DLDNN: Deterministic Lateral Displacement Design Automation by Neural Networks

TL;DR

This paper presents a neural network-based automation platform for designing deterministic lateral displacement (DLD) microfluidic devices, significantly reducing the iterative trial-and-error process by accurately predicting particle trajectories and device parameters.

Contribution

It introduces a novel neural network and evolutionary algorithm combined approach for rapid, reliable DLD device design automation, improving efficiency and generalizability over traditional methods.

Findings

Neural networks predicted velocity fields and critical diameters with less than 4% error.

The automation tool successfully tested 12 critical conditions.

The method is adaptable to other physics-based problems with transfer learning.

Abstract

Size-based separation of bioparticles/cells is crucial to a variety of biomedical processing steps for applications such as exosomes and DNA isolation. Design and improvement of such microfluidic devices is a challenge to best answer the demand for producing homogeneous end-result for study and use. Deterministic lateral displacement (DLD) exploits a similar principle that has drawn extensive attention over years. However, the lack of predictive understanding of the particle trajectory and its induced mode makes designing a DLD device an iterative procedure. Therefore, this paper investigates a fast versatile design automation platform to address this issue. To do so, convolutional and artificial neural networks were employed to learn velocity fields and critical diameters of a wide range of DLD configurations. Later, these networks were combined with a multi-objective evolutionary algorithm to construct the automation tool. After ensuring the accuracy of the neural networks, the developed tool was tested for 12 critical conditions. Reaching the imposed conditions, the automation components performed reliably with errors of less than 4%. Moreover, this tool is generalizable to other field-based problems and since the neural network is an integral part of this method, it enables transfer learning for similar physics. All the codes generated and used in this study alongside the pre-trained neural network models are available on https://github.com/HoseynAAmiri/DLDNN.