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

Democratizing Microreactor Technology for Accelerated Discoveries in Chemistry and Materials Research

Microreactor technologies have emerged as versatile platforms with the potential to revolutionize chemistry and materials research, offering sustainable solutions to global challenges in environmental and health domains. This survey paper provides an in-depth review of recent advancements in microreactor technologies, focusing on their role in facilitating accelerated discoveries in chemistry and materials. Specifically, we examine the convergence of microfluidics with machine intelligence and automation, enabling the exploitation of the cyber-physical environment as a highly integrated experimentation platform for rapid scientific discovery and process development. We investigate the applicability and limitations of microreactor-enabled discovery accelerators in various chemistry and materials contexts. Despite their tremendous potential, the integration of machine intelligence and automation into microreactor-based experiments presents challenges in establishing fully integrated, automated, and intelligent systems. These challenges can hinder the broader adoption of microreactor technologies within the research community. To address this, we review emerging technologies that can help lower barriers and facilitate the implementation of microreactor-enabled discovery accelerators. Lastly, we provide our perspective on future research directions for democratizing microreactor technologies, with the aim of accelerating scientific discoveries and promoting widespread adoption of these transformative platforms.

Machine learning assisted microfluidics dual fluorescence flow cytometry for detecting bladder tumor cells based on morphological characteristic parameters

BACKGROUND

Bladder cancer (BC) is the most common malignant tumor and has become a major public health problem, leading the causes of death worldwide. The detection of BC cells is of great significance for clinical diagnosis and disease treatment. Urinary cytology based liquid biopsy remains high specificity for early diagnosis of BC, however, it still requires microscopy examination which heavily relies on manual operations. It is imperative to investigate the potential of automated and indiscriminate cell differentiation technology to enhance the sensitivity and efficiency of urine cytology.

RESULTS

Here, we developed a machine learning algorithm empowered dual-fluorescence flow cytometry platform (μ-FCM) for urinary cytology analysis. A phenotype characteristic parameter (CP) which correlated with the size of the cell and nucleus was defined to achieve the differentiation of the BC cells and uroepithelial cells with high throughput and high accuracy. Based on CP analysis, SV-HUC-1 cells were almost differentiated from EJ cells and effectively reduced the overlap with 5637 cells. To further differentiate SV-HUC-1 cells and 5637 cells, support vector machine (SVM) machine learning algorithm was optimized to assist data analysis with the highest accuracies of 84.7 % for cell differentiation including the specificity of 91.0 % and the sensitivity of 75.0 %. Furthermore, the false positive rate (FPR) compensation enabled the detection rates of rare BC cells predicted by the well-trained SVM model were close to the true proportions with the recognition error in 0.4 % for the tumor cells.

SIGNIFICANCE

As a proof of concept, the developed μ-FCM system successfully demonstrates the capacity to identify the distribution of exfoliated cells in real urine samples. This system underscores the significance of integrating AI with microfluidics to perform high-throughput phenotyping of exfoliated cells, offering a pathway toward scalable, efficient, and automatic microfluidic systems in the fields of both biosensing and in vitro diagnosis of BC.

Discussion: Embracing microfluidics to advance environmental science and technology

Microfluidics, also called lab-on-a-chip, represents an emerging research platform that permits more precise and manipulation of samples at the microscale or even down to the nanoscale (nanofluidic) including picoliter droplets, microparticles, and microbes within miniaturized and highly integrated devices. This groundbreaking technology has made significant strides across multiple disciplines by providing an unprecedented view of physical, chemical, and biological events, fostering a holistic and an in-depth understanding of complex systems. The application of microfluidics to address the challenges in environmental science is likely to contribute to our better understanding, however, it's not yet fully developed. To raise researchers' interest, this discussion first delineates the valuable and underutilized environmental applications of microfluidic technology, ranging from environmental surveillance to acting as microreactors for investigating interfacial dynamic processes, and facilitating high-throughput bioassays. We highlight, with examples, how rationally designed microfluidic devices lead to new insights into the advancement of environmental science and technology. We then critically review the key challenges that hinder the practical adoption of microfluidic technologies. Specifically, we discuss the extent to which microfluidics accurately reflect realistic environmental scenarios, outline the areas to be improved, and propose strategies to overcome bottlenecks that impede the broad application of microfluidics. We also envision new opportunities and future research directions, aiming to provide guidelines for the broader utilization of microfluidics in environmental studies.

Towards Design Automation of Microfluidic Mixers: Leveraging Reinforcement Learning and Artificial Neural Networks

Microfluidic mixers, a pivotal application of microfluidic technology, are primarily utilized for the rapid amalgamation of diverse samples within microscale devices. Given the intricacy of their design processes and the substantial expertise required from designers, the intelligent automation of microfluidic mixer design has garnered significant attention. This paper discusses an approach that integrates artificial neural networks (ANNs) with reinforcement learning techniques to automate the dimensional parameter design of microfluidic mixers. In this study, we selected two typical microfluidic mixer structures for testing and trained two neural network models, both highly precise and cost-efficient, as alternatives to traditional, time-consuming finite-element simulations using up to 10,000 sets of COMSOL simulation data. By defining effective state evaluation functions for the reinforcement learning agents, we utilized the trained agents to successfully validate the automated design of dimensional parameters for these mixer structures. The tests demonstrated that the first mixer model could be automatically optimized in just 0.129 s, and the second in 0.169 s, significantly reducing the time compared to manual design. The simulation results validated the potential of reinforcement learning techniques in the automated design of microfluidic mixers, offering a new solution in this field.

Advancing Intelligent Organ-on-a-Chip Systems with Comprehensive In Situ Bioanalysis

In vitro models are essential to a broad range of biomedical research, such as pathological studies, drug development, and personalized medicine. As a potentially transformative paradigm for 3D in vitro models, organ-on-a-chip (OOC) technology has been extensively developed to recapitulate sophisticated architectures and dynamic microenvironments of human organs by applying the principles of life sciences and leveraging micro- and nanoscale engineering capabilities. A pivotal function of OOC devices is to support multifaceted and timely characterization of cultured cells and their microenvironments. However, in-depth analysis of OOC models typically requires biomedical assay procedures that are labor-intensive and interruptive. Herein, the latest advances toward intelligent OOC (iOOC) systems, where sensors integrated with OOC devices continuously report cellular and microenvironmental information for comprehensive in situ bioanalysis, are examined. It is proposed that the multimodal data in iOOC systems can support closed-loop control of the in vitro models and offer holistic biomedical insights for diverse applications. Essential techniques for establishing iOOC systems are surveyed, encompassing in situ sensing, data processing, and dynamic modulation. Eventually, the future development of iOOC systems featuring cross-disciplinary strategies is discussed.

Deep learning-augmented T-junction droplet generation

Droplet generation technology has become increasingly important in a wide range of applications, including biotechnology and chemical synthesis. T-junction channels are commonly used for droplet generation due to their integration capability of a larger number of droplet generators in a compact space. In this study, a finite element analysis (FEA) approach is employed to simulate droplet production and its dynamic regimes in a T-junction configuration and collect data for post-processing analysis. Next, image analysis was performed to calculate the droplet length and determine the droplet generation regime. Furthermore, machine learning (ML) and deep learning (DL) algorithms were applied to estimate outputs through examination of input parameters within the simulation range. At the end, a graphical user interface (GUI) was developed for estimation of the droplet characteristics based on inputs, enabling the users to preselect their designs with comparable microfluidic configurations within the studied range.

Recent developments and future perspectives of microfluidics and smart technologies in wearable devices

Wearable devices are gaining popularity in the fields of health monitoring, diagnosis, and drug delivery. Recent advances in wearable technology have enabled real-time analysis of biofluids such as sweat, interstitial fluid, tears, saliva, wound fluid, and urine. The integration of microfluidics and emerging smart technologies, such as artificial intelligence (AI), machine learning (ML), and Internet of Things (IoT), into wearable devices offers great potential for accurate and non-invasive monitoring and diagnosis. This paper provides an overview of current trends and developments in microfluidics and smart technologies in wearable devices for analyzing body fluids. The paper discusses common microfluidic technologies in wearable devices and the challenges associated with analyzing each type of biofluid. The paper emphasizes the importance of combining smart technologies with microfluidics in wearable devices, and how they can aid diagnosis and therapy. Finally, the paper covers recent applications, trends, and future developments in the context of intelligent microfluidic wearable devices.

Droplet Microfluidics for Current Cancer Research: From Single-Cell Analysis to 3D Cell Culture

Cancer is the second leading cause of death worldwide. Differences in drug resistance and treatment response caused by the heterogeneity of cancer cells are the primary reasons for poor cancer therapy outcomes in patients. In addition, current in vitro anticancer drug-screening methods rely on two-dimensional monolayer-cultured cancer cells, which cannot accurately predict drug behavior in vivo. Therefore, a powerful tool to study the heterogeneity of cancer cells and produce effective in vitro tumor models is warranted to leverage cancer research. Droplet microfluidics has become a powerful platform for the single-cell analysis of cancer cells and three-dimensional cell culture of in vitro tumor spheroids. In this review, we discuss the use of droplet microfluidics in cancer research. Droplet microfluidic technologies, including single- or double-emulsion droplet generation and passive- or active-droplet manipulation, are concisely discussed. Recent advances in droplet microfluidics for single-cell analysis of cancer cells, circulating tumor cells, and scaffold-free/based 3D cell culture of tumor spheroids have been systematically introduced. Finally, the challenges that must be overcome for the further application of droplet microfluidics in cancer research are discussed.

A universal inverse design methodology for microfluidic mixers

The intelligent design of microfluidic mixers encompasses both the automation of predicting fluid performance and the structural design of mixers. This article delves into the technical trajectory of computer-aided design for micromixers, leveraging artificial intelligence algorithms. We propose an automated micromixer design methodology rooted in cost-effective artificial neural network (ANN) models paired with inverse design algorithms. Initially, we introduce two inverse design methods for micromixers: one that combines ANN with multi-objective genetic algorithms, and another that fuses ANN with particle swarm optimization algorithms. Subsequently, using two benchmark micromixers as case studies, we demonstrate the automatic derivation of micromixer structural parameters. Finally, we automatically design and optimize 50 sets of micromixer structures using the proposed algorithms. The design accuracy is further enhanced by analyzing the inverse design algorithm from a statistical standpoint.

High-throughput microfluidic systems accelerated by artificial intelligence for biomedical applications

High-throughput microfluidic systems are widely used in biomedical fields for tasks like disease detection, drug testing, and material discovery. Despite the great advances in automation and throughput, the large amounts of data generated by the high-throughput microfluidic systems generally outpace the abilities of manual analysis. Recently, the convergence of microfluidic systems and artificial intelligence (AI) has been promising in solving the issue by significantly accelerating the process of data analysis as well as improving the capability of intelligent decision. This review offers a comprehensive introduction on AI methods and outlines the current advances of high-throughput microfluidic systems accelerated by AI, covering biomedical detection, drug screening, and automated system control and design. Furthermore, the challenges and opportunities in this field are critically discussed as well.

Generation of Multiple Concentration Gradients Using a Two-Dimensional Pyramid Array

Concentration heterogeneity of diffusible reactants is a prevalent phenomenon in biochemical processes, requiring the generation of concentration gradients for the relevant experiments. In this study, we present a high-density pyramid array microfluidic network for the effective and precise generation of multiple concentration gradients. The complex gradient distribution in the 2D array can be adaptively adjusted by modulating the reactant velocities and concentrations at the inlets. In addition, the unique design of each reaction chamber and mixing block in the array ensures uniform concentrations within each chamber during dynamic changes, enabling large-scale reactions with low reactant volumes. Through detailed numerical simulation of mass transport within the complex microchannel networks, the proposed method allows researchers to determine the desired number of reaction chambers within a given concentration range based on experimental requirements and to quickly obtain the operating conditions with the help of machine learning-based prediction. The effectiveness in generating a multiple concentration gradient environment was further demonstrated by concentration-dependent calcium carbonate crystallization experiments. This device provides a highly efficient mixing and adaptable concentration platform that is well suited for high-throughput and multiplexed reactions.

Counter-on-chip for bacterial cell quantification, growth, and live-dead estimations

Quantifying bacterial cell numbers is crucial for experimental assessment and reproducibility, but the current technologies have limitations. The commonly used colony forming units (CFU) method causes a time delay in determining the actual numbers. Manual microscope counts are often error-prone for submicron bacteria. Automated systems are costly, require specialized knowledge, and are erroneous when counting smaller bacteria. In this study, we took a different approach by constructing three sequential generations (G1, G2, and G3) of counter-on-chip that accurately and timely count small particles and/or bacterial cells. We employed 2-photon polymerization (2PP) fabrication technology; and optimized the printing and molding process to produce high-quality, reproducible, accurate, and efficient counters. Our straightforward and refined methodology has shown itself to be highly effective in fabricating structures, allowing for the rapid construction of polydimethylsiloxane (PDMS)-based microfluidic devices. The G1 comprises three counting chambers with a depth of 20 µm, which showed accurate counting of 1 µm and 5 µm microbeads. G2 and G3 have eight counting chambers with depths of 20 µm and 5 µm, respectively, and can quickly and precisely count Escherichia coli cells. These systems are reusable, accurate, and easy to use (compared to CFU/ml). The G3 device can give (1) accurate bacterial counts, (2) serve as a growth chamber for bacteria, and (3) allow for live/dead bacterial cell estimates using staining kits or growth assay activities (live imaging, cell tracking, and counting). We made these devices out of necessity; we know no device on the market that encompasses all these features.

Design automation of microfluidic single and double emulsion droplets with machine learning

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.

Automated design of a 3D passive microfluidic particle sorter

Microfluidic chips that can sort mixtures of cells and other particles have important applications in research and healthcare. However, designing a sorter chip for a given application is a slow and difficult process, especially when we extend the design space from 2D into a 3D scenario. Compared to the 2D scenario, we need to explore more geometries to derive the appropriate design due to the extra dimension. To evaluate sorting performance, the simulation of the particle trajectory is needed. The 3D scenario brings particle trajectory simulation more challenges of runtime and collision handling with irregular obstacle shapes. In this paper, we propose a framework to design a 3D microfluidic particle sorter for a given application with an efficient 3D particle trajectory simulator. The efficient simulator enables us to simulate more samples to ensure the robustness of the sorting performance. Our experimental result shows that the sorter designed by our framework successfully separates the particles with the targeted size.

Rational Design and Development of Polymeric Nanogels as Protein Carriers

Proteins have gained significant attention as potential therapeutic agents owing to their high specificity and reduced toxicity. Nevertheless, their clinical utility is hindered by inherent challenges associated with stability during storage and after in vivo administration. To overcome these limitations, polymeric nanogels (NGs) have emerged as promising carriers. These colloidal systems are capable of efficient encapsulation and stabilization of protein cargoes while improving their bioavailability and targeted delivery. The design of such delivery systems requires a comprehensive understanding of how the synthesis and formulation processes affect the final performance of the protein. This review highlights critical aspects involved in the development of NGs for protein delivery, with specific emphasis on loading strategies and evaluation techniques. For example, factors influencing loading efficiency and release kinetics are discussed, along with strategies to optimize protein encapsulation through protein-carrier interactions to achieve the desired therapeutic outcomes. The discussion is based on recent literature examples and aims to provide valuable insights for researchers working toward the advancement of protein-based therapeutics.

Versatility and stability optimization of flow-focusing droplet generators via quality metric-driven design automation

Droplet generation is a fundamental component of droplet microfluidics, compartmentalizing biological or chemical systems within a water-in-oil emulsion. As adoption of droplet microfluidics expands beyond expert labs or integrated devices, quality metrics are needed to contextualize the performance capabilities, improving the reproducibility and efficiency of operation. Here, we present two quality metrics for droplet generation: performance versatility, the operating range of a single device, and stability, the distance of a single operating point from a regime change. Both metrics were characterized in silico and validated experimentally using machine learning and rapid prototyping. These metrics were integrated into a design automation workflow, DAFD 2.0, which provides users with droplet generators of a desired performance that are versatile or flow stable. Versatile droplet generators with stable operating points accelerate the development of sophisticated devices by facilitating integration of other microfluidic components and improving the accuracy of design automation tools.

A general neural network model co-driven by mechanism and data for the reliable design of gas-liquid T-junction microdevices

In recent years, many models have been developed to describe the gas-liquid microdispersion process, which mainly rely on mechanistic analysis and may not be universally applicable. In order to provide a more comprehensive model and, most significantly, to provide a model for design, we have established a general database of microbubble generation in T-junction microdevices, including 854 data points from 12 pieces of literature. A neural network model that combines mechanistic and data modeling is developed. By transfer learning, more accurate results can be obtained. Additionally, we have proposed a design method that enables a relative deviation of less than 5% from the expected bubble size. A new device was designed and prepared to confirm the reliability of the method, which can prepare smaller bubbles than other common T-junction devices. In this way, a general and universal database and model are established and a design method for a gas-liquid T-junction microreactor is developed.

WSCNet: Biomedical Image Recognition for Cell Encapsulated Microfluidic Droplets

Microfluidic droplets accommodating a single cell as independent microreactors are frequently demanded for single-cell analysis of phenotype and genotype. However, challenges exist in identifying and reducing the covalence probability (following Poisson's distribution) of more than two cells encapsulated in one droplet. It is of great significance to monitor and control the quantity of encapsulated content inside each droplet. We demonstrated a microfluidic system embedded with a weakly supervised cell counting network (WSCNet) to generate microfluidic droplets, evaluate their quality, and further recognize the locations of encapsulated cells. Here, we systematically verified our approach using encapsulated droplets from three different microfluidic structures. Quantitative experimental results showed that our approach can not only distinguish droplet encapsulations (F1 score > 0.88) but also locate each cell without any supervised location information (accuracy > 89%). The probability of a "single cell in one droplet" encapsulation is systematically verified under different parameters, which shows good agreement with the distribution of the passive method (Residual Sum of Squares, RSS < 0.5). This study offers a comprehensive platform for the quantitative assessment of encapsulated microfluidic droplets.

Image-based real-time feedback control of magnetic digital microfluidics by artificial intelligence-empowered rapid object detector for automated in vitro diagnostics

In vitro diagnostics (IVD) plays a critical role in healthcare and public health management. Magnetic digital microfluidics (MDM) perform IVD assays by manipulating droplets on an open substrate with magnetic particles. Automated IVD based on MDM could reduce the risk of accidental exposure to contagious pathogens among healthcare workers. However, it remains challenging to create a fully automated IVD platform based on the MDM technology because of a lack of effective feedback control system to ensure the successful execution of various droplet operations required for IVD. In this work, an artificial intelligence (AI)-empowered MDM platform with image-based real-time feedback control is presented. The AI is trained to recognize droplets and magnetic particles, measure their size, and determine their location and relationship in real time; it shows the ability to rectify failed droplet operations based on the feedback information, a function that is unattainable by conventional MDM platforms, thereby ensuring that the entire IVD process is not interrupted due to the failure of liquid handling. We demonstrate fundamental droplet operations, which include droplet transport, particle extraction, droplet merging and droplet mixing, on the MDM platform and show how the AI rectify failed droplet operations by acting upon the feedback information. Protein quantification and antibiotic resistance detection are performed on this AI-empowered MDM platform, and the results obtained agree well with the benchmarks. We envision that this AI-based feedback approach will be widely adopted not only by MDM but also by other types of digital microfluidic platforms to offer precise and error-free droplet operations for a wide range of automated IVD applications.

Droplet-Based Microfluidics: Applications in Pharmaceuticals

Droplet-based microfluidics offer great opportunities for applications in various fields, such as diagnostics, food sciences, and drug discovery. A droplet provides an isolated environment for performing a single reaction within a microscale-volume sample, allowing for a fast reaction with a high sensitivity, high throughput, and low risk of cross-contamination. Owing to several remarkable features, droplet-based microfluidic techniques have been intensively studied. In this review, we discuss the impact of droplet microfluidics, particularly focusing on drug screening and development. In addition, we surveyed various methods of device fabrication and droplet generation/manipulation. We further highlight some promising studies covering drug synthesis and delivery that were updated within the last 5 years. This review provides researchers with a quick guide that includes the most up-to-date and relevant information on the latest scientific findings on the development of droplet-based microfluidics in the pharmaceutical field.

Deep learning with microfluidics for on-chip droplet generation, control, and analysis

Droplet microfluidics has gained widespread attention in recent years due to its advantages of high throughput, high integration, high sensitivity and low power consumption in droplet-based micro-reaction. Meanwhile, with the rapid development of computer technology over the past decade, deep learning architectures have been able to process vast amounts of data from various research fields. Nowadays, interdisciplinarity plays an increasingly important role in modern research, and deep learning has contributed greatly to the advancement of many professions. Consequently, intelligent microfluidics has emerged as the times require, and possesses broad prospects in the development of automated and intelligent devices for integrating the merits of microfluidic technology and artificial intelligence. In this article, we provide a general review of the evolution of intelligent microfluidics and some applications related to deep learning, mainly in droplet generation, control, and analysis. We also present the challenges and emerging opportunities in this field.

Machine learning in bioprocess development: from promise to practice

Fostered by novel analytical techniques, digitalization, and automation, modern bioprocess development provides large amounts of heterogeneous experimental data, containing valuable process information. In this context, data-driven methods like machine learning (ML) approaches have great potential to rationally explore large design spaces while exploiting experimental facilities most efficiently. Herein we demonstrate how ML methods have been applied so far in bioprocess development, especially in strain engineering and selection, bioprocess optimization, scale-up, monitoring, and control of bioprocesses. For each topic, we will highlight successful application cases, current challenges, and point out domains that can potentially benefit from technology transfer and further progress in the field of ML.

Active learning applied to automated physical systems increases the rate of discovery

Active machine learning is widely used in computational studies where repeated numerical simulations can be conducted on high performance computers without human intervention. But translation of these active learning methods to physical systems has proven more difficult and the accelerated pace of discoveries aided by these methods remains as yet unrealized. Through the presentation of a general active learning framework and its application to large-scale boundary layer wind tunnel experiments, we demonstrate that the active learning framework used so successfully in computational studies is directly applicable to the investigation of physical experimental systems and the corresponding improvements in the rate of discovery can be transformative. We specifically show that, for our wind tunnel experiments, we are able to achieve in approximately 300 experiments a learning objective that would be impossible using traditional methods.

Microfluidic Organ-Chips and Stem Cell Models in the Fight Against COVID-19

SARS-CoV-2, the virus underlying COVID-19, has now been recognized to cause multiorgan disease with a systemic effect on the host. To effectively combat SARS-CoV-2 and the subsequent development of COVID-19, it is critical to detect, monitor, and model viral pathogenesis. In this review, we discuss recent advancements in microfluidics, organ-on-a-chip, and human stem cell-derived models to study SARS-CoV-2 infection in the physiological organ microenvironment, together with their limitations. Microfluidic-based detection methods have greatly enhanced the rapidity, accessibility, and sensitivity of viral detection from patient samples. Engineered organ-on-a-chip models that recapitulate in vivo physiology have been developed for many organ systems to study viral pathology. Human stem cell-derived models have been utilized not only to model viral tropism and pathogenesis in a physiologically relevant context but also to screen for effective therapeutic compounds. The combination of all these platforms, along with future advancements, may aid to identify potential targets and develop novel strategies to counteract COVID-19 pathogenesis.

Ultrahigh-Throughput Enzyme Engineering and Discovery in In Vitro Compartments

Novel and improved biocatalysts are increasingly sourced from libraries via experimental screening. The success of such campaigns is crucially dependent on the number of candidates tested. Water-in-oil emulsion droplets can replace the classical test tube, to provide in vitro compartments as an alternative screening format, containing genotype and phenotype and enabling a readout of function. The scale-down to micrometer droplet diameters and picoliter volumes brings about a >107-fold volume reduction compared to 96-well-plate screening. Droplets made in automated microfluidic devices can be integrated into modular workflows to set up multistep screening protocols involving various detection modes to sort >107 variants a day with kHz frequencies. The repertoire of assays available for droplet screening covers all seven enzyme commission (EC) number classes, setting the stage for widespread use of droplet microfluidics in everyday biochemical experiments. We review the practicalities of adapting droplet screening for enzyme discovery and for detailed kinetic characterization. These new ways of working will not just accelerate discovery experiments currently limited by screening capacity but profoundly change the paradigms we can probe. By interfacing the results of ultrahigh-throughput droplet screening with next-generation sequencing and deep learning, strategies for directed evolution can be implemented, examined, and evaluated.

Microsystem Advances through Integration with Artificial Intelligence

Microfluidics is a rapidly growing discipline that involves studying and manipulating fluids at reduced length scale and volume, typically on the scale of micro- or nanoliters. Under the reduced length scale and larger surface-to-volume ratio, advantages of low reagent consumption, faster reaction kinetics, and more compact systems are evident in microfluidics. However, miniaturization of microfluidic chips and systems introduces challenges of stricter tolerances in designing and controlling them for interdisciplinary applications. Recent advances in artificial intelligence (AI) have brought innovation to microfluidics from design, simulation, automation, and optimization to bioanalysis and data analytics. In microfluidics, the Navier-Stokes equations, which are partial differential equations describing viscous fluid motion that in complete form are known to not have a general analytical solution, can be simplified and have fair performance through numerical approximation due to low inertia and laminar flow. Approximation using neural networks trained by rules of physical knowledge introduces a new possibility to predict the physicochemical nature. The combination of microfluidics and automation can produce large amounts of data, where features and patterns that are difficult to discern by a human can be extracted by machine learning. Therefore, integration with AI introduces the potential to revolutionize the microfluidic workflow by enabling the precision control and automation of data analysis. Deployment of smart microfluidics may be tremendously beneficial in various applications in the future, including high-throughput drug discovery, rapid point-of-care-testing (POCT), and personalized medicine. In this review, we summarize key microfluidic advances integrated with AI and discuss the outlook and possibilities of combining AI and microfluidics.

Machine learning in additive manufacturing & Microfluidics for smarter and safer drug delivery systems

A new technological passage has emerged in the pharmaceutical field, concerning the management, application, and transfer of knowledge from humans to machines, as well as the implementation of advanced manufacturing and product optimisation processes. Machine Learning (ML) methods have been introduced to Additive Manufacturing (AM) and Microfluidics (MFs) to predict and generate learning patterns for precise fabrication of tailor-made pharmaceutical treatments. Moreover, regarding the diversity and complexity of personalised medicine, ML has been part of quality by design strategy, targeting towards the development of safe and effective drug delivery systems. The utilisation of different and novel ML techniques along with Internet of Things sensors in AM and MFs, have shown promising aspects regarding the development of well-defined automated procedures towards the production of sustainable and quality-based therapeutic systems. Thus, the effective data utilisation, prospects on a flexible and broader production of "on demand" treatments. In this study, a thorough overview has been achieved, concerning scientific achievements of the past decade, which aims to trigger the research interest on incorporating different types of ML in AM and MFs, as essential techniques for the enhancement of quality standards of customised medicinal applications, as well as the reduction of variability potency, throughout a pharmaceutical process.

Machine Learning Enables Process Optimization of Aerosol Jet 3D Printing Based on the Droplet Morphology

Aerosol jet printing (AJP) is a promising noncontact direct ink writing technology that enables flexible and conformal electronic devices to be fabricated onto planar and nonplanar substrates with higher resolution and less waste. Despite possessing many advantages, the limited electrical performance of microelectronic devices caused by the poor printing quality is still the greatest hurdle to overcome for AJP technology. With the motivation to improve the printing quality, a novel hybrid machine learning method is proposed to analyze and optimize the AJP process based on the deposited droplet morphology in this study. The proposed method consists of classic machine learning approaches, including space-filling-based experimental design, clustering, classification, regression, and multiobjective optimization. In the proposed method, a two-dimensional (2D) design space is fully explored using a Latin hypercube sampling approach for experimental design, and a K-means clustering approach is employed to reveal the cause-effect relationship between the deposited droplet morphology and printed line characteristics. Following that, an optimal operating window with respect to the deposited droplet morphology is identified using a support vector machine to ensure the printing quality in a design space. Finally, to achieve high-controllability and sufficient-thickness droplets, Gaussian process regression is adopted to develop the process model of droplet geometrical properties, and the deposited droplet morphology is optimized under dual conflicting objectives of customizing the droplet diameter and maximizing droplet thickness. Different from previous printing quality optimization approaches, the proposed method enables a systemic investigation on the formation mechanisms of printed line characteristics, and the printing quality is fundamentally optimized based on the deposited droplet morphology. Moreover, data-driven-based characteristics can help the proposed approach serve as a guideline for printing quality optimization in other noncontact direct ink writing technologies.

Machine Learning for Two-Phase Flow Separation in a Liquid-Liquid Interface Manipulation Separator

Two-phase flow separation is a key step in various downstream purification processes. The use of a separator with controllable flow behavior is recommended to avoid contamination. In this study, a core-annular separator for biphasic flow separation with four different chemical polarities was developed, and two machine learning-based methods were proposed for answering two emergent questions to meet real industrial needs. (1) Could complete two-phase separation be achieved under these operating conditions? (2) Could the separation process be accelerated by determining the maximum input flow rate of the water? Process prediction for automation, machine learning-based classifiers, and multilayer perceptron were used to address these questions by predicting successful separation and the maximum input flow rates of unknown water-solvent systems with limited experimental data as training samples. The core-annular separator achieved complete two-phase water-solvent separation at a maximum total input flow rate of 4000 μL min^-1. Moreover, the classification accuracy for complete separation reached 92.2%, and the multilayer perceptron network had the best performance for predicting the flow rate. This liquid-liquid interface manipulation separator and machine learning method could decrease the cost of relevant process development.

3D printed microfluidics: advances in strategies, integration, and applications

The ability to construct multiplexed micro-systems for fluid regulation could substantially impact multiple fields, including chemistry, biology, biomedicine, tissue engineering, and soft robotics, among others. 3D printing is gaining traction as a compelling approach to fabricating microfluidic devices by providing unique capabilities, such as 1) rapid design iteration and prototyping, 2) the potential for automated manufacturing and alignment, 3) the incorporation of numerous classes of materials within a single platform, and 4) the integration of 3D microstructures with prefabricated devices, sensing arrays, and nonplanar substrates. However, to widely deploy 3D printed microfluidics at research and commercial scales, critical issues related to printing factors, device integration strategies, and incorporation of multiple functionalities require further development and optimization. In this review, we summarize important figures of merit of 3D printed microfluidics and inspect recent progress in the field, including ink properties, structural resolutions, and hierarchical levels of integration with functional platforms. Particularly, we highlight advances in microfluidic devices printed with thermosetting elastomers, printing methodologies with enhanced degrees of automation and resolution, and the direct printing of microfluidics on various 3D surfaces. The substantial progress in the performance and multifunctionality of 3D printed microfluidics suggests a rapidly approaching era in which these versatile devices could be untethered from microfabrication facilities and created on demand by users in arbitrary settings with minimal prior training.

Viscoelastic Particle Encapsulation Using a Hyaluronic Acid Solution in a T-Junction Microfluidic Device

The encapsulation of particles and cells in droplets is highly relevant in biomedical engineering as well as in material science. So far, however, the majority of the studies in this area have focused on the encapsulation of particles or cells suspended in Newtonian liquids. We here studied the particle encapsulation phenomenon in a T-junction microfluidic device, using a non-Newtonian viscoelastic hyaluronic acid solution in phosphate buffer saline as suspending liquid for the particles. We first studied the non-Newtonian droplet formation mechanism, finding that the data for the normalised droplet length scaled as the Newtonian ones. We then performed viscoelastic encapsulation experiments, where we exploited the fact that particles self-assembled in equally-spaced structures before approaching the encapsulation area, to then identify some experimental conditions for which the single encapsulation efficiency was larger than the stochastic limit predicted by the Poisson statistics.

Spheroid Engineering in Microfluidic Devices

Two-dimensional (2D) cell culture techniques are commonly employed to investigate biophysical and biochemical cellular responses. However, these culture methods, having monolayer cells, lack cell-cell and cell-extracellular matrix interactions, mimicking the cell microenvironment and multicellular organization. Three-dimensional (3D) cell culture methods enable equal transportation of nutrients, gas, and growth factors among cells and their microenvironment. Therefore, 3D cultures show similar cell proliferation, apoptosis, and differentiation properties to in vivo. A spheroid is defined as self-assembled 3D cell aggregates, and it closely mimics a cell microenvironment in vitro thanks to cell-cell/matrix interactions, which enables its use in several important applications in medical and clinical research. To fabricate a spheroid, conventional methods such as liquid overlay, hanging drop, and so forth are available. However, these labor-intensive methods result in low-throughput fabrication and uncontrollable spheroid sizes. On the other hand, microfluidic methods enable inexpensive and rapid fabrication of spheroids with high precision. Furthermore, fabricated spheroids can also be cultured in microfluidic devices for controllable cell perfusion, simulation of fluid shear effects, and mimicking of the microenvironment-like in vivo conditions. This review focuses on recent microfluidic spheroid fabrication techniques and also organ-on-a-chip applications of spheroids, which are used in different disease modeling and drug development studies.

Droplets microfluidics platform-A tool for single cell research

Cells are the most basic structural and functional units of living organisms. Studies of cell growth, differentiation, apoptosis, and cell-cell interactions can help scientists understand the mysteries of living systems. However, there is considerable heterogeneity among cells. Great differences between individuals can be found even within the same cell cluster. Cell heterogeneity can only be clearly expressed and distinguished at the level of single cells. The development of droplet microfluidics technology opens up a new chapter for single-cell analysis. Microfluidic chips can produce many nanoscale monodisperse droplets, which can be used as small isolated micro-laboratories for various high-throughput, precise single-cell analyses. Moreover, gel droplets with good biocompatibility can be used in single-cell cultures and coupled with biomolecules for various downstream analyses of cellular metabolites. The droplets are also maneuverable; through physical and chemical forces, droplets can be divided, fused, and sorted to realize single-cell screening and other related studies. This review describes the channel design, droplet generation, and control technology of droplet microfluidics and gives a detailed overview of the application of droplet microfluidics in single-cell culture, single-cell screening, single-cell detection, and other aspects. Moreover, we provide a recent review of the application of droplet microfluidics in tumor single-cell immunoassays, describe in detail the advantages of microfluidics in tumor research, and predict the development of droplet microfluidics at the single-cell level.

Integrating machine learning and digital microfluidics for screening experimental conditions

Digital microfluidics (DMF) has the signatures of an ideal liquid handling platform - as shown through almost two decades of automated biological and chemical assays. However, in the current state of DMF, we are still limited by the number of parallel biological or chemical assays that can be performed on DMF. Here, we report a new approach that leverages design-of-experiment and numerical methodologies to accelerate experimental optimization on DMF. The integration of the one-factor-at-a-time (OFAT) experimental technique with machine learning algorithms provides a set of recommended optimal conditions without the need to perform a large set of experiments. We applied our approach towards optimizing the radiochemistry synthesis yield given the large number of variables that affect the yield. We believe that this work is the first to combine such techniques which can be readily applied to any other assays that contain many parameters and levels on DMF.

A machine learning-based framework to design capillary-driven networks

We present a novel approach for the design of capillary-driven microfluidic networks using a machine learning genetic algorithm (ML-GA). This strategy relies on a user-friendly 1D numerical tool specifically developed to generate the necessary data to train the ML-GA. This 1D model was validated using analytical results issued from a Y-shaped capillary network and experimental data. For a given microfluidic network, we defined the objective of the ML-GA to obtain the set of geometric parameters that produces the closest matching results against two prescribed curves of delivered volume against time. We performed more than 20 generations of 10 000 simulations to train the ML-GA and achieved the optimal solution of the inverse design problem. The optimisation took less than 6 hours, and the results were successfully validated using experimental data. This work establishes the utility of the presented method for the fast and reliable design of complex capillary-driven devices, enabling users to optimise their designs via an easy-to-use 1D numerical tool and machine learning technique.

3D printing-enabled uniform temperature distributions in microfluidic devices

Many microfluidic processes rely heavily on precise temperature control. Though internally-contained heaters have been developed using traditional fabrication methods, they are limited in their ability to isothermally heat a precisely defined volume. Advances in 3D printing have led to high resolution printers capable of using bio-compatible materials and achieving geometry resolutions near 20 μm. 3D printing's ability to create arbitrary 3D structures with an arbitrary 3D orientation as opposed to traditional microfluidic fabrication methods enables new three-dimensional heater geometries to be created. As examples, we demonstrate three new 3D heater geometries: a non-planar serpentine channel, a tapered helical channel, and a diamond channel. These new geometries are shown through finite element simulation to isothermally heat microfluidic channels of cross section 200 μm × 200 μm with a 0.1 °C temperature difference along up to 91% of a 10 mm length, compared to designs from the literature that are only able to have that same temperature distance over several μms. Finally, a set of design rules to create isothermal regions in 3D based on the desired temperature, heater pitch, heater gradient, and radial space around a target volume are detailed.

Deep learning detector for high precision monitoring of cell encapsulation statistics in microfluidic droplets

Encapsulation of cells inside microfluidic droplets is central to several applications involving cellular analysis. Although, theoretically the encapsulation statistics are expected to follow a Poisson distribution, experimentally this may not be achieved due to lack of full control of the experimental variables and conditions. Therefore, there is a need for automatic detection of droplets and cell count enumeration within droplets so a process control feedback to adjust experimental conditions can be implemented. In this study, we use a deep learning object detector called You Only Look Once (YOLO), an influential class of object detectors with several benefits over traditional methods. This paper investigates the application of both YOLOv3 and YOLOv5 object detectors in the development of an automated droplet and cell detector. Experimental data was obtained from a microfluidic flow focusing device with a dispersed phase of cancer cells. The microfluidic device contained an expansion chamber downstream of the droplet generator, allowing for visualization and recording of cell-encapsulated droplet images. In the procedure, a droplet bounding box is predicted, then cropped from the original image for the individual cells to be detected through a separate model for further examination. The system includes a production set for additional performance analysis with Poisson statistics while providing an experimental workflow with both droplet and cell models. The training set is collected and preprocessed before labeling and applying image augmentations, allowing for a generalizable object detector. Precision and recall were utilized as a validation and test set metric, resulting in a high mean average precision (mAP) metric for an accurate droplet detector. To examine model limitations, the predictions were compared to ground truth labels, illustrating that the YOLO predictions closely matched with the droplet and cell labels. Furthermore, it is demonstrated that droplet enumeration from the YOLOv5 model is consistent with hand counted ratios and the Poisson distribution, confirming that the platform can be used in real-time experiments for cell encapsulation optimization.

A Portable, Negative-Pressure Actuated, Dynamically Tunable Microfluidic Droplet Generator

Droplet microfluidics utilize a monodisperse water-in-oil emulsion, with an expanding toolbox offering a wide variety of operations on a range of droplet sizes at high throughput. However, translation of these capabilities into applications for non-expert laboratories to fully harness the inherent potential of microscale manipulations is woefully trailing behind. One major obstacle is that droplet microfluidic setups often rely on custom fabricated devices, costly liquid actuators, and are not easily set up and operated by non-specialists. This impedes wider adoption of droplet technologies in, e.g., the life sciences. Here, we demonstrate an easy-to-use minimal droplet production setup with a small footprint, built exclusively from inexpensive commercially sourced parts, powered and controlled by a laptop. We characterize the components of the system and demonstrate production of droplets ranging in volume from 3 to 21 nL in a single microfluidic device. Furthermore, we describe the dynamic tuning of droplet composition. Finally, we demonstrate the production of droplet-templated cell spheroids from primary cells, where the mobility and simplicity of the setup enables its use within a biosafety cabinet. Taken together, we believe this minimal droplet setup is ideal to drive broad adoption of droplet microfluidics technology.

Surfactant-laden droplet size prediction in a flow-focusing microchannel: a data-driven approach

The control of droplet formation and size using microfluidic devices is a critical operation for both laboratory and industrial applications, e.g. in micro-dosage. Surfactants can be added to improve the stability and control the size of the droplets by modifying their interfacial properties. In this study, a large-scale data set of droplet size was obtained from high-speed imaging experiments conducted on a flow-focusing microchannel where aqueous surfactant-laden droplets were generated in silicone oil. Three types of surfactants were used including anionic, cationic and non-ionic at concentrations below and above the critical micelle concentration (CMC). To predict the final droplet size as a function of flow rates, surfactant type and concentration of surfactant, two data-driven models were built. Using a Bayesian regularised artificial neural network and XGBoost, these models were initially based on four inputs (flow rates of the two phases, interfacial tension at equilibrium and the normalised surfactant concentration). The mean absolute percentage errors (MAPE) show that data-driven models are more accurate (MAPE = 3.9%) compared to semi-empirical models (MAPE = 11.4%). To overcome experimental difficulties in acquiring accurate interfacial tension values under some conditions, both models were also trained with reduced inputs by removing the interfacial tension. The results show again a very good prediction of the droplet diameter. Finally, over 10 000 synthetic data were generated, based on the initial data set, with a Variational Autoencoder (VAE). The high-fidelity of the extended synthetic data set highlights that this method can be a quick and low-cost alternative to study microdroplet formation in future lab on a chip applications, where experimental data may not be readily available.

Hardware, Software, and Wetware Codesign Environment for Synthetic Biology

Synthetic biology is the process of forward engineering living systems. These systems can be used to produce biobased materials, agriculture, medicine, and energy. One approach to designing these systems is to employ techniques from the design of embedded electronics. These techniques include abstraction, standards, modularity, automated design, and formal semantic models of computation. Together, these elements form the foundation of "biodesign automation," where software, robotics, and microfluidic devices combine to create exciting biological systems of the future. This paper describes a "hardware, software, wetware" codesign vision where software tools can be made to act as "genetic compilers" that transform high-level specifications into engineered "genetic circuits" (wetware). This is followed by a process where automation equipment, well-defined experimental workflows, and microfluidic devices are explicitly designed to house, execute, and test these circuits (hardware). These systems can be used as either massively parallel experimental platforms or distributed bioremediation and biosensing devices. Next, scheduling and control algorithms (software) manage these systems' actual execution and data analysis tasks. A distinguishing feature of this approach is how all three of these aspects (hardware, software, and wetware) may be derived from the same basic specification in parallel and generated to fulfill specific cost, performance, and structural requirements.

Optimization of Microchannels and Application of Basic Activation Functions of Deep Neural Network for Accuracy Analysis of Microfluidic Parameter Data

The fabrication of microflow channels with high accuracy in terms of the optimization of the proposed designs, minimization of surface roughness, and flow control of microfluidic parameters is challenging when evaluating the performance of microfluidic systems. The use of conventional input devices, such as peristaltic pumps and digital pressure pumps, to evaluate the flow control of such parameters cannot confirm a wide range of data analysis with higher accuracy because of their operational drawbacks. In this study, we optimized the circular and rectangular-shaped microflow channels of a 100 μm microfluidic chip using a three-dimensional simulation tool, and analyzed concentration profiles of different regions of the microflow channels. Then, we applied a deep learning (DL) algorithm for the dense layers of the rectified linear unit (ReLU), Leaky ReLU, and Swish activation functions to train and test 1600 experimental and interpolation of data samples which obtained from the microfluidic chip. Moreover, using the same DL algorithm, we configured three models for each of these three functions by changing the internal middle layers of these models. As a result, we obtained a total of 9 average accuracy values of ReLU, Leaky ReLU, and Swish functions for a defined threshold value of 6×10-5 using the trial-and-error method. We applied single-to-five-fold cross-validation technique of deep neural network to avoid overfitting and reduce noises from data-set to evaluate better average accuracy of data of microfluidic parameters.

Machine learning for microfluidic design and control

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.

Neural Network-Based Optimization of an Acousto Microfluidic System for Submicron Bioparticle Separation

The advancement in microfluidics has provided an excellent opportunity for shifting from conventional sub-micron-sized isolation and purification methods to more robust and cost-effective lab-on-chip platforms. The acoustic-driven separation approach applies differential forces acting on target particles, guiding them towards different paths in a label-free and biocompatible manner. The main challenges in designing the acoustofluidic-based isolation platforms are minimizing the reflected radio frequency signal power to achieve the highest acoustic radiation force acting on micro/nano-sized particles and tuning the bandwidth of the acoustic resonator in an acceptable range for efficient size-based binning of particles. Due to the complexity of the physics involved in acoustic-based separations, the current existing lack in performance predictive understanding makes designing these miniature systems iterative and resource-intensive. This study introduces a unique approach for design automation of acoustofluidic devices by integrating the machine learning and multi-objective heuristic optimization approaches. First, a neural network-based prediction platform was developed to predict the resonator's frequency response according to different geometrical configurations of interdigitated transducers In the next step, the multi-objective optimization approach was executed for extracting the optimum design features for maximum possible device performance according to decision-maker criteria. The results show that the proposed methodology can significantly improve the fine-tuned IDT designs with minimum power loss and maximum working frequency range. The examination of the power loss and bandwidth on the alternation and distribution of the acoustic pressure inside the microfluidic channel was carried out by conducting a 3D finite element-based simulation. The proposed methodology improves the performance of the acoustic transducer by overcoming the constraints related to bandwidth operation, the magnitude of acoustic radiation force on particles, and the distribution of pressure acoustic inside the microchannel.

Shear-flow-induced graphene coating microfibers from microfluidic spinning

The advancements in flexible electronics call for invention of fiber-based electronic systems by surface modification or encapsulation. Here we present novel shear-flow-induced graphene nanosheets coating microfibers by integrating the dip coating approach with the microfluidic spinning method. The core hydrogel microfiber was first spun continuously from the microfluidic device, and the shear flow from the dip coating approach allowed formation of the thin graphene oxide (GO) nanosheet coating shell. Because the fluid components and flow rates in the microfluidic spinning together with the lifting speed in the dip coating approach are highly controllable, the morphology of the resultant microfibers could be precisely tailored, including the core-shell structure, conductivity, and thermal responsibilities. These features equipped the resultant microfibers with the potential of thermal and motion sensors, and their value in gesture indicators has also been explored. Microfibers generated from such a simple and controllable method could be versatile in flexible electronics.

Machine Learning-Driven Multiobjective Optimization: An Opportunity of Microfluidic Platforms Applied in Cancer Research

Cancer metastasis is one of the primary reasons for cancer-related fatalities. Despite the achievements of cancer research with microfluidic platforms, understanding the interplay of multiple factors when it comes to cancer cells is still a great challenge. Crosstalk and causality of different factors in pathogenesis are two important areas in need of further research. With the assistance of machine learning, microfluidic platforms can reach a higher level of detection and classification of cancer metastasis. This article reviews the development history of microfluidics used for cancer research and summarizes how the utilization of machine learning benefits cancer studies, particularly in biomarker detection, wherein causality analysis is useful. To optimize microfluidic platforms, researchers are encouraged to use causality analysis when detecting biomarkers, analyzing tumor microenvironments, choosing materials, and designing structures.