Deep Learning of Nanopore Sensing Signals Using a Bi-Path Network

Machine learning empowered next generation DNA sequencing: perspective and prospectus

The pursuit of ultra-rapid, cost-effective, and accurate DNA sequencing is a highly sought after aspect of personalized medicine development. With recent advancements, mainstream machine learning (ML) algorithms hold immense promise for high throughput DNA sequencing at the single nucleotide level. While ML has revolutionized multiple domains of nanoscience and nanotechnology, its implementation in DNA sequencing is still in its preliminary stages. ML-aided DNA sequencing is especially appealing, as ML has the potential to decipher complex patterns and extract knowledge from complex datasets. Herein, we present a holistic framework of ML-aided next-generation DNA sequencing with domain knowledge to set directions toward the development of artificially intelligent DNA sequencers. This perspective focuses on the current state-of-the-art ML-aided DNA sequencing, exploring the opportunities as well as the future challenges in this field. In addition, we provide our personal viewpoints on the critical issues that require attention in the context of ML-aided DNA sequencing.

A Robust Parallel Computing Data Extraction Framework for Nanopore Experiments

The success of a nanopore experiment relies not only on the quality of the experimental design but also on the performance of the analysis program utilized to decipher the ionic perturbations necessary for understanding the fundamental molecular intricacies. An event extraction framework is developed that leverages parallel computing, efficient memory management, and vectorization, yielding significant performance enhancement. The newly developed abf-ultra-simple function extracts key parameters from the header critical for the operation of open-seek-read-close data loading architecture running on multiple cores. This underpins the swift analysis of large files where an ≈ × 18 improvement is found for a 100 min-long file (≈4.5 GB) compared to the more traditional single (cell) array data loading method. The application is benchmarked against five other analysis platforms showcasing significant performance enhancement (>2 ×-1120 ×). The integrated provisions for batch analysis enable concurrently analyzing multiple files (vital for high-bandwidth experiments). Furthermore, the application is equipped with multi-level data fitting based on abrupt changes in the event waveform. The application condenses the extracted events to a single binary file improving data portability (e.g., 16 GB file with 28 182 events reduces to 47.9 MB-343 × size reduction) and enables a multitude of post-analysis extractions to be done efficiently.

Brownian Motion Paving the Way for Molecular Translocation in Nanopores

Tracing fast nanopore-translocating analytes requires a high-frequency measurement system that warrants a temporal resolution better than 1 µs. This constraint may practically shift the challenge from increasing the sampling bandwidth to dealing with the rapidly growing noise with frequencies typically above 10 kHz, potentially making it still uncertain if all translocation events are unambiguously captured. Here, a numerical simulation model is presented as an alternative to discern translocation events with different experimental settings including pore dimension, bias voltage, the charge state of the analyte, salt concentration, and electrolyte viscosity. The model allows for simultaneous analysis of forces exerting on a large analyte cohort along their individual trajectories; these forces are responsible for the analyte movement leading eventually to the nanopore translocation. Through tracing the analyte trajectories, the Brownian force is found to dominate the analyte movement in electrolytes until the last moment at which the electroosmotic force determines the final translocation act. The mean dwell time of analytes mimicking streptavidin decreases from ≈6 to ≈1 µs with increasing the bias voltage from ±100 to ±500 mV. The simulated translocation events qualitatively agree with the experimental data with streptavidin. The simulation model is also helpful for the design of new solid-state nanopore sensors.

Engineering Biological Nanopore Approaches toward Protein Sequencing

Biotechnological innovations have vastly improved the capacity to perform large-scale protein studies, while the methods we have for identifying and quantifying individual proteins are still inadequate to perform protein sequencing at the single-molecule level. Nanopore-inspired systems devoted to understanding how single molecules behave have been extensively developed for applications in genome sequencing. These nanopore systems are emerging as prominent tools for protein identification, detection, and analysis, suggesting realistic prospects for novel protein sequencing. This review summarizes recent advances in biological nanopore sensors toward protein sequencing, from the identification of individual amino acids to the controlled translocation of peptides and proteins, with attention focused on device and algorithm development and the delineation of molecular mechanisms with the aid of simulations. Specifically, the review aims to offer recommendations for the advancement of nanopore-based protein sequencing from an engineering perspective, highlighting the need for collaborative efforts across multiple disciplines. These efforts should include chemical conjugation, protein engineering, molecular simulation, machine-learning-assisted identification, and electronic device fabrication to enable practical implementation in real-world scenarios.

Portable nanopore-sequencing technology: Trends in development and applications

Sequencing technology is the most commonly used technology in molecular biology research and an essential pillar for the development and applications of molecular biology. Since 1977, when the first generation of sequencing technology opened the door to interpreting the genetic code, sequencing technology has been developing for three generations. It has applications in all aspects of life and scientific research, such as disease diagnosis, drug target discovery, pathological research, species protection, and SARS-CoV-2 detection. However, the first- and second-generation sequencing technology relied on fluorescence detection systems and DNA polymerization enzyme systems, which increased the cost of sequencing technology and limited its scope of applications. The third-generation sequencing technology performs PCR-free and single-molecule sequencing, but it still depends on the fluorescence detection device. To break through these limitations, researchers have made arduous efforts to develop a new advanced portable sequencing technology represented by nanopore sequencing. Nanopore technology has the advantages of small size and convenient portability, independent of biochemical reagents, and direct reading using physical methods. This paper reviews the research and development process of nanopore sequencing technology (NST) from the laboratory to commercially viable tools; discusses the main types of nanopore sequencing technologies and their various applications in solving a wide range of real-world problems. In addition, the paper collates the analysis tools necessary for performing different processing tasks in nanopore sequencing. Finally, we highlight the challenges of NST and its future research and application directions.

Procedural Data Processing for Single-Molecule Identification by Nanopore Sensors

Nanopores are promising single-molecule sensing devices that have been successfully used for DNA sequencing, protein identification, as well as virus/particles detection. It is important to understand and characterize the current pulses collected by nanopore sensors, which imply the associated information of the analytes, including the size, structure, and surface charge. Therefore, a signal processing program, based on the MATLAB platform, was designed to characterize the ionic current signals of nanopore measurements. In a movable data window, the selected current segment was analyzed by the adaptive thresholds and corrected by multi-functions to reduce the noise obstruction of pulse signals. Accordingly, a set of single molecular events was identified, and the abundant information of current signals with the dwell time, amplitude, and current pulse area was exported for quantitative analysis. The program contributes to the efficient and fast processing of nanopore signals with a high signal-to-noise ratio, which promotes the development of the nanopore sensing devices in various fields of diagnosis systems and precision medicine.

Electrical Conductance of Charged Nanopores

A nanopore's response to an electrical potential drop is characterized by its electrical conductance, . For the last two decades, it has been thought that at low electrolyte concentrations, , the conductance is concentration-independent such that . It has been recently demonstrated that surface charge regulation changes the dependency to , whereby the slope typically takes the values α = 1/3 or 1/2. However, experiments have observed slopes of 2/3 and 1 suggesting that additional mechanisms, such as convection and slip-lengths, appear. Here, we elucidate the interplay between three mechanisms: surface charge regulation, convection, and slip lengths. We show that the inclusion of convection does not change the slope, and when the effects of hydrodynamic slip are included, the slope is doubled. We show that when all effects are accounted for, α can take any value between 0 and 1 where the exact value of the slope depends on the material properties. This result is of utmost importance in designing any electro-kinetically driven nanofluidic system characterized by its conductance.

A Generalized Transformer-Based Pulse Detection Algorithm

Pulse-like signals are ubiquitous in the field of single molecule analysis, e.g., electrical or optical pulses caused by analyte translocations in nanopores. The primary challenge in processing pulse-like signals is to capture the pulses in noisy backgrounds, but current methods are subjectively based on a user-defined threshold for pulse recognition. Here, we propose a generalized machine-learning based method, named pulse detection transformer (PETR), for pulse detection. PETR determines the start and end time points of individual pulses, thereby singling out pulse segments in a time-sequential trace. It is objective without needing to specify any threshold. It provides a generalized interface for downstream algorithms for specific application scenarios. PETR is validated using both simulated and experimental nanopore translocation data. It returns a competitive performance in detecting pulses through assessing them with several standard metrics. Finally, the generalization nature of the PETR output is demonstrated using two representative algorithms for feature extraction.

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.