An official website of the United States government
Abstract Droplet microfluidics enables kHz screening of picoliter samples at a fraction of the cost of other high-throughput approaches. However, generating stable droplets with desired characteristics typically requires labor-intensive empirical optimization of device designs and flow conditions that limit adoption to specialist labs. Here, we compile a comprehensive droplet dataset and use it to train machine learning models capable of accurately predicting device geometries and flow conditions required to generate stable aqueous-in-oil and oil-in-aqueous single and double emulsions from 15 to 250 μm at rates up to 12000 Hz for different fluids commonly used in life sciences. Blind predictions by our models for as-yet-unseen fluids, geometries, and device materials yield accurate results, establishing their generalizability. Finally, we generate an easy-to-use design automation tool that yield droplets within 3 μm (<8%) of the desired diameter, facilitating tailored droplet-based platforms and accelerating their utility in life sciences.
more »
« less
This content will become publicly available on May 1, 2026
Artificial Intelligence‐Empowered Automated Double Emulsion Droplet Library Generation
Abstract Double emulsions with core‐shell structures are versatile materials used in applications such as cell culture, drug delivery, and materials synthesis. A droplet library with precisely controlled dimensions and properties would streamline screening and optimization for specific applications. While microfluidic droplet generation offers high precision, it is typically labor‐intensive and sensitive to disturbances, requiring continuous operator intervention. To address these limitations, we present an artificial intelligence (AI)‐empowered automated double emulsion droplet library generator. This system integrates a convolutional neural network (CNN)‐based object detection model, decision‐making, and feedback control algorithms to automate droplet generation and collection. The system monitors droplet generation every 171 ms—faster than a Formula 1 driver's reaction time—ensuring rapid response to disturbances and consistent production of single‐core double emulsions. It autonomously generates libraries of 25 distinct monodisperse droplets with user‐defined properties. This automation reduces labor and waste, enhances precision, and supports rapid and reliable droplet library generation. We anticipate that this platform will accelerate discovery and optimization in biomedical, biological, and materials research.
more »
« less
- Award ID(s):
- 2152205
- PAR ID:
- 10588742
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Small
- Volume:
- 21
- Issue:
- 18
- ISSN:
- 1613-6810
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present Jammed Interconnected Bilayer Emulsions (JIBEs) as a class of tissue-like materials with macroscopic scalability and rapid fabrication, comprising millions to billions of bilayer-separated aqueous compartments. These materials closely mimic the organizational structure and properties of biological tissues. Our rapid self-assembly method for producing JIBEs generates milliliter- to deciliter-scale volumes within minutes representing over 10,000-fold improvement in the fabrication speed of droplet-based artificial tissues compared to existing droplet-based methods, enabling the creation of a truly macroscopic material. The method is highly adaptable to a wide range of amphiphiles, including lipids and block-copolymers, providing flexibility in tailoring JIBEs for diverse applications. The jammed architecture of JIBEs imparts unique properties, such as direct 3D-printabilty into aqueous solutions or onto air-exposed surfaces. Their membrane-bound structure also allows functionalization with biological and artificial nanochannels, enabling the material to exhibit the specific properties of the incorporated channels. In this work, we demonstrate three key features of JIBEs using distinct ion channels: tunable conductance, selective transport, and memristance. Incorporating an E. coli outer membrane protein increased ionic conductance by approximately 4,400-fold compared to non-functionalized tissues. Introducing a peptide-based transporter produced ion-selective membranes capable of discriminating ammonium over sodium at a ratio greater than 15:1. Finally, incorporating a model voltage-gated pore enabled the construction of a massively networked memristive device. We propose that functionalizing JIBEs with additional membrane proteins or synthetic ion channels could unlock a broad range of applications, including separations, energy generation and storage, neuromorphic computing, tissue engineering, drug delivery, and soft robotics.more » « less
-
null (Ed.)Microfluidic devices enable the production of uniform double emulsions with control over droplet size and shell thickness. However, the limited production rate of microfluidic devices precludes the use of monodisperse double emulsions for industrial-scale applications, which require large quantities of droplets. To increase throughput, devices can be parallelized to contain many dropmakers operating simultaneously in one chip, but this is challenging to do for double emulsion dropmakers. Production of double emulsions requires dropmakers to have both hydrophobic and hydrophilic channels, requiring spatially precise patterning of channel surface wettability. Precise wettability patterning is difficult for devices containing multiple dropmakers, posing a significant challenge for parallelization. In this paper, we present a multilayer dropmaker geometry that greatly simplifies the process of producing microfluidic devices with excellent spatial control over channel wettability. Wettability patterning is achieved through the independent functionalization of channels in each layer prior to device assembly, rendering the dropmaker with a precise step between hydrophobic and hydrophilic channels. This device geometry enables uniform wettability patterning of parallelized dropmakers, providing a scalable approach for the production of double emulsions.more » « less
-
Microencapsulation of pristine core liquids in polymer shells has critical applications in thermal energy storage and management, targeted drug delivery, and carbon capture, among others. Herein, we report a novel encapsulation approach based on a double emulsion soft-template to produce microcapsules comprised of an ionic liquid (IL) core in a degradable polymer shell. We demonstrate the production of [IL-in-oil1]-in-oil2 (IL/O1/O2) double emulsions, in which the oil interphase (O1) contains a CO2-derived polycarbonate bearing vinyl pendant groups, tetrathiol small molecule crosslinker, and photoinitiator; upon irradiation of the double emulsion under low shear, thiol–ene crosslinking of the loaded species results in the formation of a robust shell around the pure IL droplets. The core–shell structures have enhanced physisorption for CO2 uptake compared to the bulk IL, which is consistent with the combined capacity of the IL/shell alone and demonstrates more rapid uptake due to an enhanced gas–liquid interface. This approach to microencapsulation of functional liquids offers researchers a distinct route to fabricate composite architectures with a pristine core for applications in separations, transport of cargo, and gas uptake.more » « less
-
We report a microfluidic droplet generator which can produce single and compound droplets using a 3D axisymmetric co-flow structure. The design considered for the fabrication of the device integrated a user-friendly and cost-effective 3D printing process. To verify the performance of the device, single and compound emulsions of deionized water and mineral oil were generated and their features such as size, generation frequency, and emulsion structures were successfully characterized. In addition, the generation of bio emulsions such as alginate and collagen aqueous droplets in mineral oil was demonstrated in this study. Overall, the monolithic 3D printed axisymmetric droplet generator could offer any user an accessible and easy-to-utilize device for the generation of single and compound emulsions.more » « less
