An Intelligent Low-Power Low-Cost Mobile Lab-On-Chip Yeast Cell Culture Platform

Cells are the fundamental unit of life activities, and the basis of studying life phenomena. It is very important to observe the growth state of yeast cells for exploring the law of life movement, diagnosis and treatment of diseases, drug screening and so on. This study proposes a kind of intelligent low-cost portable cell culture platform using the microfluidic channel and the special machine learning circuit. The platform can independently complete the whole work of living cell culture and monitoring. For realizing the reusable and low-power deep learning circuit, a complement optimization neural network algorithm for hardware optimization and corresponding multi-clock-domain reusable multi-level precision neural network accelerator circuit were proposed, which can reduce the circuit area and power of convolution operation in all precisions by average 18.11% and 23.5% respectively. Besides, a dynamic multi-level precision control method based on the battery level is proposed to dynamically adjust the precision of machine learning operation, in order to balance the working time and segmentation accuracy of the culture platform. In addition, a microcolumns-based three-port input microfluidic structure was designed for better yeast culture effect. The experiment showed that the culture platform can realize yeast cell culture and achieve almost the same segmentation accuracy as the large biological laboratory with low-power and low-cost. Compared with the previous work, the cost of mass production was reduced by 88.95%, and the equipment volume was 27.1% smaller. At the same time, it can achieve the best balance of working time and working accuracy under the condition of limited power of equipment according to the needs of users.

[1]  Yoshua Bengio,et al.  BinaryConnect: Training Deep Neural Networks with binary weights during propagations , 2015, NIPS.

[2]  Chia-Fu Chou,et al.  Asymmetric cancer-cell filopodium growth induced by electric-fields in a microfluidic culture chip. , 2011, Lab on a chip.

[3]  Vernella Vickerman,et al.  Design, fabrication and implementation of a novel multi-parameter control microfluidic platform for three-dimensional cell culture and real-time imaging. , 2008, Lab on a chip.

[4]  M. Gustin,et al.  Osmotic stress and the yeast cytoskeleton: phenotype-specific suppression of an actin mutation , 1992, The Journal of cell biology.

[5]  Philipp Gysel,et al.  Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks , 2016, ArXiv.

[6]  F F Becker,et al.  Cell separation on microfabricated electrodes using dielectrophoretic/gravitational field-flow fractionation. , 1999, Analytical chemistry.

[7]  Y. Bourbonnais,et al.  Overexpression of MID2 suppresses the profilin‐deficient phenotype of yeast cells , 1998, Molecular microbiology.

[8]  D. Botstein,et al.  Genomic binding sites of the yeast cell-cycle transcription factors SBF and MBF , 2001, Nature.

[9]  H. T. Kung.  Why systolic architectures? , 1982, Computer.

[10]  K Konstantinov,et al.  Fermentor temperature as a tool for control of high-density perfusion cultures of mammalian cells. , 1997, Biotechnology and bioengineering.

[11]  S. Reed,et al.  Primary structure homology between the product of yeast cell division control gene CDC28 and vertebrate oncogenes , 1984, Nature.

[12]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[13]  R. Naviaux,et al.  Reactive biomolecular divergence in genetically altered yeast cells and isolated mitochondria as measured by biocavity laser spectroscopy: rapid diagnostic method for studying cellular responses to stress and disease. , 2006, Journal of biomedical optics.

[14]  Ezzatollah Salari,et al.  A new method for the segmentation of algae images using retinex and support vector machine , 2015, 2015 IEEE International Conference on Electro/Information Technology (EIT).

[15]  Vittorio Bianco,et al.  A deep learning-enabled portable imaging flow cytometer for cost-effective, high-throughput, and label-free analysis of natural water samples , 2018, Light: Science & Applications.

[16]  Harold F. Hemond,et al.  A Multi-Platform Optical Sensor for In Vivo and In Vitro Algae Classification , 2017, Sensors.

[17]  Brenda J. Andrews,et al.  Unsupervised Clustering of Subcellular Protein Expression Patterns in High-Throughput Microscopy Images Reveals Protein Complexes and Functional Relationships between Proteins , 2013, PLoS Comput. Biol..

[18]  U. Jung,et al.  Genome‐wide analysis of gene expression regulated by the yeast cell wall integrity signalling pathway , 1999, Molecular microbiology.

[19]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[20]  Lin Xu,et al.  Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights , 2017, ICLR.

[21]  Paul Yager,et al.  Cell lysis and protein extraction in a microfluidic device with detection by a fluorogenic enzyme assay. , 2002, Analytical chemistry.

[22]  Ferry Hagen,et al.  Classification of yeast cells from image features to evaluate pathogen conditions , 2007, Electronic Imaging.

[23]  R. Mathies,et al.  Single-molecule detection of DNA separations in microfabricated capillary electrophoresis chips employing focused molecular streams. , 1999, Analytical chemistry.

[24]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[25]  Dana M Spence,et al.  Deformation-induced release of ATP from erythrocytes in a poly(dimethylsiloxane)-based microchip with channels that mimic resistance vessels. , 2004, Analytical chemistry.

[26]  I. Shmulevich,et al.  Dynamic analysis of MAPK signaling using a high-throughput microfluidic single-cell imaging platform , 2009, Proceedings of the National Academy of Sciences.

[27]  T. Park,et al.  Integration of Cell Culture and Microfabrication Technology , 2003, Biotechnology progress.

[28]  A. Folch,et al.  Biology on a chip: microfabrication for studying the behavior of cultured cells. , 2003, Critical reviews in biomedical engineering.

[29]  Yuanyuan Wang,et al.  High-resolution image reconstruction for portable ultrasound imaging devices , 2019 .

[30]  D. J. Harrison,et al.  Microchip-based capillary electrophoresis for immunoassays: analysis of monoclonal antibodies and theophylline. , 1997, Analytical chemistry.

[31]  Ninghui Sun,et al.  DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning , 2014, ASPLOS.

[32]  Nicola J. Rinaldi,et al.  Serial Regulation of Transcriptional Regulators in the Yeast Cell Cycle , 2001, Cell.

[33]  J. Squier,et al.  Microfluidic sorting system based on optical waveguide integration and diode laser bar trapping. , 2006, Lab on a chip.

[34]  Alan M. Moses,et al.  YeastSpotter: accurate and parameter-free web segmentation for microscopy images of yeast cells , 2019, Bioinform..

[35]  Xiwei Huang,et al.  A Single-Frame Superresolution Algorithm for Lab-on-a-Chip Lensless Microfluidic Imaging , 2015, IEEE Design & Test.

[36]  Sheri J. Lillard,et al.  New approaches to single-cell analysis by capillary electrophoresis , 2001 .

[37]  M. Mochizuki,et al.  Inducible expression of a gene encoding an L41 ribosomal protein responsible for the cycloheximide-resistant phenotype in the yeast Candida maltosa , 1995, Journal of bacteriology.

[38]  P. Lio’,et al.  Periodic gene expression program of the fission yeast cell cycle , 2004, Nature Genetics.