1
|
Kokabi M, Tayyab M, Rather GM, Pournadali Khamseh A, Cheng D, DeMauro EP, Javanmard M. Integrating optical and electrical sensing with machine learning for advanced particle characterization. Biomed Microdevices 2024; 26:25. [PMID: 38780704 PMCID: PMC11116188 DOI: 10.1007/s10544-024-00707-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/15/2024] [Indexed: 05/25/2024]
Abstract
Particle classification plays a crucial role in various scientific and technological applications, such as differentiating between bacteria and viruses in healthcare applications or identifying and classifying cancer cells. This technique requires accurate and efficient analysis of particle properties. In this study, we investigated the integration of electrical and optical features through a multimodal approach for particle classification. Machine learning classifier algorithms were applied to evaluate the impact of combining these measurements. Our results demonstrate the superiority of the multimodal approach over analyzing electrical or optical features independently. We achieved an average test accuracy of 94.9% by integrating both modalities, compared to 66.4% for electrical features alone and 90.7% for optical features alone. This highlights the complementary nature of electrical and optical information and its potential for enhancing classification performance. By leveraging electrical sensing and optical imaging techniques, our multimodal approach provides deeper insights into particle properties and offers a more comprehensive understanding of complex biological systems.
Collapse
Affiliation(s)
- Mahtab Kokabi
- Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, 08854, USA
| | - Muhammad Tayyab
- Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, 08854, USA
| | - Gulam M Rather
- Rutgers Cancer Institute of New Jersey, Rutgers University, New Brunswick, NJ, 08901, USA
| | | | - Daniel Cheng
- Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, 08854, USA
| | - Edward P DeMauro
- Department of Mechanical and Aerospace Engineering, Rutgers University, Piscataway, NJ, 08854, USA
| | - Mehdi Javanmard
- Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, 08854, USA.
| |
Collapse
|
2
|
Tayyab M, Barrett D, van Riel G, Liu S, Reinius B, Scharfe C, Griffin P, Steinmetz LM, Javanmard M, Pelechano V. Digital assay for rapid electronic quantification of clinical pathogens using DNA nanoballs. SCIENCE ADVANCES 2023; 9:eadi4997. [PMID: 37672583 PMCID: PMC10482329 DOI: 10.1126/sciadv.adi4997] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/29/2023] [Accepted: 08/04/2023] [Indexed: 09/08/2023]
Abstract
Fast and accurate detection of nucleic acids is key for pathogen identification. Methods for DNA detection generally rely on fluorescent or colorimetric readout. The development of label-free assays decreases costs and test complexity. We present a novel method combining a one-pot isothermal generation of DNA nanoballs with their detection by electrical impedance. We modified loop-mediated isothermal amplification by using compaction oligonucleotides that self-assemble the amplified target into nanoballs. Next, we use capillary-driven flow to passively pass these nanoballs through a microfluidic impedance cytometer, thus enabling a fully compact system with no moving parts. The movement of individual nanoballs is detected by a change in impedance providing a quantized readout. This approach is flexible for the detection of DNA/RNA of numerous targets (severe acute respiratory syndrome coronavirus 2, HIV, β-lactamase gene, etc.), and we anticipate that its integration into a standalone device would provide an inexpensive (<$5), sensitive (10 target copies), and rapid test (<1 hour).
Collapse
Affiliation(s)
- Muhammad Tayyab
- Rutgers, The State University of New Jersey, New Brunswick, NJ, USA
| | - Donal Barrett
- SciLifeLab, Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Solna, Sweden
| | - Gijs van Riel
- SciLifeLab, Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Solna, Sweden
| | - Shujing Liu
- SciLifeLab, Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Solna, Sweden
- International Institute of Tea Industry Innovation for the Belt and Road, Nanjing Agricultural University, Nanjing 210095, China
| | - Björn Reinius
- Department of Medical Biochemistry and Biophysics, Karolinska Institutet, Solna, Sweden
| | | | - Peter Griffin
- Stanford Genome Technology Center, Stanford, CA, USA
| | - Lars M. Steinmetz
- Stanford Genome Technology Center, Stanford, CA, USA
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
| | - Mehdi Javanmard
- Rutgers, The State University of New Jersey, New Brunswick, NJ, USA
| | - Vicent Pelechano
- SciLifeLab, Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Solna, Sweden
| |
Collapse
|
3
|
Julian T, Tang T, Hosokawa Y, Yalikun Y. Machine learning implementation strategy in imaging and impedance flow cytometry. BIOMICROFLUIDICS 2023; 17:051506. [PMID: 37900052 PMCID: PMC10613093 DOI: 10.1063/5.0166595] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Accepted: 10/06/2023] [Indexed: 10/31/2023]
Abstract
Imaging and impedance flow cytometry is a label-free technique that has shown promise as a potential replacement for standard flow cytometry. This is due to its ability to provide rich information and archive high-throughput analysis. Recently, significant efforts have been made to leverage machine learning for processing the abundant data generated by those techniques, enabling rapid and accurate analysis. Harnessing the power of machine learning, imaging and impedance flow cytometry has demonstrated its capability to address various complex phenotyping scenarios. Herein, we present a comprehensive overview of the detailed strategies for implementing machine learning in imaging and impedance flow cytometry. We initiate the discussion by outlining the commonly employed setup to acquire the data (i.e., image or signal) from the cell. Subsequently, we delve into the necessary processes for extracting features from the acquired image or signal data. Finally, we discuss how these features can be utilized for cell phenotyping through the application of machine learning algorithms. Furthermore, we discuss the existing challenges and provide insights for future perspectives of intelligent imaging and impedance flow cytometry.
Collapse
Affiliation(s)
- Trisna Julian
- Division of Materials Science, Nara Institute of Science and Technology, 8916-5 Takayamacho, Ikoma, Nara 630-0192, Japan
| | - Tao Tang
- Department of Biomedical Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore 117583, Singapore
| | - Yoichiroh Hosokawa
- Division of Materials Science, Nara Institute of Science and Technology, 8916-5 Takayamacho, Ikoma, Nara 630-0192, Japan
| | | |
Collapse
|
4
|
Tang T, Julian T, Ma D, Yang Y, Li M, Hosokawa Y, Yalikun Y. A review on intelligent impedance cytometry systems: Development, applications and advances. Anal Chim Acta 2023; 1269:341424. [PMID: 37290859 DOI: 10.1016/j.aca.2023.341424] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Revised: 05/22/2023] [Accepted: 05/23/2023] [Indexed: 06/10/2023]
Abstract
Impedance cytometry is a well-established technique for counting and analyzing single cells, with several advantages, such as convenience, high throughput, and no labeling required. A typical experiment consists of the following steps: single-cell measurement, signal processing, data calibration, and particle subtype identification. At the beginning of this article, we compared commercial and self-developed options extensively and provided references for developing reliable detection systems, which are necessary for cell measurement. Then, a number of typical impedance metrics and their relationships to biophysical properties of cells were analyzed with respect to the impedance signal analysis. Given the rapid advances of intelligent impedance cytometry in the past decade, this article also discussed the development of representative machine learning-based approaches and systems, and their applications in data calibration and particle identification. Finally, the remaining challenges facing the field were summarized, and potential future directions for each step of impedance detection were discussed.
Collapse
Affiliation(s)
- Tao Tang
- Division of Materials Science, Nara Institute of Science and Technology, 8916-5 Takayamacho, Ikoma, Nara, 630-0192, Japan; Department of Biomedical Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583, Singapore
| | - Trisna Julian
- Division of Materials Science, Nara Institute of Science and Technology, 8916-5 Takayamacho, Ikoma, Nara, 630-0192, Japan
| | - Doudou Ma
- Center for Biosystems Dynamics Research (BDR), RIKEN, 1-3 Yamadaoka, Suita, Osaka, 565-0871, Japan
| | - Yang Yang
- Institute of Deep-Sea Science and Engineering, Chinese Academy of Sciences, Sanya, Hainan, 572000, PR China
| | - Ming Li
- School of Engineering, Macquarie University, Sydney, 2109, Australia
| | - Yoichiroh Hosokawa
- Division of Materials Science, Nara Institute of Science and Technology, 8916-5 Takayamacho, Ikoma, Nara, 630-0192, Japan
| | - Yaxiaer Yalikun
- Division of Materials Science, Nara Institute of Science and Technology, 8916-5 Takayamacho, Ikoma, Nara, 630-0192, Japan; Center for Biosystems Dynamics Research (BDR), RIKEN, 1-3 Yamadaoka, Suita, Osaka, 565-0871, Japan.
| |
Collapse
|
5
|
Purwidyantri A, Azinheiro S, García Roldán A, Jaegerova T, Vilaça A, Machado R, Cerqueira MF, Borme J, Domingues T, Martins M, Alpuim P, Prado M. Integrated Approach from Sample-to-Answer for Grapevine Varietal Identification on a Portable Graphene Sensor Chip. ACS Sens 2023; 8:640-654. [PMID: 36657739 PMCID: PMC9973367 DOI: 10.1021/acssensors.2c02090] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Accepted: 12/23/2022] [Indexed: 01/21/2023]
Abstract
Identifying grape varieties in wine, related products, and raw materials is of great interest for enology and to ensure its authenticity. However, these matrices' complexity and low DNA content make this analysis particularly challenging. Integrating DNA analysis with 2D materials, such as graphene, offers an advantageous pathway toward ultrasensitive DNA detection. Here, we show that monolayer graphene provides an optimal test bed for nucleic acid detection with single-base resolution. Graphene's ultrathinness creates a large surface area with quantum confinement in the perpendicular direction that, upon functionalization, provides multiple sites for DNA immobilization and efficient detection. Its highly conjugated electronic structure, high carrier mobility, zero-energy band gap with the associated gating effect, and chemical inertness explain graphene's superior performance. For the first time, we present a DNA-based analytic tool for grapevine varietal discrimination using an integrated portable biosensor based on a monolayer graphene field-effect transistor array. The system comprises a wafer-scale fabricated graphene chip operated under liquid gating and connected to a miniaturized electronic readout. The platform can distinguish closely related grapevine varieties, thanks to specific DNA probes immobilized on the sensor, demonstrating high specificity even for discriminating single-nucleotide polymorphisms, which is hard to achieve with a classical end-point polymerase chain reaction or quantitative polymerase chain reaction. The sensor was operated in ultralow DNA concentrations, with a dynamic range of 1 aM to 0.1 nM and an attomolar detection limit of ∼0.19 aM. The reported biosensor provides a promising way toward developing decentralized analytical tools for tracking wine authenticity at different points of the food value chain, enabling data transmission and contributing to the digitalization of the agro-food industry.
Collapse
Affiliation(s)
- Agnes Purwidyantri
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
| | - Sarah Azinheiro
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
- Department
of Analytical Chemistry, Nutrition and Food Science, School of Veterinary
Sciences, University of Santiago de Compostela, Campus of Lugo, Lugo27002, Spain
| | - Aitor García Roldán
- Department
of Analytical Chemistry, Nutrition and Food Science, School of Veterinary
Sciences, University of Santiago de Compostela, Campus of Lugo, Lugo27002, Spain
| | - Tereza Jaegerova
- Department
of Food Analysis and Nutrition, Faculty of Food and Biochemical Technology, University of Chemistry and Technology Prague, Prague 6, Prague166 28, Czech Republic
| | - Adriana Vilaça
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
| | - Rofer Machado
- Centre
of Chemistry, University of Minho, Campus de Gualtar, Braga4710-057, Portugal
| | - M. Fátima Cerqueira
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
- Center
of Physics of the Universities of Minho and Porto, University of Minho, Braga4710-057, Portugal
| | - Jérôme Borme
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
| | - Telma Domingues
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
- Center
of Physics of the Universities of Minho and Porto, University of Minho, Braga4710-057, Portugal
| | - Marco Martins
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
| | - Pedro Alpuim
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
- Center
of Physics of the Universities of Minho and Porto, University of Minho, Braga4710-057, Portugal
| | - Marta Prado
- International
Iberian Nanotechnology Laboratory, Braga4715-330, Portugal
| |
Collapse
|
6
|
Kokabi M, Sui J, Gandotra N, Pournadali Khamseh A, Scharfe C, Javanmard M. Nucleic Acid Quantification by Multi-Frequency Impedance Cytometry and Machine Learning. BIOSENSORS 2023; 13:bios13030316. [PMID: 36979528 PMCID: PMC10046493 DOI: 10.3390/bios13030316] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/11/2023] [Revised: 02/15/2023] [Accepted: 02/20/2023] [Indexed: 06/10/2023]
Abstract
Determining nucleic acid concentrations in a sample is an important step prior to proceeding with downstream analysis in molecular diagnostics. Given the need for testing DNA amounts and its purity in many samples, including in samples with very small input DNA, there is utility of novel machine learning approaches for accurate and high-throughput DNA quantification. Here, we demonstrated the ability of a neural network to predict DNA amounts coupled to paramagnetic beads. To this end, a custom-made microfluidic chip is applied to detect DNA molecules bound to beads by measuring the impedance peak response (IPR) at multiple frequencies. We leveraged electrical measurements including the frequency and imaginary and real parts of the peak intensity within a microfluidic channel as the input of deep learning models to predict DNA concentration. Specifically, 10 different deep learning architectures are examined. The results of the proposed regression model indicate that an R_Squared of 97% with a slope of 0.68 is achievable. Consequently, machine learning models can be a suitable, fast, and accurate method to measure nucleic acid concentration in a sample. The results presented in this study demonstrate the ability of the proposed neural network to use the information embedded in raw impedance data to predict the amount of DNA concentration.
Collapse
Affiliation(s)
- Mahtab Kokabi
- Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ 08854, USA
| | - Jianye Sui
- Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ 08854, USA
| | - Neeru Gandotra
- Department of Genetics, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520, USA
| | | | - Curt Scharfe
- Department of Genetics, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520, USA
| | - Mehdi Javanmard
- Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ 08854, USA
| |
Collapse
|
7
|
Marszalek Z, Duda K, Piwowar P, Stencel M, Zeglen T, Izydorczyk J. Load Estimation of Moving Passenger Cars Using Inductive-Loop Technology. SENSORS (BASEL, SWITZERLAND) 2023; 23:2063. [PMID: 36850661 PMCID: PMC9967455 DOI: 10.3390/s23042063] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Revised: 02/06/2023] [Accepted: 02/10/2023] [Indexed: 06/18/2023]
Abstract
Due to their lack of driving controllability, overweight vehicles are a big threat to road safety. The proposed method for a moving passenger car load estimation is capable of detecting an overweight vehicle, and thus it finds its application in road safety improvement. The weight of a car's load entering or leaving a considered zone, e.g., industrial facility, a state, etc., is also of concern in many applications, e.g., surveillance. Dedicated vehicle weight-in-motion measurement systems generally use expensive load sensors that also require deep intervention in the road while being installed and also are calibrated only for heavy trucks. In this paper, a vehicle magnetic profile (VMP) is used for defining a load parameter proportional to the passenger vehicle load. The usefulness of the proposed load parameter is experimentally demonstrated in field tests. The sensitivity of the VMP to the load change results from the fact that the higher load decreases the vehicle clearance value which in turn increases the VMP. It is also shown that a slim inductive-loop sensors allows the building of a load estimation system, with a maximum error around 30 kg, which allows approximate determination of the number of passengers in the car. The presented proof of concept extends the functionality of inductive loops, already installed in the road, for acquiring other traffic parameters, e.g., moving vehicle axle-to-axle distance measurement, to road safety and surveillance related applications.
Collapse
Affiliation(s)
- Zbigniew Marszalek
- Department of Measurement and Electronics, AGH University of Science and Technology, 30 Mickiewicz Avenue, 30-059 Krakow, Poland
| | - Krzysztof Duda
- Department of Measurement and Electronics, AGH University of Science and Technology, 30 Mickiewicz Avenue, 30-059 Krakow, Poland
| | - Piotr Piwowar
- Department of Measurement and Electronics, AGH University of Science and Technology, 30 Mickiewicz Avenue, 30-059 Krakow, Poland
| | - Marek Stencel
- Department of Measurement and Electronics, AGH University of Science and Technology, 30 Mickiewicz Avenue, 30-059 Krakow, Poland
| | - Tadeusz Zeglen
- Department of Measurement and Electronics, AGH University of Science and Technology, 30 Mickiewicz Avenue, 30-059 Krakow, Poland
| | - Jacek Izydorczyk
- Department of Telecommunications and Teleinformatic, Silesian University of Technology, 16 Akademicka, 44-100 Gliwice, Poland
| |
Collapse
|
8
|
Ashley BK, Sui J, Javanmard M, Hassan U. Antibody-functionalized aluminum oxide-coated particles targeting neutrophil receptors in a multifrequency microfluidic impedance cytometer. LAB ON A CHIP 2022; 22:3055-3066. [PMID: 35851596 PMCID: PMC9378602 DOI: 10.1039/d2lc00563h] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Personalized diagnostics of infectious diseases require monitoring disease progression due to their ever-changing physiological conditions and the multi-faceted organ system mechanisms involved in disease pathogenesis. In such instances, the recommended clinical strategies involve multiplexing data collection from critical biomarkers related to a patient's conditions along with longitudinal frequent patient monitoring. Numerous detection technologies exist both in research and commercial settings to monitor these conditions, however, they fail to provide biomarker multiplexing ability with design and data processing simplicity. For a recently conceived multiplexing biomarker modality, this work demonstrates the use of electrically sensitive microparticles targeting and identifying membrane receptors on leukocytes using a single detection source, with a high potential for multiplexing greater than any existing impedance-based single-detection scheme. Here, polystyrene microparticles are coated with varying thicknesses of metal oxides, which generate quantifiable impedance shifts when exposed to multifrequency electric fields depending on the metal oxide thickness. Using multifrequency impedance cytometry, these particles can be measured and differentiated rapidly across one coplanar electrode scheme. After surface-functionalizing particles with antibodies targeting CD11b and CD66b receptors, the particles are combined with isolated neutrophils to measure receptor expression. A combination of data analysis techniques including multivariate analysis, supervised machine learning, and unsupervised machine learning was able to accurately differentiate samples with up to 91% accuracy. This proof-of-concept study demonstrates the potential for these oxide-coated particles for enumerating specific leukocytes enabling multiplexing. Further, additional coating thicknesses or different metal oxide materials can enable a compendium of multiplexing targeting resource to be used to develop a high-multiplexing sensor for targeting membrane receptor expression.
Collapse
Affiliation(s)
- Brandon K Ashley
- Department of Biomedical Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA.
| | - Jianye Sui
- Department of Electrical and Computer Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA
| | - Mehdi Javanmard
- Department of Biomedical Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA.
- Department of Electrical and Computer Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA
| | - Umer Hassan
- Department of Biomedical Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA.
- Department of Electrical and Computer Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA
- Global Health Institute, Rutgers, The State University of New Jersey, New Brunswick, NJ, 08901, USA
| |
Collapse
|
9
|
Wu H, Saito Y, Yoshizaki G, Yoshiura Y, Ohnuki H, Endo H. Study on the development of carbon nanotube enhanced biosensor for gender determination of fish. SENSING AND BIO-SENSING RESEARCH 2022. [DOI: 10.1016/j.sbsr.2022.100474] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/25/2022] Open
|