasets from other flow cytometers or scanning flow cytometers.

Trait‐based analysis of subpolar North Atlantic phytoplankton and plastidic ciliate communities using automated flow cytometer

“…In addition to light‐scattering properties, the fluorescence signatures resulting from excitation by the blue light (488 nm) were detected as emitted light at several wavelengths; red Chl a fluorescence (FR; 650–830 nm, about 95% of Chl a fluorescence arises from Photosystem II, Johnsen and Sakshaug ), orange fluorescence (FO, emission from phycobiliproteins; 562–650 nm), and yellow/green fluorescence (FY/G, decaying pigments; 515–562 nm, Fontana et al ). A “curvature” channel adds an extra two‐dimensional component by capturing the “split” forward scatter signal from a double laser beam with +45° (left) and −45° (right) polarization angles (Thomas et al ). If a particle has a curved or spiral shape (often observed in diatom chains; e.g., Chaetoceros curvisetus ), the forward scatter polarization ratio is high.…”

Light limitation increases multidimensional trait evenness in phytoplankton populations

“…Using this sample dataset, we trained a random forest classifying algorithm(Breiman 2001;Liaw & Wiener 2002) and assigned every particle in the whole dataset to one of the three abovementioned categories. The data cleaning and clustering procedure is described in detail inThomas et al (2018).Individual-based trait distributionThe regularity in the distribution of individual cells in multidimensional trait space was quantified for all samples using the TED index ('trait even distribution';Fontana, Petchey & Pomati 2016), which compares the probability density function (kernel density estimation) of pairwise distances between individuals in a target population or community and in a perfectly even reference trait distribution. For the calculation of this multivariate index four SFC-derived traits were used, which should reflect ability to compete for light: total fluorescence in each of the red, orange, yellow and green channels.…”

Semi-automated classification of colonial Microcystis by FlowCAM imaging flow cytometry in mesocosm experiment reveals high heterogeneity during seasonal bloom

“…This allowed us to create class-balanced training sets by choosing time points with sufficient amounts of all five Microcystis morphospecies. It is a first attempt to apply a semi-automatic algorithm for intrageneric analysis of colonial Microcystis , the majority of previous studies being focused on the analysis of colonial phytoplankton taxa at genus level 10 , 12 , 53 or used for analysis training sets build with single-celled Microcystis laboratory cultures 9 , 11 .…”