Discriminating single-bacterial shape using low-aspect-ratio pores

Immunological assay using a solid-state pore with a low limit of detection

Emerging infectious diseases, cancer, and other diseases are quickly tested mainly via immune reactions based on specific molecular recognition between antigens and antibodies. By changing the diameter of solid-state pores, biomolecules of various sizes can be rapidly detected at the single-molecule level. The combination of immunoreactions and solid-state pores paves the way for an efficient testing method with high specificity and sensitivity. The challenge in developing this method is achieving quantitative analysis using solid-state pores. Here, we demonstrate a method with a low limit of detection for testing tumor markers using a combination of immunoreactions and solid-state pore technology. Quantitative analysis of the mixing ratio of two and three beads with different diameters was achieved with an error rate of up to 4.7%. The hybrid solid-state pore and immunoreaction methods with prostate-specific antigen (PSA) and anti-PSA antibody-modified beads achieved a detection limit of 24.9 fM PSA in 30 min. The hybrid solid-state pore and immunoreaction enabled the rapid development of easy-to-use tests with lower limit of detection and greater throughput than commercially available immunoassay for point-of-care testing.

Detection of Glutamate Decarboxylase Antibodies and Simultaneous Multi-Molecular Translocation Exploration by Glass Nanopores

Glutamic acid decarboxylase antibody (GADAb) has emerged as a significant biomarker for clinical diagnosis and prognosis in type 1 diabetes (T1D). In this study, we investigated the potential utilization of glass capillary solid-state nanopores as a cost-effective and easily preparable platform for the detection of individual antigens, antibodies, and antigen-antibody complexes without necessitating any modifications to the nanopores. Our findings revealed notable characteristic variations in the translocation events of glutamic acid decarboxylase (GAD65) through nanopores under different voltage conditions, discovered that anomalous phenomenon of protein translocation events increasing with voltage may potentially be caused by the crowding of multiple proteins in the nanopores, and demonstrated that there are multiple components in the polyclonal antibodies (GADAb-poly). Furthermore, we achieved successful differentiation between GAD65, GADAb, and GADAb-GAD65 complexes. These results offer promising prospects for the development of a rapid and reliable GADAb detection method, which holds the potential to be applied in patient serum samples, thereby facilitating a label-free, cost-effective, and early diagnosis of type I diabetes.

Using novel micropore technology combined with artificial intelligence to differentiate Staphylococcus aureus and Staphylococcus epidermidis

Methods for identifying bacterial pathogens are broadly categorised into conventional culture-based microbiology, nucleic acid-based tests, and mass spectrometry. The conventional method requires several days to isolate and identify bacteria. Nucleic acid-based tests and mass spectrometry are relatively rapid and reliable, but they require trained technicians. Moreover, mass spectrometry requires expensive equipment. The development of a novel, inexpensive, and simple technique for identifying bacterial pathogens is needed. Through combining micropore technology and assembly machine learning, we developed a novel classifier whose receiver operating characteristic (ROC) curve showed an area under the ROC curve of 0.94, which rapidly differentiated between Staphylococcus aureus and Staphylococcus epidermidis in this proof-of-concept study. Morphologically similar bacteria belonging to an identical genus can be distinguished using our method, which requires no specific training, and may facilitate the diagnosis and treatment of patients with bacterial infections in remote areas and in developing countries.

Direct Determination of the Structure of Single Biopolymer Molecules Using Nanopore Sequencing

This review highlights operational principles, features, and modern aspects of the development of third-generation sequencing technology of biopolymers focusing on the nucleic acids analysis, namely the nanopore sequencing system. Basics of the method and technical solutions used for its realization are considered, from the first works showing the possibility of creation of these systems to the easy-to-handle procedure developed by Oxford Nanopore Technologies company. Moreover, this review focuses on applications, which were developed and realized using equipment developed by the Oxford Nanopore Technologies, including assembly of whole genomes, methagenomics, direct analysis of the presence of modified bases.

Single-molecule lipopolysaccharides identification and the interplay with biomolecules via nanopore readout

Lipopolysaccharides (LPS) are the major constituent on the cell envelope of all gram-negative bacteria. They are ubiquitous in air, and are toxic inflammatory stimulators for urinary disorders and sepsis. The reported optical, thermal, and electrochemical sensors via the intermolecular interplay of LPS with proteins and aptamers are generally complicated methods. We demonstrate the single-molecule nanopore approach for LPS identification in distinct bacteria as well as the serotypes discrimination. With a 4 nm nanopore, we achieve a detection limit of 10 ng/mL. Both the antibiotic polymyxin B (PMB) and DNA aptamer display specific binding to LPS. The identification of LPS in both human serum and tap water show good performance with nanopore platforms. Our work shows a highly-sensitive and easy-to-handle scheme for clinical and environmental biomarkers determination and provides a promising screening tool for early warning of contamination in water and medical supplies.

Solid-State Nanopore Distinguishes Ferritin and Apo-Ferritin with Identical Exteriors through Amplified Flexibility at Single-Molecule Level

Protein identification and discrimination at the single-molecule level are big challenges. Solid-state nanopores as a sensitive biosensor have been used for protein analysis, although it is difficult to discriminate proteins with similar structures in the traditional discrimination method based on the current blockage fraction. Here, we select ferritin and apo-ferritin as the model proteins that exhibit identical exterior and different interior structures and verify the practicability of their discrimination with flexibility features by the strategy of gradually decreasing the nanopore size. We show that the larger nanopore (relative to the protein size) has no obvious effect on discriminating two proteins. Then, the comparable-sized nanopore plays a key role in discriminating two proteins based on the dwell time and fraction distribution, and the conformational changes of both proteins are also studied with this nanopore. Finally, in the smaller nanopore, the protein molecules are trapped rather than translocated, where two proteins are obviously discriminated through the current fluctuation caused by the vibration of proteins. This strategy has potential in the discrimination of other important similar proteins.

High-precision rapid testing of omicron SARS-CoV-2 variants in clinical samples using AI-nanopore

A digital platform that can rapidly and accurately diagnose pathogenic viral variants, including SARS-CoV-2, will minimize pandemics, public anxiety, and economic losses. We recently reported an artificial intelligence (AI)-nanopore platform that enables testing for Wuhan SARS-CoV-2 with high sensitivity and specificity within five minutes. However, which parts of the virus are recognized by the platform are unknown. Similarly, whether the platform can detect SARS-CoV-2 variants or the presence of the virus in clinical samples needs further study. Here, we demonstrated the platform can distinguish SARS-CoV-2 variants. Further, it identified mutated Wuhan SARS-CoV-2 expressing spike proteins of the delta and omicron variants, indicating it discriminates spike proteins. Finally, we used the platform to identify omicron variants with a sensitivity and specificity of 100% and 94%, respectively, in saliva specimens from COVID-19 patients. Thus, our results demonstrate the AI-nanopore platform is an effective diagnostic tool for SARS-CoV-2 variants.

High Accuracy Protein Identification: Fusion of Solid-State Nanopore Sensing and Machine Learning

Proteins are arguably one of the most important class of biomarkers for health diagnostic purposes. Label-free solid-state nanopore sensing is a versatile technique for sensing and analyzing biomolecules such as proteins at single-molecule level. While molecular-level information on size, shape, and charge of proteins can be assessed by nanopores, the identification of proteins with comparable sizes remains a challenge. Here, solid-state nanopore sensing is combined with machine learning to address this challenge. The translocations of four similarly sized proteins is assessed using amplifiers with bandwidths (BWs) of 100 kHz and 10 MHz, the highest bandwidth reported for protein sensing, using nanopores fabricated in <10 nm thick silicon nitride membranes. F-values of up to 65.9% and 83.2% (without clustering of the protein signals) are achieved with 100 kHz and 10 MHz BW measurements, respectively, for identification of the four proteins. The accuracy of protein identification is further enhanced by classifying the signals into different clusters based on signal attributes, with F-value and specificity of up to 88.7% and 96.4%, respectively, for combinations of four proteins. The combined use of high bandwidth instruments, advanced clustering and machine learning methods allows label-free identification of proteins with high accuracy.

Study on the controllability of the fabrication of single-crystal silicon nanopores/nanoslits with a fast-stop ionic current-monitored TSWE method

The application of single-crystal silicon (SCS) nanopore structures in single-molecule-based analytical devices is an emerging approach for the separation and analysis of nanoparticles. The key challenge is to fabricate individual SCS nanopores with precise sizes in a controllable and reproducible way. This paper introduces a fast-stop ionic current-monitored three-step wet etching (TSWE) method for the controllable fabrication of SCS nanopores. Since the nanopore size has a quantitative relationship with the corresponding ionic current, it can be regulated by controlling the ionic current. Thanks to the precise current-monitored and self-stop system, an array of nanoslits with a feature size of only 3 nm was obtained, which is the smallest size ever reported using the TSWE method. Furthermore, by selecting different current jump ratios, individual nanopores of specific sizes were controllably prepared, and the smallest deviation from the theoretical value was 1.4 nm. DNA translocation measurement results revealed that the prepared SCS nanopores possessed the excellent potential to be applied in DNA sequencing.

Development of an Artificially Intelligent Nanopore for High-Throughput DNA Sequencing with a Machine-Learning-Aided Quantum-Tunneling Approach

Solid-state nanopore-based single-molecule DNA sequencing with quantum tunneling technology poses formidable challenges to achieve long-read sequencing and high-throughput analysis. Here, we propose a method for developing an artificially intelligent (AI) nanopore that does not require extraction of the signature transmission function for each nucleotide of the whole DNA strand by integrating supervised machine learning (ML) and transverse quantum transport technology with a graphene nanopore. The optimized ML model can predict the transmission function of all other nucleotides after training with data sets of all the orientations of any nucleotide inside the nanopore with a root-mean-square error (RMSE) of as low as 0.062. Further, up to 96.01% accuracy is achieved in classifying the unlabeled nucleotides with their transmission readouts. We envision that an AI nanopore can alleviate the experimental challenges of the quantum-tunneling method and pave the way for rapid and high-precision DNA sequencing by predicting their signature transmission functions.

Machine Learning Aided Interpretable Approach for Single Nucleotide-Based DNA Sequencing using a Model Nanopore

Solid-state nanopore-based electrical detection of DNA nucleotides with the quantum tunneling technique has emerged as a powerful strategy to be the next-generation sequencing technology. However, experimental complexity has been a foremost obstacle in achieving a more accurate high-throughput analysis with industrial scalability. Here, with one of the nucleotide training data sets of a model monolayer gold nanopore, we have predicted the transmission function for all other nucleotides with root-mean-square error scores as low as 0.12 using the optimized eXtreme Gradient Boosting Regression (XGBR) model. Further, the SHapley Additive exPlanations (SHAP) analysis helped in exploring the interpretability of the XGBR model prediction and revealed the complex relationship between the molecular properties of nucleotides and their transmission functions by both global and local interpretable explanations. Hence, experimental integration of our proposed machine-learning-assisted transmission function prediction method can offer a new direction for the realization of cheap, accurate, and ultrafast DNA sequencing.

Rapid and label-free identification of single foodborne pathogens using microfluidic pore sensors

Foodborne pathogenic microorganisms have become major threats that endanger human life and health. The current technology cannot perform rapid screening of foodborne pathogenic bacteria, and fail to timely control food safety risks. Here, we develop a novel microfluidic sensor for real-time and label-free bacteria classification at the single-cell level. Concretely, a low-aspect-ratio SiN micropore with PDMS coating was fabricated, which could significantly reduce the noise of the sensing system, and makes the microfluidic pore sensor sensitive to bacteria discrimination. The prepared SiN micropore equipped with the high temporal-spatial resolution was applied to observe bacterial translocation “events” and the current pulse signals could be obtained, which depend on the size, charge, and morphology of the target bacteria. According to the variation of the current pulse signals produced by different bacteria across the micropore, three common foodborne pathogens such as Salmonella enteric, Listeria monocytogenes, and Escherichia coli were identified. Due to convenience, rapidity, and accuracy, the label-free method we report here has great potential for the identification of diverse foodborne microorganisms at single-cell sensitivity.

Probing the Hepatitis B Virus E-Antigen with a Nanopore Sensor Based on Collisional Events Analysis

Real-time monitoring, simple operation, and cheaper methods for detecting immunological proteins hold the potential for a solid influence on proteomics and human biology, as they can promote the onset of timely diagnoses and adequate treatment protocols. In this work we present an exploratory study suggesting the applicability of resistive-pulse sensing technology in conjunction with the α-hemolysin (α-HL) protein nanopore, for the detection of the chronic hepatitis B virus (HBV) e-antigen (HBeAg). In this approach, the recognition between HBeAg and a purified monoclonal hepatitis B e antibody (Ab(HBeAg)) was detected via transient ionic current spikes generated by partial occlusions of the α-HL nanopore by protein aggregates electrophoretically driven toward the nanopore’s vestibule entrance. Despite the steric hindrance precluding antigen, antibody, or antigen–antibody complex capture inside the nanopore, their stochastic bumping with the nanopore generated clear transient blockade events. The subsequent analysis suggested the detection of protein subpopulations in solution, rendering the approach a potentially valuable label-free platform for the sensitive, submicromolar-scale screening of HBeAg targets.

Methodology to Detect Biological Particles Using a Biosensing Surface Integrated in Resistive Pulse Sensing

Resistive pulse sensing (RPS) is an analytical method that can be used to individually count particles from a small sample. RPS simply monitors the physical characteristics of particles, such as size, shape, and charge density, and the integration of RPS with biosensing is an attractive theme to detect biological particles such as virus and bacteria. In this report, a methodology of biosensing on RPS was investigated. Polydopamine (PD), an adhesive component of mussels, was used as the base material to create a sensing surface. PD adheres to most materials, such as noble metals, metal oxides, semiconductors, and polymers; as a result, PD is a versatile intermediate layer for the fabrication of a biosensing surface. As an example of a biological particle, human influenza A virus (H1N1 subtype) was used to monitor translocation of particles through the pore membrane. When virus-specific ligands (6'-sialyllactose) were immobilized on the pore surface, the translocation time of the virus particles was considerably extended. The detailed translocation data suggest that the viral particles were trapped on the sensing surface by specific interactions. In addition, virus translocation processes on different pore surfaces were distinguished using machine learning. The result shows that the simple and versatile PD-based biosensor surface design was effective. This advanced RPS measurement system could be a promising analytical technique.

Nanopore sensors for viral particle quantification: current progress and future prospects

Rapid, inexpensive, and laboratory-free diagnostic of viral pathogens is highly critical in controlling viral pandemics. In recent years, nanopore-based sensors have been employed to detect, identify, and classify virus particles. By tracing ionic current containing target molecules across nano-scale pores, nanopore sensors can recognize the target molecules at the single-molecule level. In the case of viruses, they enable discrimination of individual viruses and obtaining important information on the physical and chemical properties of viral particles. Despite classical benchtop virus detection methods, such as amplification techniques (e.g., PCR) or immunological assays (e.g., ELISA), that are mainly laboratory-based, expensive and time-consuming, nanopore-based sensing methods can enable low-cost and real-time point-of-care (PoC) and point-of-need (PoN) monitoring of target viruses. This review discusses the limitations of classical virus detection methods in PoN virus monitoring and then provides a comprehensive overview of nanopore sensing technology and its emerging applications in quantifying virus particles and classifying virus sub-types. Afterward, it discusses the recent progress in the field of nanopore sensing, including integrating nanopore sensors with microfabrication technology, microfluidics and artificial intelligence, which have been demonstrated to be promising in developing the next generation of low-cost and portable biosensors for the sensitive recognition of viruses and emerging pathogens.

A Guide to Signal Processing Algorithms for Nanopore Sensors

Nanopore technology holds great promise for a wide range of applications such as biomedical sensing, chemical detection, desalination, and energy conversion. For sensing performed in electrolytes in particular, abundant information about the translocating analytes is hidden in the fluctuating monitoring ionic current contributed from interactions between the analytes and the nanopore. Such ionic currents are inevitably affected by noise; hence, signal processing is an inseparable component of sensing in order to identify the hidden features in the signals and to analyze them. This Guide starts from untangling the signal processing flow and categorizing the various algorithms developed to extracting the useful information. By sorting the algorithms under Machine Learning (ML)-based versus non-ML-based, their underlying architectures and properties are systematically evaluated. For each category, the development tactics and features of the algorithms with implementation examples are discussed by referring to their common signal processing flow graphically summarized in a chart and by highlighting their key issues tabulated for clear comparison. How to get started with building up an ML-based algorithm is subsequently presented. The specific properties of the ML-based algorithms are then discussed in terms of learning strategy, performance evaluation, experimental repeatability and reliability, data preparation, and data utilization strategy. This Guide is concluded by outlining strategies and considerations for prospect algorithms.

Application of Micropore Device for Accurate, Easy, and Rapid Discrimination of Saccharomyces pastorianus from Dekkera spp

Traceability analysis, such as identification and discrimination of yeasts used for fermentation, is important for ensuring manufacturing efficiency and product safety during brewing. However, conventional methods based on morphological and physiological properties have disadvantages such as time consumption and low sensitivity. In this study, the resistive pulse method (RPM) was employed to discriminate between Saccharomyces pastorianus and Dekkera anomala and S. pastorianus and D. bruxellensis by measuring the ionic current response of cells flowing through a microsized pore. The height and shape of the pulse signal were used for the simultaneous measurement of the size, shape, and surface charge of individual cells. Accurate discrimination of S. pastorianus from Dekkera spp. was observed with a recall rate of 96.3 ± 0.8%. Furthermore, budding S. pastorianus was quantitatively detected by evaluating the shape of the waveform of the current ionic blockade. We showed a proof-of-concept demonstration of RPM for the detection of contamination of Dekkera spp. in S. pastorianus and for monitoring the fermentation of S. pastorianus through the quantitative detection of budding cells.

Deep Learning-Enhanced Nanopore Sensing of Single-Nanoparticle Translocation Dynamics

Noise is ubiquitous in real space that hinders detection of minute yet important signals in electrical sensors. Here, the authors report on a deep learning approach for denoising ionic current in resistive pulse sensing. Electrophoretically-driven translocation motions of single-nanoparticles in a nano-corrugated nanopore are detected. The noise is reduced by a convolutional auto-encoding neural network, designed to iteratively compare and minimize differences between a pair of waveforms via a gradient descent optimization. This denoising in a high-dimensional feature space is demonstrated to allow detection of the corrugation-derived wavy signals that cannot be identified in the raw curves nor after digital processing in frequency domains under the given noise floor, thereby enabled in-situ tracking to electrokinetic analysis of fast-moving single- and double-nanoparticles. The ability of the unlabeled learning to remove noise without compromising temporal resolution may be useful in solid-state nanopore sensing of protein structure and polynucleotide sequence.

Combining machine learning and nanopore construction creates an artificial intelligence nanopore for coronavirus detection

High-throughput, high-accuracy detection of emerging viruses allows for the control of disease outbreaks. Currently, reverse transcription-polymerase chain reaction (RT-PCR) is currently the most-widely used technology to diagnose the presence of SARS-CoV-2. However, RT-PCR requires the extraction of viral RNA from clinical specimens to obtain high sensitivity. Here, we report a method for detecting novel coronaviruses with high sensitivity by using nanopores together with artificial intelligence, a relatively simple procedure that does not require RNA extraction. Our final platform, which we call the artificially intelligent nanopore, consists of machine learning software on a server, a portable high-speed and high-precision current measuring instrument, and scalable, cost-effective semiconducting nanopore modules. We show that artificially intelligent nanopores are successful in accurately identifying four types of coronaviruses similar in size, HCoV-229E, SARS-CoV, MERS-CoV, and SARS-CoV-2. Detection of SARS-CoV-2 in saliva specimen is achieved with a sensitivity of 90% and specificity of 96% with a 5-minute measurement.

Rapid Discrimination of Extracellular Vesicles by Shape Distribution Analysis

A rapid and simple cancer detection method independent of cancer type is an important technology for cancer diagnosis. Although the expression profiles of biological molecules contained in cancer cell-derived extracellular vesicles (EVs) are considered candidates for discrimination indexes to identify any cancerous cells in the body, it takes a certain amount of time to examine these expression profiles. Here, we report the shape distributions of EVs suspended in a solution and the potential of these distributions as a discrimination index to discriminate cancer cells. Distribution analysis is achieved by low-aspect-ratio nanopore devices that enable us to rapidly analyze EV shapes individually in solution, and the present results reveal a dependence of EV shape distribution on the type of cells (cultured liver, breast, and colorectal cancer cells and cultured normal breast cells) secreting EVs. The findings in this study provide realizability and experimental basis for a simple method to discriminate several types of cancerous cells based on rapid analyses of EV shape distributions.

Effect of Electrolyte Concentration on Cell Sensing by Measuring Ionic Current Waveform through Micropores

Immunostaining has been widely used in cancer prognosis for the quantitative detection of cancer cells present in the bloodstream. However, conventional detection methods based on the target membrane protein expression exhibit the risk of missing cancer cells owing to variable protein expressions. In this study, the resistive pulse method (RPM) was employed to discriminate between cultured cancer cells (NCI-H1650) and T lymphoblastoid leukemia cells (CCRF-CEM) by measuring the ionic current response of cells flowing through a micro-space. The height and shape of a pulse signal were used for the simultaneous measurement of size, deformability, and surface charge of individual cells. An accurate discrimination of cancer cells could not be obtained using 1.0 × phosphate-buffered saline (PBS) as an electrolyte solution to compare the size measurements by a microscopic observation. However, an accurate discrimination of cancer cells with a discrimination error rate of 4.5 ± 0.5% was achieved using 0.5 × PBS containing 2.77% glucose as the electrolyte solution. The potential application of RPM for the accurate discrimination of cancer cells from leukocytes was demonstrated through the measurement of the individual cell size, deformability, and surface charge in a solution with a low electrolyte concentration.

Dielectric Coatings for Resistive Pulse Sensing Using Solid-State Pores

The present study reports on the systematic characterization of the effectiveness of dielectric coating to tailor capture-to-translocation dynamics of single particles in solid-state pores. We covered the surface of SiN_x membranes with SiO₂, HfO₂, Al₂O₃, TiO₂, or ZnO, which allowed us to change the ζ-potential at the pore wall, reflecting the isoelectric points of these coating materials. Resistive pulse measurements of negatively charged polystyrene beads elucidated more facile electrophoretic capture of the particles and slower translocation motions in the channel under more negative electric potential at the oxide surface. These findings provide a guide to engineer pore wall surface for optimizing the translocation dynamics for efficient sensing of particles and molecules.

Nanostructures for Biosensing, with a Brief Overview on Cancer Detection, IoT, and the Role of Machine Learning in Smart Biosensors

Biosensors are essential tools which have been traditionally used to monitor environmental pollution and detect the presence of toxic elements and biohazardous bacteria or virus in organic matter and biomolecules for clinical diagnostics. In the last couple of decades, the scientific community has witnessed their widespread application in the fields of military, health care, industrial process control, environmental monitoring, food-quality control, and microbiology. Biosensor technology has greatly evolved from in vitro studies based on the biosensing ability of organic beings to the highly sophisticated world of nanofabrication-enabled miniaturized biosensors. The incorporation of nanotechnology in the vast field of biosensing has led to the development of novel sensors and sensing mechanisms, as well as an increase in the sensitivity and performance of the existing biosensors. Additionally, the nanoscale dimension further assists the development of sensors for rapid and simple detection in vivo as well as the ability to probe single biomolecules and obtain critical information for their detection and analysis. However, the major drawbacks of this include, but are not limited to, potential toxicities associated with the unavoidable release of nanoparticles into the environment, miniaturization-induced unreliability, lack of automation, and difficulty of integrating the nanostructured-based biosensors, as well as unreliable transduction signals from these devices. Although the field of biosensors is vast, we intend to explore various nanotechnology-enabled biosensors as part of this review article and provide a brief description of their fundamental working principles and potential applications. The article aims to provide the reader a holistic overview of different nanostructures which have been used for biosensing purposes along with some specific applications in the field of cancer detection and the Internet of things (IoT), as well as a brief overview of machine-learning-based biosensing.

Digital Pathology Platform for Respiratory Tract Infection Diagnosis via Multiplex Single-Particle Detections

The variability of bioparticles remains a key barrier to realizing the competent potential of nanoscale detection into a digital diagnosis of an extraneous object that causes an infectious disease. Here, we report label-free virus identification based on machine-learning classification. Single virus particles were detected using nanopores, and resistive-pulse waveforms were analyzed multilaterally using artificial intelligence. In the discrimination, over 99% accuracy for five different virus species was demonstrated. This advance is accessed through the classification of virus-derived ionic current signal patterns reflecting their intrinsic physical properties in a high-dimensional feature space. Moreover, consideration of viral similarity based on the accuracies indicates the contributing factors in the recognitions. The present findings offer the prospect of a novel surveillance system applicable to detection of multiple viruses including new strains.

Advancing Biosensors with Machine Learning

Chemometrics play a critical role in biosensors-based detection, analysis, and diagnosis. Nowadays, as a branch of artificial intelligence (AI), machine learning (ML) have achieved impressive advances. However, novel advanced ML methods, especially deep learning, which is famous for image analysis, facial recognition, and speech recognition, has remained relatively elusive to the biosensor community. Herein, how ML can be beneficial to biosensors is systematically discussed. The advantages and drawbacks of most popular ML algorithms are summarized on the basis of sensing data analysis. Specially, deep learning methods such as convolutional neural network (CNN) and recurrent neural network (RNN) are emphasized. Diverse ML-assisted electrochemical biosensors, wearable electronics, SERS and other spectra-based biosensors, fluorescence biosensors and colorimetric biosensors are comprehensively discussed. Furthermore, biosensor networks and multibiosensor data fusion are introduced. This review will nicely bridge ML with biosensors, and greatly expand chemometrics for detection, analysis, and diagnosis.

Machine learning-driven electronic identifications of single pathogenic bacteria

A rapid method for screening pathogens can revolutionize health care by enabling infection control through medication before symptom. Here we report on label-free single-cell identifications of clinically-important pathogenic bacteria by using a polymer-integrated low thickness-to-diameter aspect ratio pore and machine learning-driven resistive pulse analyses. A high-spatiotemporal resolution of this electrical sensor enabled to observe galvanotactic response intrinsic to the microbes during their translocation. We demonstrated discrimination of the cellular motility via signal pattern classifications in a high-dimensional feature space. As the detection-to-decision can be completed within milliseconds, the present technique may be used for real-time screening of pathogenic bacteria for environmental and medical applications.

Analysis Method of the Ion Current-Time Waveform Obtained from Low Aspect Ratio Solid-state Nanopores

Low aspect ratio nanopores are expected to be applied to the detection of viruses and bacteria because of their high spatial resolution. Multiphysics simulations have revealed that the ion current-time waveform obtained from low aspect ratio nanopores contains information on not only the volume of viruses and bacteria, but also the structure, surface charge, and flow dynamics. Analysis using machine learning extracts information about these analytes from the ion current-time waveform. The combination of low aspect ratio nanopores, multiphysics simulation, and machine learning has made it possible to distinguish different types of viruses and bacteria with high accuracy.

Tailoring Dielectric Surface Charge via Atomic Layer Thickness

Channel surface property is a crucial factor that affects capture-to-translocation dynamics of single-particles in solid-state pores. Here, we show that atomically-thin dielectrics can be used to finely tune the pore wall surface potential. We isotopically coated alumina of atomically controlled thickness on a Si₃N₄ micropore. The surface zeta-potential in a buffer was found to decrease sharply by 1 nm thick deposition that served as a water-permeable ultra-thin sheet to modulate the effective charge density of the Al₂O₃/Si₃N₄ multilayer structure. Further thickening of the atomic layer enabled to control the zeta potential with a thickness at 3.4 mV/nm resolution. Accordingly, we observed concomitant enhancement in the capture rate and the translocation speed of negatively charged polymeric particles by virtue of the mitigated electroosmotic back flow in the functionalized pore channel. This simple method is widely applicable for tailoring the surface charge properties of essentially any sensors and devices working in aqueous media.

Combination of Single-Molecule Electrical Measurements and Machine Learning for the Identification of Single Biomolecules

The development of a next-generation DNA sequencer has provided a method for electrically measuring single molecules. Methods for electrically measuring one molecule are roughly divided into methods for measuring tunneling and ion currents. These methods enable identification of a single molecule of DNA, a RNA nucleotide, or a single protein based on current histograms. However, overlapping of current histograms of molecules with similar properties has been a major barrier to identifying single molecules with high accuracy. This barrier was broken by introducing machine learning. Combining single-molecule electrical measurement and machine learning enables high-precision identification of single molecules. Highly accurate discrimination has been demonstrated for DNA nucleotides, RNA nucleotides, amino acids, sugars, viruses, and bacteria. This combination enables quantitative evaluation of molecular recognition ability. Furthermore, a device structure suitable for high-precision identification has been designed. Combining single-molecule electrical measurement with machine learning enables digital analytical chemistry that can count certain types of molecules. Digital analytical chemistry enables comprehensive analysis of chemical reactions. This new analytical method will lead to the discovery of unknown or missed valuable molecules.

A methodology for characterising nanoparticle size and shape using nanopores

The discovery and characterisation of nanomaterials represents a multidisciplinary problem. Their properties and applications within biological, physical and medicinal sciences depend on their size, shape, concentration and surface charge. No single technology can currently measure all characteristics. Here we combine resistive pulse sensing with predictive logistic regression models, termed RPS-LRM, to rapidly characterise a nanomaterial's size, aspect ratio, shape and concentration when mixtures of nanorods and nanospheres are present in the same solution. We demonstrate that RPS-LRM can be applied to the characterisation of nanoparticles over a wide size range, and varying aspect ratios, and can distinguish between nanorods over nanospheres when they possess an aspect ratio grater then two. The RPS-LRM can rapidly measure the ratios of nanospheres to nanorods in solution within mixtures, regardless of their relative sizes and ratios i.e. many large nanospherical particles do not interfere with the characterisation of smaller nanorods. This was done with a 91% correct classification of nanospherical particles and 72% correct classification of nanorods even when the fraction of nanorods in solution is as low as 20%. The methodology here will enable the classification of nanomedicines, new nanomaterials and biological analytes in solution.

Polarization Induced Electro-Functionalization of Pore Walls: A Contactless Technology

This review summarizes recent advances in micro- and nanopore technologies with a focus on the functionalization of pores using a promising method named contactless electro-functionalization (CLEF). CLEF enables the localized grafting of electroactive entities onto the inner wall of a micro- or nano-sized pore in a solid-state silicon/silicon oxide membrane. A voltage or electrical current applied across the pore induces the surface functionalization by electroactive entities exclusively on the inside pore wall, which is a significant improvement over existing methods. CLEF's mechanism is based on the polarization of a sandwich-like silicon/silicon oxide membrane, creating electronic pathways between the core silicon and the electrolyte. Correlation between numerical simulations and experiments have validated this hypothesis. CLEF-induced micro- and nanopores functionalized with antibodies or oligonucleotides were successfully used for the detection and identification of cells and are promising sensitive biosensors. This technology could soon be successfully applied to planar configurations of pores, such as restrictions in microfluidic channels.

Peptide Nanocarriers for Detection of Heavy Metal Ions Using Resistive Pulse Sensing

The use of nanocarriers within resistive pulse sensing facilitates the detection and quantification of analytes. To date the field has been dominated by polyionic carriers or nanomaterials. Together they combine the recognition elements of a ligand with a stable support, facilitating the sample handling, analysis times, and multiplex detection. Here we develop the use of peptide-functionalized superparamagnetic nanocarriers to extract and quantify metal ions in solution. The interaction between nickel and the peptide ligand is measured as a change in translocation velocity of the carrier. The magnitude of change is proportional to the concentration of the metal ions in solution. Unlike DNA aptamers where a change in the tertiary structure and the folding of the polyanionic backbone influences the carrier velocity, the peptides here had a lower net charge under the assay conditions. To try and enhance the signal we engineered charged groups within the peptide to explore the effects on the signal. In all cases the metal ion binding dominated the velocity of the carrier. The assay was shown to work across 3 orders of magnitude and can detect Ni²⁺ in the presence of some other heavy metal ions. We demonstrate this by quantifying Ni²⁺ in both tap and pond water. The work allows for future multiplexed sensing strategies using both peptides and DNA aptamers in resistive pulse sensors.

Back-Side Polymer-Coated Solid-State Nanopore Sensors

We systematically investigated the influence of polymer coating on temporal resolution of solid-state nanopores. We fabricated a Si₃N₄ nanopore integrated with a polyimide sheet partially covering the substrate surface. Upon detecting the nanoparticles dispersed in an electrolyte buffer by ionic current measurements, we observed a larger resistive pulse height along with a faster current decay at the tails under larger coverage of the polymeric layer, thereby suggesting a prominent role of the water-touching Si₃N₄ thin film as a significant capacitor serving to retard the ionic current response to the ion blockade by fast translocation of particles through the nanopores. From this, we came up with back-side polymer-coated chip designs and demonstrated improved pore sensor temporal resolution by developing a nanopore with a thick polymethyl-methacrylate layer laminated on the bottom surface. The present findings may be useful in developing integrated solid-state nanopore sensors with embedded nanochannels and nanoelectrodes.

Electric field interference and bimodal particle translocation in nano-integrated multipores

Parallel integration of multiple channels is a fundamental strategy for high-throughput particle detection in solid-state nanopores wherein understanding and control of crosstalk is an important issue for the post resistive pulse analysis. Here we report on a prominent effect of cross-channel electric field interference on the ionic current blockade by nanoparticles in nano-spaced pore arrays in a thin Si3N4 membrane. We systematically investigated the variations in resistive pulse profiles in multipore systems of various inter-channel distances. Although each pore acted independently when they were formed at excessively far distances, we observed significant cross-pore electrostatic interactions under close-integration that led the multipores to virtually act as a single-pore of equivalent area. As a result of the interference, the resistive pulse height demonstrated bimodal distributions due to the pronounced particle trajectory-dependence of the ionic blockade effects. Most importantly, the overcrowded multi-channel structure was found to deliver significant crosstalk with serious degradation of the sensor sensitivity to particle sizes. The present results provide a guide to design multipore structures regarding the trade-off between the detection throughput and sensor sensitivity.

Identifying Single Particles in Air Using a 3D-Integrated Solid-State Pore

Solid-state micro- and nanopores are a versatile sensor platform capable of detecting single particles in electrolyte solution by cross-pore ionic current. Here we report on a use of this technology to identify airborne particulate matter. The detection concept lies in an electrophoretic control of air-floating particles captured in liquid to deliver them into a pore detector via microfluidic channels. We demonstrate resistive pulse measurements to machine-learning-based discriminations of intragranular contents of cypress and cedar pollens at a single-particle level. This all-electrical-sensor technique would pave a new venue toward real-time monitoring of single particles and molecules in air.

Volume discrimination of nanoparticles via electrical trapping using nanopores

Electrophoretic capture of an oversized object on a solid-state nanopore is a useful approach for single-particle analyses via post electrical and optical measurements. Here we report on nanoparticle discriminations by the volume through combining this nanopore trap method with the cross-membrane ionic current measurements. We investigated ion transport through a pore channel being partially occluded by an electrophoretically-drawn nanoparticle at the orifice. We found distinct difference in the amount of current blockage by particles of different sizes. Multiphysics simulations revealed dominant contribution of particle volume over the other properties. We also demonstrated single-particle discriminations of two different sizes in a mixture solution. The present results demonstrate that this electrical capturing is a promising technique to immobilize a target at a single particle level that concomitantly offer wealth of information concerning their volume.

Silicon substrate effects on ionic current blockade in solid-state nanopores

We investigated the roles of silicon substrate material compositions in ionic current blockade in solid-state nanopores. When detecting single nanoparticles using an ionic current in a Si3N4 nanopore supported on a doped silicon wafer, resistive pulses were found to be blunted significantly via signal retardation due to predominant contributions of large capacitance at the ultrathin membrane. Unexpectedly, in contrast, changing the substrate material to non-doped silicon led to the sharpening of the spike-like signal feature, suggesting a better temporal resolution of the cross-channel ionic current measurements by virtue of the thick intrinsic semiconductor layer that served to diminish the net chip capacitance. The present results suggest the importance of the choice of Si compositions regarding the capacitance effects to attain better spatiotemporal resolution in solid-state nanopore sensors.

Particle Capture in Solid-State Multipores

Utilization of multiple-channel structure is a promising way of accomplishing high-throughput detections of analytes in solid-state pore sensors. Here we report on systematic investigation of particle capture efficiency in Si₃N₄ multipore systems of various array configurations. We demonstrated enhanced detection throughput with increasing numbers of pore channels in a membrane. Meanwhile, we also observed significant contributions of the interchannel crosstalk in closely integrated multipores that tended to deteriorate throughput performance by causing shrinkage of the absorption zone via the interference-derived weakening of the electric field around the pore orifice. At the same time, the interference-derived electric field distributions were also found to diminish the electroosmotic contributions to the particle capture efficiency. The present findings can be useful in designing pore arrays with optimal throughput performance.

Selective detections of single-viruses using solid-state nanopores

Rapid diagnosis of flu before symptom onsets can revolutionize our health through diminishing a risk for serious complication as well as preventing infectious disease outbreak. Sensor sensitivity and selectivity are key to accomplish this goal as the number of virus is quite small at the early stage of infection. Here we report on label-free electrical diagnostics of influenza based on nanopore analytics that distinguishes individual virions by their distinct physical features. We accomplish selective resistive-pulse sensing of single flu virus having negative surface charges in a physiological media by exploiting electroosmotic flow to filter contaminants at the Si₃N₄ pore orifice. We demonstrate identifications of allotypes with 68% accuracy at the single-virus level via pattern classifications of the ionic current signatures. We also show that this discriminability becomes >95% under a binomial distribution theorem by ensembling the pulse data of >20 virions. This simple mechanism is versatile for point-of-care tests of a wide range of flu types.

Robust Ionic Current Sensor for Bacterial Cell Size Detection

Ionic current sensing methods are useful tools for detecting sub- to several-micron scale particles such as bacteria. However, conventional commercially available ionic current sensing devices are not suitable for on-site measurement use because of inherent limitations on their robustness. Here, we proposed a portable robust ionic current sensor (Robust-ICS) using a bridge circuit that offers a high signal-to-noise (S/N) ratio by suppressing background current. Because the Robust-ICS can tolerate increased noise in current sensing, a simple, lightweight electromagnetic shield can be used and measurements under large electromagnetic noise conditions can be made. The weight of the device was lowered below 4 kg and outdoor particle detection measurements were completed successfully. Accuracy of size detection of Staphylococcus aureus ( S. aureus) was equivalent to that obtained by SEM imaging.

Identification of Individual Bacterial Cells through the Intermolecular Interactions with Peptide-Functionalized Solid-State Pores

Bioinspired pore sensing for selective detection of flagellated bacteria was investigated. The Au micropore wall surface was modified with a synthetic peptide designed from toll-like receptor 5 (TLR5) to mimic the pathogen-recognition capability. We found that intermolecular interactions between the TLR5-derived recognition peptides and flagella induce ligand-specific perturbations in the translocation dynamics of Escherichia coli, which facilitated the discrimination between the wild-type and flagellin-deletion mutant (ΔfliC) by the resistive pulse patterns thereby demonstrating the sensing of bacteria at a single-cell level. These results provide a novel concept of utilizing weak intermolecular interactions as a recognition probes for single-cell microbial identification.