Label-Free Phytoplankton Analysis by High-Throughput Quantitative Phase Imaging Cytometry and Machine Learning

Phytoplankton, highly diversified in species, plays a critical role in the atmospheric carbon cycle and marine ecosystem [1]. Capable of doing large-scale analysis of phytoplankton is thus of significance in environmental monitoring and biofuel production. However, current techniques lack the throughput to efficiently screen the highly heterogeneous population of phytoplankton at the single-cell precision for accurate taxonomic classification and/or overwhelmingly rely upon biochemical assays, which are typically non-invasive and destructive, to characterise the physiological states and functions. Here we report a high-throughput, label-free imaging flow cytometer (>10,000 cells/sec) based on a new type of quantitative phase imaging technique, called multiplexed asymmetric-detection time-stretch optical microscopy (multi-ATOM) [2] combined with a supervised learning strategy. We demonstrate that multi-ATOM provides sufficient label-free statistical power for multi-class classification of phytoplankton (13 classes) (Fig. 1a-b). We also show that the label-free single-cell biophysical phenotypes (>100) derived from multi-ATOM are sensitive to changes in cultivation nutrient and could be the potential label-free biomarkers for lipid-content screening in biofuel production (Fig. 1c-d).