Dataset Information

Machine learning enables design automation of microfluidic flow-focusing droplet generation.

ABSTRACT: Droplet-based microfluidic devices hold immense potential in becoming inexpensive alternatives to existing screening platforms across life science applications, such as enzyme discovery and early cancer detection. However, the lack of a predictive understanding of droplet generation makes engineering a droplet-based platform an iterative and resource-intensive process. We present a web-based tool, DAFD, that predicts the performance and enables design automation of flow-focusing droplet generators. We capitalize on machine learning algorithms to predict the droplet diameter and rate with a mean absolute error of less than 10 ?m and 20 Hz. This tool delivers a user-specified performance within 4.2% and 11.5% of the desired diameter and rate. We demonstrate that DAFD can be extended by the community to support additional fluid combinations, without requiring extensive machine learning knowledge or large-scale data-sets. This tool will reduce the need for microfluidic expertise and design iterations and facilitate adoption of microfluidics in life sciences.

SUBMITTER: Lashkaripour A

PROVIDER: S-EPMC7782806 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning enables design automation of microfluidic flow-focusing droplet generation.

Lashkaripour Ali A Rodriguez Christopher C Mehdipour Noushin N Mardian Rizki R McIntyre David D Ortiz Luis L Campbell Joshua J Densmore Douglas D

Nature communications 20210104 1

Droplet-based microfluidic devices hold immense potential in becoming inexpensive alternatives to existing screening platforms across life science applications, such as enzyme discovery and early cancer detection. However, the lack of a predictive understanding of droplet generation makes engineering a droplet-based platform an iterative and resource-intensive process. We present a web-based tool, DAFD, that predicts the performance and enables design automation of flow-focusing droplet generato ...[more]

PMID: 33397940

Similar Datasets

Project description:Most commercial microfluidic droplet generators rely on the planar flow-focusing configuration implemented in polymer or glass chips. The planar geometry, however, suffers from many limitations and drawbacks, such as the need of specific coatings or the use of dedicated surfactants, depending on the fluids in play. On the contrary, and thanks to their axisymmetric geometry, glass capillary-based droplet generators are a priori not fluid-dependent. Nevertheless, they have never reached the market because their assembly requires fastidious and not scalable fabrication techniques. Here we present a new device, called Raydrop, based on the alignment of two capillaries immersed in a pressurized chamber containing the continuous phase. The dispersed phase exits one of the capillaries through a 3D-printed nozzle placed in front of the extraction capillary for collecting the droplets. This non-embedded implementation of an axisymmetric flow-focusing is referred to non-embedded co-flow-focusing configuration. Experimental results demonstrate the universality of the device in terms of the variety of fluids that can be emulsified, as well as the range of droplet radii that can be obtained, without neither the need of surfactant nor coating. Additionally, numerical computations of the Navier-Stokes equations based on the quasi-steadiness assumption allow to provide an explanation to the underlying mechanism behind the drop formation and the mechanism of the dripping to jetting transition. Excellent predictions were also obtained for the droplet radius, as well as for the dripping-jetting transition, when varying the geometrical and fluid parameters, showing the ability of this configuration to enventually enhance the dripping regime. The monodispersity ensured by the dripping regime, the robustness of the fabrication technique, the optimization capabilities from the numerical modelling and the universality of the configuration confer to the Raydrop technology a very high potential in the race towards high-throughput droplet generation processes.

Dataset Information

Machine learning enables design automation of microfluidic flow-focusing droplet generation.

Publications

Machine learning enables design automation of microfluidic flow-focusing droplet generation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets