Machine learning for microfluidic design and control

Abstract

Microfluidics has developed into a mature field with applications across science and engineering, having particular commercial success in molecular diagnostics, next-generation sequencing, and bench-top analysis. Despite its ubiquity, the complexity of designing and controlling custom microfluidic devices present major barriers to adoption, requiring intuitive knowledge gained from years of experience. If these barriers were overcome, microfluidics could miniaturize biological and chemical research for non-experts through fully-automated platform development and operation. The intuition of microfluidic experts can be captured through machine learning, where complex statistical models are trained for pattern recognition and subsequently used for event prediction. Integration of machine learning with microfluidics could significantly expand its adoption and impact. Here, we present the current state of machine learning for the design and control of microfluidic devices, its possible applications, and current limitations.

Fig. 1. Overview of machine learning enabled automated microfluidic design and control. (A) Complex microfluidic devices, such as the MATE-seq platform, is comprised of two components, a deterministic-lateral-displacement array and droplet generator, which can be parameterized to describe both the physical design and experimental conditions. By mapping these parameters to a target performance, datasets can be generated and used to train machine learning models that predict the performance of each component. Design automation tools can use these models to automatically design each component such that the desired performance is achieved while adhering to design constraints. Figure reproduced from Ng et al., 2019 (ref. 9) with permission from the Royal Society of Chemistry. (B) Microfluidic devices, such as a droplet sorter, can consist of a series of vital non-fluidic modules (schematic copyright 2017 National Academy of Sciences). These include: (1) flow controllers to drive behavior of the device; (2) sensors to measure and quantify occurring phenomena; (3) actuators to manipulate device behavior on the single-event level; and (4) feedback systems to respond to sensor information and intelligently control device behavior via the other modules. Machine learning provides a sophisticated feedback system to intelligently link modules together to perform complex tasks in real-time.

Fig. 2. Overview of ML approaches in microfluidic performance prediction. (A) The performance of a microfluidic device is affected by the flow rates, fluid properties, device geometry, and material. (B) With informed sampling methods, this large design space can be explored experimentally or numerically to create a sufficiently sized dataset for training ML models. (C) Several classes of ML models, such as fully-connected neural networks (fcNN), convolutional neural networks (CNN), and autoencoders can be trained to gain generalizable predictive understanding of microfluidics. (D) Examples of ML-assisted performance prediction in several types of microfluidic devices. (D.i) An autoencoder in conjunction with a fcNN was used to predict droplet stability in tightly packed emulsions passing through a constriction. Figure reproduced from Khor et al., 2019 (ref. 77) with permission from the Royal Society of Chemistry. (D.ii) ML models were used to predict the distribution of lift in broad range of operating conditions, which was then used to estimate particle inertial focusing in multiple cross-sections. Figure reproduced from Su et al., 2021 (ref. 15) with permission from the Royal Society of Chemistry. (D.iii) CNNs were used to predict the solute concentrations and flow rates at the three outlets of a 2-inlet randomly designed grid micromixer. Figure reproduced from Wang et al., 2021 (ref. 78) with permission from the Royal Society of Chemistry.

Fig. 3. Examples of ML-assisted workflows for design automation of microfluidic devices. (A) Direct approaches use ML reverse models that convert the desired performance to microfluidic design parameters. (A.i) ML-assisted direct design automation were demonstrated for flow sculpting in inertial flows, figure reproduced from Stoecklein et al., 2017 (ref. 84) licensed by CC BY 4.0; and (A.ii) for generating user-specified concentration gradients, figure redrawn from Hong et al., 2020 (ref. 76) licensed by CC BY 4.0. (B) Iterative design automation uses ML forward models that convert microfluidic design parameters to the predicted performance in conjunction with a iterative search algorithm to convert the user specified desired performance to the necessary design parameters. Iterative design automation were demonstrated for (B.i) design automation of output solute concentrations and flow rates in randomly designed 2-inlet, 3-outlet grid micromixers, random mixer figure reproduced from Wang et al., 2016 (ref. 83) with permission from the Royal Society of Chemistry; and (B.ii) for droplet diameter and generation rate in flow-focusing microfluidic droplet generators, figure reproduced from Lashkaripour et al., 2021 (ref. 13) licensed by CC BY 4.0.

Fig. 4. Example of an application of machine-guided microfluidic control in its implementation to optimize droplet generation at multiple length scales. (A) After an initial sampling of the parameter space, (B) a small-scale dataset is generated and (C) automatically analyzed using computer vision methods. (D) These results are then fed into a Bayesian decision policy that determines the next set of data to generate. (E) This iterative loop continues until performance is optimized and the boundaries of the stable droplet generation regime is identified. Reprinted with permission from Siemenn et al., 2022. Copyright 2022 American Chemical Society.

Fig. 5. Outlook for machine learning in microfluidics. (A) To effectively learn microfluidic performance across the field, community repositories are needed consisting of standardized designs, fabrication protocols, and performance metrics together with predictive models previously trained on standardized datasets. These datasets and models can be retrieved by researchers, and adapted to new applications through transfer learning with additional smaller datasets. Sharing the updated models on community repositories completes a positive feedback cycle to continuously extend the predictive understanding of microfluidics to new components and applications. (B) Once the performance of enough components are accurately predicted, they can be integrated into an ML-guided “robot scientist” that can route together different components for fully-automated hypothesis testing and optimization. (C) Such a system has been successfully implemented in automated synthesis of organic compounds using millifluidic flow modules. From Coley et al., 2019. Reprinted with permission from AAAS.