Random design of microfluidics

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.

GNN-Based Concentration Prediction With Variable Input Flow Rates for Microfluidic Mixers

Recent years have witnessed significant advances brought by microfluidic biochips in automating biochemical protocols. Accurate preparation of fluid samples is an essential component of these protocols, where concentration prediction and generation are critical. Equipped with the advantages of convenient fabrication and control, microfluidic mixers demonstrate huge potential in sample preparation. Although finite element analysis (FEA) is the most commonly used simulation method for accurate concentration prediction of a given microfluidic mixer, it is time-consuming with poor scalability for large biochip sizes. Recently, machine learning models have been adopted in concentration prediction, with great potential in enhancing the efficiency over traditional FEA methods. However, the state-of-the-art machine learning-based method can only predict the concentration of mixers with fixed input flow rates and fixed sizes. In this paper, we propose a new concentration prediction method based on graph neural networks (GNNs), which can predict output concentrations for microfluidic mixters with variable input flow rates. Moreover, a transfer learning method is proposed to transfer the trained model to mixers of different sizes with reduced training data. Experimental results show that, for microfluidic mixers with fixed input flow rates, the proposed method obtains an average reduction of 88% in terms of prediction errors compared with the state-of-the-art method. For microfluidic mixers with variable input flow rates, the proposed method reduces the prediction error by 85% on average. Besides, the proposed transfer learning method reduces the training data by 84% for extending the pre-trained model for microfluidic mixers of different sizes with acceptable prediction error.

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.

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.

Integrated system for rapid enrichment and detection of airborne polycyclic aromatic hydrocarbons

Polycyclic aromatic hydrocarbons (PAHs) are extremely toxic environmental pollutants, which are harmful to the human body. Direct collection and analysis of airborne PAHs is essential for air quality monitoring. Herein, we demonstrated an integrated system for airborne PAHs enrichment and detection. The enrichment cube was composed of channels with threaded structures and curved channels, which had high capture efficiency. Then PAHs-carried particles could be crushed into the detection chip for testing. The whole process took about 25 min (5 min for PAHs enrichment and 20 min for PAHs test). The limit of detection was 3.3 ng/m³, which could meet the needs of daily analysis. It had the advantages of low cost, low reagent consumption, simple operation, semi-automatic operation, high sensitivity, high speed and high throughput compared with conventional techniques, showing the potential for becoming an air pollution monitoring platform.

Machine-Learning-Enabled Design and Manipulation of a Microfluidic Concentration Gradient Generator

Microfluidics concentration gradient generators have been widely applied in chemical and biological fields. However, the current gradient generators still have some limitations. In this work, we presented a microfluidic concentration gradient generator with its corresponding manipulation process to generate an arbitrary concentration gradient. Machine-learning techniques and interpolation algorithms were implemented to help researchers instantly analyze the current concentration profile of the gradient generator with different inlet configurations. The proposed method has a 93.71% accuracy rate with a 300× acceleration effect compared to the conventional finite element analysis. In addition, our method shows the potential application of the design automation and computer-aided design of microfluidics by leveraging both artificial neural networks and computer science algorithms.

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.

Predicting the fluid behavior of random microfluidic mixers using convolutional neural networks

With the various applications of microfluidics, numerical simulation is highly recommended to verify its performance and reveal potential defects before fabrication. Among all the simulation parameters and simulation tools, the velocity field and concentration profile are the key parts and are generally simulated using finite element analysis (FEA). In our previous work [Wang et al., Lab Chip, 2016, 21, 4212-4219], automated design of microfluidic mixers by pre-generating a random library with the FEA was proposed. However, the duration of the simulation process is time-consuming, while the matching consistency between limited pre-generated designs and user desire is not stable. To address these issues, we inventively transformed the fluid mechanics problem into an image recognition problem and presented a convolutional neural network (CNN)-based technique to predict the fluid behavior of random microfluidic mixers. The pre-generated 10 513 candidate designs in the random library were used in the training process of the CNN, and then 30 757 brand new microfluidic mixer designs were randomly generated, whose performance was predicted by the CNN. Experimental results showed that the CNN method could complete all the predictions in just 10 seconds, which was around 51 600× faster than the previous FEA method. The CNN library was extended to contain 41 270 candidate designs, which has filled up those empty spaces in the fluid velocity versus solute concentration map of the random library, and able to provide more choices and possibilities for user desire. Besides, the quantitative analysis has confirmed the increased compatibility of the CNN library with user desire. In summary, our CNN method not only presents a much faster way of generating a more complete library with candidate mixer designs but also provides a solution for predicting fluid behavior using a machine learning technique.

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

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 μm 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.

Computer-Aided Design of Microfluidic Circuits

Microfluidic devices developed over the past decade feature greater intricacy, increased performance requirements, new materials, and innovative fabrication methods. Consequentially, new algorithmic and design approaches have been developed to introduce optimization and computer-aided design to microfluidic circuits: from conceptualization to specification, synthesis, realization, and refinement. The field includes the development of new description languages, optimization methods, benchmarks, and integrated design tools. Here, recent advancements are reviewed in the computer-aided design of flow-, droplet-, and paper-based microfluidics. A case study of the design of resistive microfluidic networks is discussed in detail. The review concludes with perspectives on the future of computer-aided microfluidics design, including the introduction of cloud computing, machine learning, new ideation processes, and hybrid optimization.

Finding the optimal design of a passive microfluidic mixer

The ability to thoroughly mix two fluids is a fundamental need in microfluidics. While a variety of different microfluidic mixers have been designed by researchers, it remains unknown which (if any) of these mixers are optimal (that is, which designs provide the most thorough mixing with the smallest possible fluidic resistance across the mixer). In this work, we automatically designed and rationally optimized a microfluidic mixer. We accomplished this by first generating a library of thousands of different randomly designed mixers, then using the non-dominated sorting genetic algorithm II (NSGA-II) to optimize the random chips in order to achieve Pareto efficiency. Pareto efficiency is a state of allocation of resources (e.g. driving force) from which it is impossible to reallocate so as to make any one individual criterion better off (e.g. pressure drop) without making at least one individual criterion (e.g. mixing performance) worse off. After 200 generations of evolution, Pareto efficiency was achieved and the Pareto-optimal front was found. We examined designs at the Pareto-optimal front and found several design criteria that enhance the mixing performance of a mixer while minimizing its fluidic resistance; these observations provide new criteria on how to design optimal microfluidic mixers. Additionally, we compared the designs from NSGA-II with some popular microfluidic mixer designs from the literature and found that designs from NSGA-II have lower fluidic resistance with similar mixing performance. As a proof of concept, we fabricated three mixer designs from 200 generations of evolution and one conventional popular mixer design and tested the performance of these four mixers. Using this approach, an optimal design of a passive microfluidic mixer is found and the criteria of designing a passive microfluidic mixer are established.

3DμF - Interactive Design Environment for Continuous Flow Microfluidic Devices

The design of microfluidic Lab on a Chip (LoC) systems is an onerous task requiring specialized skills in fluid dynamics, mechanical design drafting, and manufacturing. Engineers face significant challenges during the labor-intensive process of designing microfluidic devices, with very few specialized tools that help automate the process. Typical design iterations require the engineer to research the architecture, manually draft the device layout, optimize for manufacturing processes, and manually calculate and program the valve sequences that operate the microfluidic device. The problem compounds when engineers not only have to test the functionality of the chip but are also expected to optimize them for the robust execution of biological assays. In this paper, we present an interactive tool for designing continuous flow microfluidic devices. 3DμF is the first completely open source interactive microfluidic system designer that readily supports state of the art design automation algorithms. Through various case studies, we show 3DμF can be used to reproduce designs from literature, provide metrics for evaluating microfluidic design complexity and showcase how 3DμF is a platform for integrating a wide assortment of engineering techniques used in the design of microfluidic devices as a part of the standard design workflow.

Meander Designer: Automatically Generating Meander Channel Designs

Microfluidics continues to bring innovation to the life sciences. It stimulates progress by enabling new ways of research in biology, chemistry, and biotechnology. However, when designing a microfluidic device, designers have to conduct many tasks by hand-resulting in labor-intensive processes. In particular, when drawing the design of the device, designers have to handle re-occurring entities. Meander channels are one example, which are frequently used in different platforms but always have to fit the respective application and design rules. This work presents an online tool which is capable of automatically generating user-defined, two-dimensional designs of fluidic meander channels facilitating fluidic hydrodynamic resistances. The tool implements specific design rules as it considers the user's needs and fabrication requirements. The compliance of the meanders generated by the proposed tool is confirmed by fabricating the generated designs and comparing whether the resulting devices indeed realize the desired specification. To this end, two case studies are considered: first, the realization of dedicated fluidic resistances and, second, the realization of dedicated mixing ratios of fluids. The results demonstrate the versatility of the tool regarding application and technology. Overall, the freely accessible tool with its flexibility and simplicity renders manual drawing of meanders obsolete and, hence, allows for a faster, more straightforward design process.

Instantaneous simulation of fluids and particles in complex microfluidic devices

Microfluidics researchers are increasingly using computer simulation in many different aspects of their research. However, these simulations are often computationally intensive: simulating the behavior of a simple microfluidic chip can take hours to complete on typical computing hardware, and even powerful workstations can lack the computational capabilities needed to simulate more complex chips. This slows the development of new microfluidic chips for new applications. To address this issue, we present a microfluidic simulation method that can simulate the behavior of fluids and particles in some typical microfluidic chips instantaneously (in around one second). Our method decomposes the chip into its primary components: channels and intersections. The behavior of fluid in each channel is determined by leveraging analogies with electronic circuits, and the behavior of fluid and particles in each intersection is determined by querying a database containing nearly 100,000 pre-simulated channel intersections. While constructing this database takes a nontrivial amount of computation time, once built, this database can be queried to determine the behavior of fluids and particles in a given intersection in a fraction of a second. Using this approach, the behavior of a microfluidic chip can be simulated in just one second on a standard laptop computer, without any noticeable degradation in the accuracy of the simulation. While our current technique has some constraints on the designs of the chips it can simulate (namely, T- or cross-shaped intersections, 90 degree channel turns, a fixed channel width, fluid flow rates between 0 and 2 cm/s, and particles with diameters between 1 and 20 microns), we provide several strategies for increasing the range of possible chip designs that can be simulated using our technique. As a proof of concept, we show that our simulation method can instantaneously simulate the paths followed by particles in both simple and complex microfluidic chips, with results that are essentially indistinguishable from simulations that took hours or even days to complete using conventional approaches.

From single-molecule detection to next-generation sequencing: microfluidic droplets for high-throughput nucleic acid analysis

Droplet-based microfluidic technologies have proved themselves to be of significant utility in the performance of high-throughput chemical and biological experiments. By encapsulating and isolating reagents within femtoliter-nanoliter droplet, millions of (bio) chemical reactions can be processed in a parallel fashion and on ultra-short timescales. Recent applications of such technologies to genetic analysis have suggested significant utility in low-cost, efficient and rapid workflows for DNA amplification, rare mutation detection, antibody screening and next-generation sequencing. To this end, we describe and highlight some of the most interesting recent developments and applications of droplet-based microfluidics in the broad area of nucleic acid analysis. In addition, we also present a cursory description of some of the most essential functional components, which allow the creation of integrated and complex workflows based on flowing streams of droplets.