Prediction of single cell mechanical properties in microchannels based on deep learning

doi:10.1007/s10483-024-3187-6

摘要/Abstract

Abstract:

Traditional methods for measuring single-cell mechanical characteristics face several challenges, including lengthy measurement times, low throughput, and a requirement for advanced technical skills. To overcome these challenges, a novel machine learning (ML) approach is implemented based on the convolutional neural networks (CNNs), aiming at predicting cells' elastic modulus and constitutive equations from their deformations while passing through micro-constriction channels. In the present study, the computational fluid dynamics technology is used to generate a dataset within the range of the cell elastic modulus, incorporating three widely-used constitutive models that characterize the cellular mechanical behavior, i.e., the Mooney-Rivlin (M-R), Neo-Hookean (N-H), and Kelvin-Voigt (K-V) models. Utilizing this dataset, a multi-input convolutional neural network (MI-CNN) algorithm is developed by incorporating cellular deformation data as well as the time and positional information. This approach accurately predicts the cell elastic modulus, with a coefficient of determination R² of 0.999, a root mean square error of 0.218, and a mean absolute percentage error of 1.089%. The model consistently achieves high-precision predictions of the cellular elastic modulus with a maximum R² of 0.99, even when the stochastic noise is added to the simulated data. One significant feature of the present model is that it has the ability to effectively classify the three types of constitutive equations we applied. The model accurately and reliably predicts single-cell mechanical properties, showcasing a robust ability to generalize. We demonstrate that incorporating deformation features at multiple time points can enhance the algorithm's accuracy and generalization. This algorithm presents a possibility for high-throughput, highly automated, real-time, and precise characterization of single-cell mechanical properties.

Key words: cell deformation, single-cell mechanics, machine learning (ML), constitutive law, convolutional neural network (CNN)

中图分类号:

76D05
76Z99

. [J]. Applied Mathematics and Mechanics (English Edition), 2024, 45(11): 1857-1874.

Jiajie GONG, Xinyue LIU, Yancong ZHANG, Fengping ZHU, Guohui HU. Prediction of single cell mechanical properties in microchannels based on deep learning[J]. Applied Mathematics and Mechanics (English Edition), 2024, 45(11): 1857-1874.

图/表 12

参考文献 66

1	EL-ALI,J.,SORGER,P. K., andJENSEN,K. F.Cells on chips.nature,442(7101),403-411(2006)
2	FRITSCH,A.,HÖCKEL,M.,KIESSLING,T.,NNETU,K. D.,WETZEL,F.,ZINK,M., andKÄS,J. A.Are biomechanical changes necessary for tumour progression?.Nature Physics,6(10),730-732(2010)
3	BYUN,S.,SON,S.,AMODEI,D.,CERMAK,N.,SHAW,J.,KANG,J. H., andMANALIS,S. R.Characterizing deformability and surface friction of cancer cells.Proceedings of the National Academy of Sciences,110(19),7580-7585(2013)
4	ISERMANN,P., andLAMMERDING,J.Nuclear mechanics and mechanotransduction in health and disease.Current Biology,23(24),R1113-R1121(2013)
5	DI CARLO,D.A mechanical biomarker of cell state in medicine.Journal of Laboratory Automation,17(1),32-42(2012)
6	GUZNICZAK,E.,MOHAMMAD-ZADEH,M.,DEMPSEY,F.,JIMENEZ,M.,BOCK,H.,WHYTE,G., andBRIDLE,H.High-throughput assessment of mechanical properties of stem cell derived red blood cells, toward cellular downstream processing.Scientific Reports,7(1),14457(2017)
7	GUCK,J., andCHILVERS,E. R.Mechanics meets medicine.Science Translational Medicine,5(212),212fs41(2013)
8	TREPAT,X.,DENG,L.,AN,S. S.,NAVAJAS,D.,TSCHUMPERLIN,D. J.,GERTHOFFER,W. T., andFREDBERG,J. J.Universal physical responses to stretch in the living cell.nature,447(7144),592-595(2007)
9	DENG,L.,TREPAT,X.,BUTLER,J. P.,MILLET,E.,MORGAN,K. G.,WEITZ,D. A., andFREDBERG,J. J.Fast and slow dynamics of the cytoskeleton.Nature Materials,5(8),636-640(2006)
10	EKPENYONG,A. E.,WHYTE,G.,CHALUT,K.,PAGLIARA,S.,LAUTENSCHLÄGER,F.,FIDDLER,C., andGUCK,J.Viscoelastic properties of differentiating blood cells are fate-and function-dependent.PLoS ONE,7(9),e45237(2012)
11	LAUTENSCHLÄGER,F.,PASCHKE,S.,SCHINKINGER,S.,BRUEL,A.,BEIL,M., andGUCK,J.The regulatory role of cell mechanics for migration of differentiating myeloid cells.Proceedings of the National Academy of Sciences,106(37),15696-15701(2009)
12	TSE,H. T.,GOSSETT,D. R.,MOON,Y. S.,MASAELI,M.,SOHSMAN,M.,YING,Y., andDI CARLO,D.Quantitative diagnosis of malignant pleural effusions by single-cell mechanophenotyping.Science Translational Medicine,5(212),212ra163(2013)
13	SHAREI,A.,ZOLDAN,J.,ADAMO,A.,SIM,W. Y.,CHO,N.,JACKSON,E., andJENSEN,K. F.A vector-free microfluidic platform for intracellular delivery.Proceedings of the National Academy of Sciences,110(6),2082-2087(2013)
14	LEE,J.,SHAREI,A.,SIM,W. Y.,ADAMO,A.,LANGER,R.,JENSEN,K. F., andBAWENDI,M. G.Nonendocytic delivery of functional engineered nanoparticles into the cytoplasm of live cells using a novel, high-throughput microfluidic device.Nano Letters,12(12),6322-6327(2012)
15	CHAI,J., andSONG,Q.Multiple-protein detections of single-cells reveal cell-cell heterogeneity in human cells.IEEE Transactions on Biomedical Engineering,62(1),30-38(2014)
16	UNAL,M.,ALAPAN,Y.,JIA,H.,VARGA,A. G.,ANGELINO,K.,ASLAN,M., andGURKAN,U. A.Micro and nano-scale technologies for cell mechanics.Nanobiomedicine,1,1-5(2014)
17	HAO,Y.,CHENG,S.,TANAKA,Y.,HOSOKAWA,Y.,YALIKUN,Y., andLI,M.Mechanical properties of single cells: measurement methods and applications.Biotechnology Advances,45,107648(2020)
18	WU,P. H.,AROUSH,D. R. B.,ASNACIOS,A.,CHEN,W. C.,DOKUKIN,M. E.,DOSS,B. L., andWIRTZ,D.A comparison of methods to assess cell mechanical properties.Nature Methods,15,491-498(2018)
19	BENTO,D.,RODRIGUES,R. O.,FAUSTINO,V.,PINHO,D.,FERNANDES,C. S.,PEREIRA,A. I., andLIMA,R.Deformation of red blood cells, air bubbles, and droplets in microfluidic devices: flow visualizations and measurements.Micromachines,9(4),151(2018)
20	TOEPFNER,N.,HEROLD,C.,OTTO,O.,ROSENDAHL,P.,JACOBI,A.,KRÄTER,M.,STÄCHELE,J.,MENSCHNER,L.,HERBIG,M.,CIUFFREDA,L.,FORD-CARTWRIGHT,L.,GRZYBEK,M.,COSKUN,Ü.,REITHUBER,E.,GARRISS,G.,MELLROTH,P.,HENRIQUES-NORMARK,B.,TREGAY,N.,SUTTORP,M.,BORNHÄUSER,M.,CHILVERS,E. R.,BERNER,R., andGUCK,J.Detection of human disease conditions by single-cell morpho-rheological phenotyping of blood.eLife,7,e29213(2018)
21	XIE,J., andHU,G. H.Computational modelling of membrane gating in capsule translocation through microchannel with variable section.Microfluidics and Nanofluidics,25(2),17(2021)
22	ABKARIAN,M.,FAIVRE,M., andSTONE,H. A.High-speed microfluidic differential manometer for cellular-scale hydrodynamics.Proceedings of the National Academy of Sciences,103(3),538-542(2006)
23	BOW,H.,PIVKIN,I. V.,DIEZ-SILVA,M.,GOLDFLESS,S. J.,DAO,M.,NILES,J. C., andHAN,J.A microfabricated deformability-based flow cytometer with application to malaria.Lab on a Chip,11(6),1065-1073(2011)
24	GOSSETT,D. R.,TSE,H. T.,LEE,S. A.,YING,Y.,LINDGREN,A. G.,YANG,O. O., andDICARLO,D.Hydrodynamic stretching of single cells for large population mechanical phenotyping.Proceedings of the National Academy of Sciences,109(20),7630-7635(2012)
25	AI,J. F.,XIE,J., andHU,G. H.Numerical simulation of red blood cells deformation in microchannel under zero-net-mass-flux jet.Acta Physica Sinica,69(23),234701(2020)
26	LIU,X. Y.,AI,J. F.,XIE,J., andHU,G. H.Numerical study of opposed zero-net-mass-flow jet-induced erythrocyte mechanoporation.Applied Mathematics and Mechanics (English Edition),43(11),1763-1776(2022) doi: 10.1007/s10483-022-2931-6
27	MACQUEEN,L. A.,BUSCHMANN,M. D., andWERTHEIMER,M. R.Mechanical properties of mammalian cells in suspension measured by electro-deformation.Journal of Micromechanics and Microengineering,20(6),065007(2010)
28	BEECH,J. P.,HOLM,S. H.,ADOLFSSON,K., andTEGENFELDT,J. O.Sorting cells by size, shape and deformability.Lab on a Chip,12(6),1048-1051(2012)
29	OTTO,O.,ROSENDAHL,P.,MIETKE,A.,GOLFIERS,S.,HEROLD,C.,KLAUE,D., andGUCK,J.Real-time deformability cytometry: on-the-fly cell mechanical phenotyping.Nature Methods,12(3),199-202(2015)
30	ROSENDAHL,P.,PLAK,K.,JACOBI,A.,KRAETER,M.,TOEPFNER,N.,OTTO,O., andGUCK,J.Real-time fluorescence and deformability cytometry.Nature Methods,15(5),355-358(2018)
31	MIETKE,A.,OTTO,O.,GIRARDO,S.,ROSENDAHL,P.,TAUBENBERGER,A.,GOLFIERS,S., andFISCHER-FRIEDRICH,E.Extracting cell stiffness from real-time deformability cytometry: theory and experiment.Biophysical Journal,109(10),2023-2036(2015)
32	MOKBEL,M.,MOKBEL,D.,MIETKE,A.,TRABER,N.,GIRARDO,S.,OTTO,O., andALAND,S.Numerical simulation of real-time deformability cytometry to extract cell mechanical properties.ACS Biomaterials Science and Engineering,3(11),2962-2973(2017)
33	SARKER,I. H.Machine learning: algorithms, real-world applications and research directions.SN Computer Science,2(3),160(2021)
34	PRALJAK,N.,IRAM,S.,GOREKE,U.,SINGH,G.,HILL,A.,GURKAN,U. A., andHINCZEWSKI,M.Integrating deep learning with microfluidics for biophysical classification of sickle red blood cells adhered to laminin.PLoS Computational Biology,17(11),e1008946(2021)
35	HEIDARI,M.,LAKSHMIVARAHAN,S.,MIRNIAHARIKANDEHEI,S.,DANALA,G.,MARYADA,S. K. R.,LIU,H., andZHENG,B.Applying a random projection algorithm to optimize machine learning model for breast lesion classification.IEEE Transactions on Biomedical Engineering,68(9),2764-2775(2021)
36	TIAN,Y.,LIN,W.,QU,K.,WANG,Z., andZHU,X.Insights into cell classification based on combination of multiple cellular mechanical phenotypes by using machine learning algorithm.Journal of the Mechanical Behavior of Biomedical Materials,128,105097(2022)
37	PHILLIP,J. M.,HAN,K. S.,CHEN,W. C.,WIRTZ,D., andWU,P. H.A robust unsupervised machine-learning method to quantify the morphological heterogeneity of cells and nuclei.Nature Protocols,16(2),754-774(2021)
38	SONG,T. H.,SANCHEZ,V.,EIDALY,H., andRAJPOOT,N. M.Dual-channel active contour model for megakaryocytic cell segmentation in bone marrow trephine histology images.IEEE Transactions on Biomedical Engineering,64(12),2913-2923(2017)
39	HERBIG,M.,JACOBI,A.,WOBUS,M.,WEIDNER,H.,MIES,A.,KRÄTER,M.,OTTO,O.,THIEDE,C.,WEICKERT,M.,GÖTZE,K. S.,RAUNER,M.,HOFBAUER,L. C.,BORNHÄUSER,M.,GUCK,J.,ADER,M.,PLATZBECKER,U., andBALAIAN,E.Machine learning assisted real-time deformability cytometry of CD34+ cells allows to identify patients with myelodysplastic syndromes.Scientific Reports,12(1),870(2022)
40	ISLAM,S.,SHAH,V.,GIDDE,S. T. R.,HUTAPEA,P.,SONG,S. H.,PICONE,J., andKIM,A.A machine learning enabled wireless intracranial brain deformation sensing system.IEEE Transactions on Biomedical Engineering,67(12),3521-3530(2020)
41	LEE,S.,LUKAN,J.,BOYKO,T.,ZELENOVA,K.,MAKLED,B.,PARSEY,C., andDE,S.A deep learning model for burn depth classification using ultrasound imaging.Journal of the Mechanical Behavior of Biomedical Materials,125,104930(2022)
42	SHEN,S. C. Y.,FERNÁNDEZ,M. P.,TOZZI,G., andBUEHLER,M. J.Deep learning approach to assess damage mechanics of bone tissue.Journal of the Mechanical Behavior of Biomedical Materials,123,104761(2021)
43	KARNIADAKIS,G. E.,KEVREKIDIS,I. G.,LU,L.,PERDIKARIS,P.,WANG,S., andYANG,L.Physics-informed machine learning.Nature Reviews Physics,3(6),422-440(2021)
44	LIN,T.,WANG,Z.,LU,R.,WANG,W., andSUI,Y.Characterising mechanical properties of flowing microcapsules using a deep convolutional neural network.Advances in Applied Mathematics and Mechanics,14(1),79-100(2022)
45	LIN,T.,WANG,Z.,WANG,W., andSUI,Y.A neural network-based algorithm for high-throughput characterisation of viscoelastic properties of flowing microcapsules.Soft Matter,17(15),4027-4039(2021)
46	GUO,Z.,LIN,T.,JING,D.,WANG,W., andSUI,Y.A method for real-time mechanical characterisation of microcapsules.Biomechanics and Modeling in Mechanobiology,22(4),1209-1220(2023)
47	NGUYEN,D.,TAO,L.,YE,H., andLI,Y.Machine learning-based prediction for single-cell mechanics.Mechanics of Materials,180,104631(2023)
48	LIANG,L.,LIU,M., andSUN,W.A deep learning approach to estimate chemically-treated collagenous tissue nonlinear anisotropic stress-strain responses from microscopy images.Acta Biomaterialia,63,227-235(2017)
49	MARTÍNEZ-MARTÍNEZ,F.,RUPÉREZ-MORENO,M. J.,MARTíNEZ-SOBER,M.,SOLVES-LLORENS,J. A.,LORENTE,D.,SERRANO-LÓPEZ,A. J.,MARTÍNEZ-SANCHIS,S.,MONSERRAT,C., andMARTÍN-GUERRERO,J. D.A finite element-based machine learning approach for modeling the mechanical behavior of the breast tissues under compression in real-time.Computers in Biology and Medicine,90,116-124(2017)
50	XIAO,P.,HAQUE,E.,ZHANG,T.,DONG,X. N.,HUANG,Y., andWANG,X.Can DXA image-based deep learning model predict the anisotropic elastic behavior of trabecular bone?.Journal of the Mechanical Behavior of Biomedical Materials,124,104834(2021)
51	WANG, Z., LUO, W., GAO, L., and LI, M. Modeling the bottom-up filling of through silicon vias with different additives. 15th International Conference on Electronic Packaging Technology, IEEE, Chengdu (2014)
52	YANEN, W., SHENGMIN, W., YAN, X. T., YAO, C., and MING, Y. Computer simulation for bone scaffolds on account of fluid-solid coupling model. 2009 International Forum on Computer Science-Technology and Applications, IEEE, Chongqing (2009)
53	LIU,X.,GUI,N.,WU,H.,YANG,X.,TU,J., andJIANG,S.Numerical simulation of flow past stationary and oscillating deformable circles with fluid-structure interaction.Experimental and Computational Multiphase Flow,2,151-161(2020)
54	KALLIONTZIS,D.Fluid-structure interaction with ALE formulation and skeleton-based structural models.Journal of Fluids and Structures,110,103513(2022)
55	FOURNIER,J. B., andBARBETTA,C.Direct calculation from the stress tensor of the lateral surface tension of fluctuating fluid membranes.Physical Review Letters,100(7),078103(2008)
56	PENROSE,J. M. T., andSTAPLES,C. J.Implicit fluid-structure coupling for simulation of cardiovascular problems.International Journal for Numerical Methods in Fluids,40(3-4),467-478(2002)
57	WEI,X.,SANG,J.,TIAN,C.,SUN,L., andLIU,B.Different types of constitutive parameters red blood cell membrane based on machine learning and FEM.International Journal of Computational Methods,20(3),2250057(2023)
58	HAN,Y.,LIN,H.,DING,M.,LI,R., andSHI,T.Flow-induced translocation of vesicles through a narrow pore.Soft Matter,15(16),3307-3314(2019)
59	POZRIKIDIS,C.Modeling and Simulation of Capsules and Biological Cells,Chapman and Hall/CRC,New York(2003)
60	SKALAK,R.,TOZEREN,A.,ZARDA,R. P., andCHIEN,S.Strain energy function of red blood cell membranes.Biophysical Journal,13(3),245-264(1973)
61	BERGSTROM,J. S.Mechanics of Solid Polymers: Theory and Computational Modeling,William Andrew,New York(2015)
62	HOWELL,P.,KOZYREFF,G., andOCKENDON,J.Applied Solid Mechanics,Cambridge University Press,Cambridge(2009)
63	GREEN,A. E., andADKINS,J. E.Large Elastic Deformations,Oxford University Press,Oxford(1970)
64	KUZNETSOVA,T. G.,STARODUBTSEVA,M. N.,YEGORENKOV,N. I.,CHIZHIK,S. A., andZHDANOV,R. I.Atomic force microscopy probing of cell elasticity.Micron,38(8),824-833(2007)
65	SUZUKI,S.Topological structural analysis of digitized binary images by border following.Computer Vision, Graphics, and Image Processing,30(1),32-46(1985)
66	DIETTERICH, T. G. Ensemble methods in machine learning. International Workshop on Multiple Classifier Systems, Springer, Heidelberg, 1–15 (2000)

[1]	Jianhua QIN, Fei LIAO, Guodan DONG, Xiaolei YANG. Parallelization strategies for resolved simulations of fluid-structure-particle interactions[J]. Applied Mathematics and Mechanics (English Edition), 2024, 45(5): 857-872.
[2]	M. RAHMAN, M. TURKYILMAZOGLU, Z. MUSHTAQ. Effects of multiple shapes for steady flow with transformer oil+Fe₃O₄+TiO₂ between two stretchable rotating disks[J]. Applied Mathematics and Mechanics (English Edition), 2024, 45(2): 373-388.
[3]	H. OWHADI. Gaussian process hydrodynamics[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(7): 1175-1198.
[4]	A. V. ROŞCA, N. C. ROŞCA, I. POP. Three-dimensional mixed convection stagnation-point flow past a vertical surface with second-order slip velocity[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(4): 641-652.
[5]	Kunpeng WANG, Qingxiang LI, Yuhong DONG. Transport of dissolved oxygen at the sediment-water interface in the spanwise oscillating flow[J]. Applied Mathematics and Mechanics (English Edition), 2021, 42(4): 527-540.
[6]	S. NADEEM, S. AKHTAR, A. SALEEM. Peristaltic flow of a heated Jeffrey fluid inside an elliptic duct: streamline analysis[J]. Applied Mathematics and Mechanics (English Edition), 2021, 42(4): 583-592.
[7]	G. C. SHIT, S. MUKHERJEE. MHD graphene-polydimethylsiloxane Maxwell nanofluid flow in a squeezing channel with thermal radiation effects[J]. Applied Mathematics and Mechanics (English Edition), 2019, 40(9): 1269-1284.
[8]	Luyu SHEN, Changgen LU, Xiaoqing ZHU. Leading-edge receptivity of boundary layer to three-dimensional free-stream turbulence[J]. Applied Mathematics and Mechanics (English Edition), 2019, 40(6): 851-860.
[9]	Beiji SHI, Xiaolei YANG, Guodong JIN, Guowei HE, Shizhao WANG. Wall-modeling for large-eddy simulation of flows around an axisymmetric body using the diffuse-interface immersed boundary method[J]. Applied Mathematics and Mechanics (English Edition), 2019, 40(3): 305-320.
[10]	A. MAHDY. Simultaneous impacts of MHD and variable wall temperature on transient mixed Casson nanofluid flow in the stagnation point of rotating sphere[J]. Applied Mathematics and Mechanics (English Edition), 2018, 39(9): 1327-1340.
[11]	Hang XU, I. POP, Q. SUN. Fluid flow driven along microchannel by its upper stretching wall with electrokinetic effects[J]. Applied Mathematics and Mechanics (English Edition), 2018, 39(3): 395-408.
[12]	H. ASHRAF, A. M. SIDDIQUI, M. A. RANA. Fallopian tube assessment of the peristaltic-ciliary flow of a linearly viscous fluid in a finite narrow tube[J]. Applied Mathematics and Mechanics (English Edition), 2018, 39(3): 437-454.
[13]	Xiaodi WU, Fu CHEN, Huaping LIU. Combined immersed boundary method and multiple-relaxation-time lattice Boltzmann flux solver for numerical simulations of incompressible flows[J]. Applied Mathematics and Mechanics (English Edition), 2017, 38(12): 1679-1696.
[14]	Luyu SHEN, Changgen LU. Mechanism of three-dimensional boundary-layer receptivity[J]. Applied Mathematics and Mechanics (English Edition), 2017, 38(9): 1213-1224.
[15]	M. M. LARIMI, A. RAMIAR, A. A. RANJBAR. Numerical simulation of magnetic drug targeting with Eulerian-Lagrangian model and effect of viscosity modification due to diabetics[J]. Applied Mathematics and Mechanics (English Edition), 2016, 37(12): 1631-1646.