Coding of Experimental Conditions in Microfluidic Droplet Assays Using Colored Beads and Machine Learning Supported Image Analysis

Abstract

To efficiently exploit the potential of several millions of droplets that can be considered as individual bioreactors in microfluidic experiments, methods to encode different experimental conditions in droplets are needed. The approach presented here is based on coencapsulation of colored polystyrene beads with biological samples. The decoding of the droplets, as well as content quantification, are performed by automated analysis of triggered images of individual droplets in‐flow using bright‐field microscopy. The decoding strategy combines bead classification using a random forest classifier and Bayesian inference to identify different codes and thus experimental conditions. Antibiotic susceptibility testing of nine different antibiotics and the determination of the minimal inhibitory concentration of a specific antibiotic against a laboratory strain of Escherichia coli are presented as a proof‐of‐principle. It is demonstrated that this method allows successful encoding and decoding of 20 different experimental conditions within a large droplet population of more than 105 droplets per condition. The decoding strategy correctly assigns 99.6% of droplets to the correct condition and a method for the determination of minimal inhibitory concentration using droplet microfluidics is established. The current encoding and decoding pipeline can readily be extended to more codes by adding more bead colors or color combinations.

Advanced Characterisation of a Sensor System for Droplet-Based Microfluidics

“…This allows for a significant increase of achievable information rate in comparison to previous approaches with presence/absence or distance encoding. In contrast to [17] no beads have to be introduced to achieve colour coding. Furthermore, a large colour alphabet made up of three fundamental colours can be used, wheras in [17] only 20 different predetermined bead colours were differentiated.…”

“…A state-of-the-art video processing tool was presented in [16], which enables the evaluation of multiple droplet parameters, such as size and velocity. Colour coded characterisation of droplets was achieved in [17] by injecting droplets with coloured polystyrene beads. These were detected under a bright-field microscope with the use of machine learning to differentiate between 20 different states.…”

“…The aim of this work is to further investigate the capabilities of this sensor device for droplet characterisation in terms of droplet size and colour, which can be used for information encoding in data transmission scenarios, as well as for other LoC applications. In contrast to [17], we propose a more flexible coding system for colour coded data transmission, using ink to produce coloured droplets, allowing for the creation of a large coding alphabet by mixing three fundamental colours.…”

Microfluidics for Biosynthesizing: from Droplets and Vesicles to Artificial Cells

“…The fluid in the orifice was used to provides shearing force, and it can deform another fluid ejected from the nozzle and finally produce droplets . Flow‐focusing techniques for the fabrication of droplets were widely used, for example, the preparation of the ferrofluid droplets and the droplets with colored polystyrene beads . Droplets' application prospects were highly relevant to the microfluidic system.…”

“…With the highly integrated microfluidic systems, the multiphase fluids in devices can be operated to realize coexistence or diverse interplays. Recent advances in microfabrication technologies for the fabrication of colorful droplets, microgels, and microspheres have greatly broadened their applications. The utilization of microfluidic methods for biosynthesizing has drawn increasing attention, and one of the eye‐catching emerging applications is the microfluidic platform based artificial cell fabrication …”