MSRCall: a multi-scale deep neural network to basecall Oxford Nanopore sequences

Abstract

Motivation MinION, a third-generation sequencer from Oxford Nanopore Technologies, is a portable device that can provide long-nucleotide read data in real-time. It primarily aims to deduce the makeup of nucleotide sequences from the ionic current signals generated when passing DNA/RNA fragments through nanopores charged with a voltage difference. To determine nucleotides from measured signals, a translation process known as basecalling is required. However, compared to NGS basecallers, the calling accuracy of MinION still needs to be improved. Results In this work, a simple but powerful neural network architecture called multi-scale recurrent caller (MSRCall) is proposed. MSRCall comprises a multi-scale structure, recurrent layers, a fusion block and a connectionist temporal classification decoder. To better identify both short-and long-range dependencies, the recurrent layer is redesigned to capture various time-scale features with a multi-scale structure. The results show that MSRCall outperforms other basecallers in terms of both read and consensus accuracies. Availability and implementation MSRCall is available at: https://github.com/d05943006/MSRCall. Supplementary information Supplementary data are available at Bioinformatics online.

RawHash: Enabling Fast and Accurate Real-Time Analysis of Raw Nanopore Signals for Large Genomes

“…One of the immediate steps after generating raw nanopore signals is their translation to their corresponding DNA bases as sequences of characters with a computationallyintensive step, basecalling. Basecalling approaches are usually computationally costly and consume significant energy as they use complex deep learning models [26][27][28][29][30][31][32][33][34][35][36][37][38]. Although we do not evaluate in this work, we expect that RawHash can be used as a low-cost filter to eliminate the reads that are unlikely to be useful in downstream analysis, which can reduce the overall workload of basecallers and further downstream analysis.…”

“…Deep learning models can successfully basecall genomes due to the developments and advancements in their architecture, which enables them to model and accurately recognize spatial characteristics in the raw data. Many basecallers have been proposed using modern deep learning-based architectures [28][29][30][31][32][33][34][35][36][37] However, the use of complex deep learning models makes basecalling slow and memory-hungry, bottlenecking all genomic analyses that depend on it [27]. Recent works focus on developing methods to speed up the basecalling process.…”

Environment Design and Exhibition Based on Convolutional Neural Network

“…Generally, they walk to the right, take shortcuts, and don't go back. This requires the space design to detain mobility and guidance, and reasonably arrange the space layout to arrange visitors' visits and guide people to stop [4][5].…”