Related papers: Dynamic Pooling Improves Nanopore Base Calling Acc…

Resistive pulse sensing is used to characterize and count single particles in solution moving through channels under an electric bias, with nanoscale pores providing enough spatial resolution for single-molecule identification and…

Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings hierarchically into a final graph representation. However,…

In unforeseen situations, such as nuclear power plant's or civilian radiation accidents, there is a need for effective and computationally inexpensive methods to determine the expression level of a selected gene panel, allowing for rough…

Very deep CNNs with small 3x3 kernels have recently been shown to achieve very strong performance as acoustic models in hybrid NN-HMM speech recognition systems. In this paper we investigate how to efficiently scale these models to larger…

The last decade, nanopores have emerged as a new and interesting tool for the study of biological macromolecules like proteins and DNA. While biological pores, especially alpha-hemolysin, have been promising for the detection of DNA, their…

Training of deep neural networks (DNNs) is a computationally intensive task and requires massive volumes of data transfer. Performing these operations with the conventional von Neumann architectures creates unmanageable time and power…

Nanopore sequencing, a next-generation sequencing technology, holds the potential to revolutionize multiple facets of life sciences, forensics, and healthcare. While previous research has focused on its technical intricacies and biomedical…

We propose a DNA sequencing scheme based on silicene nanopores. Using first principles theory, we compute the electrical properties of such pores in the absence and presence of nucleobases. Within a two-terminal geometry, we analyze the…

The ability to accurately represent sentences is central to language understanding. We describe a convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of sentences. The…

We demonstrate simultaneous measurements of DNA translocation into glass nanopores using ionic current detection and fluorescent imaging. We verify the correspondence between the passage of a single DNA molecule through the nanopore and the…

The task of estimating the fundamental frequency of a monophonic sound recording, also known as pitch tracking, is fundamental to audio processing with multiple applications in speech processing and music information retrieval. To date, the…

Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compress models. Although…

Pooling is a simple but essential layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation functions, while leaving the pooling layers with fewer options. We…

We report translocation experiments on double-strand DNA through a silicon oxide nanopore. Samples containing DNA fragments with seven different lengths between 2000 to 96000 basepairs have been electrophoretically driven through a 10 nm…

We investigate the ionic current modulation in DNA nanopore translocation setups by numerically solving the electrokinetic mean-field equations for an idealized model. Specifically, we study the dependence of the ionic current on the…

Nanopores in 2D materials are of significant interest in advanced membrane technologies aimed at the sensing and separation of ions and molecules. These applications necessitate 2D nanopores that are precise in size and shape, and abundant…

Basecalling is an essential step in nanopore sequencing analysis where the raw signals of nanopore sequencers are converted into nucleotide sequences, i.e., reads. State-of-the-art basecallers employ complex deep learning models to achieve…

DNA nanotechnology promises to provide controllable self-assembly on the nanoscale, allowing for the design of static structures, dynamic machines and computational architectures. In this article I review the state-of-the art of DNA…

Translocation event detection from raw nanopore current signals is a fundamental step in nanopore signal analysis. Traditional data analysis methods rely on user-defined parameters to extract event information, making the interpretation of…

Downsampling layers, including pooling and strided convolutions, are crucial components of the convolutional neural network architecture that determine both the granularity/scale of image feature analysis as well as the receptive field size…