Chiron: translating nanopore raw signal directly into nucleotide sequence using deep learning

Teng, Haotian; Cao, Minh Duc; Hall, Michael B.; Duarte, Tânia; Wang, Sheng; Coin, Lachlan

doi:10.1093/gigascience/giy037

Cited by 138 publications

(103 citation statements)

References 31 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…Basecaller Albacore Basecaller developed by Oxford Nanopore Technologies Inc. https://nanoporetech.com Chiron Establish end-to-end basecalling using a deep learning CNN+RNN+CTC structure (Teng et al, 2018) Metrichor Cloud-based basecaller that cannot be run locally https://nanoporetech.com Tombo Detection tool for modified nucleotides such as methylation https://nanoporetech.com Polishing Nanopolish HMM-based polishing tool using raw signal data of reads (Louis et al, 2016) Racon Polishing tool for contigs assembled by Canu (Koren et al, 2017) with raw long reads. (Vaser, Sovic, Nagarajan, & Sikic, 2017) Pilon Polishing tool for contigs assembled by Canu (Koren et al, 2017) with Illumina short reads.…”

Section: Software Description Referencementioning

confidence: 99%

“…Throughput of the system is greatly enhanced; for example, by the recent introduction of the PromethION system, where a single flow cell can yield 50-100 Gbp (typical yield of MinION system is 5-10 Gbp) and 24 flow cells can be run in parallel. Improvements in base-caller software from Hidden Markov Model (HMM) based methods to Recurrent Neural Network (RNN) based algorithms enhanced base-level accuracy by 2%-5% (Rang et al, 2018;Teng et al, 2018). In the following sections, we review each of the above points in detail.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Nanopore sequencing: Review of potential applications in functional genomics

2019

View full text Add to dashboard Cite

Molecular biology has been led by various measurement technologies, and increased throughput has developed omics analysis. The development of massively parallel sequencing technology has enabled access to fundamental molecular data and revealed genomic and transcriptomic signatures. Nanopore sequencers have driven such evolution to the next stage. Oxford Nanopore Technologies Inc. provides a new type of single molecule sequencer using protein nanopore that realizes direct sequencing without DNA synthesizing or amplification. This nanopore sequencer can sequence an ultra‐long read limited by the input nucleotide length, or can determine DNA/RNA modifications. Recently, many fields such as medicine, epidemiology, ecology, and education have benefited from this technology. In this review, we explain the features and functions of the nanopore sequencer, introduce various situations where it has been used as a critical technology, and expected future applications.

show abstract

Section: Software Description Referencementioning

confidence: 99%

mentioning

confidence: 99%

Nanopore sequencing: Review of potential applications in functional genomics

2019

View full text Add to dashboard Cite

show abstract

“…For example, BasecRAWller [5] puts the event segmentation step in a later stage after initial feature extraction by a RNN. Chiron [6] and recent ONT basecallers use a Connectionist Temporal Classification (CTC) module to avoid explicitly segmentation for base-calling from raw signals. With CTC, a variant length base sequence can be generated for a fixed-length signal window through output-space searching.…”

Section: Introductionmentioning

confidence: 99%

Nanopore base-calling from a perspective of instance segmentation

Zhang

Akdemir

Tremmel

et al. 2019

Preprint

View full text Add to dashboard Cite

Background Nanopore sequencing is a rapidly developing third-generation sequencing technology, which can generate long nucleotide reads of molecules within a portable device in real time. Through detecting the change of ion currency signals during a DNA/RNA fragment's pass through a nanopore, genotypes are determined. Currently, the accuracy of nanopore base-calling has a higher error rate than short-read base-calling. Through utilizing deep neural networks, the-state-of-the art nanopore base-callers achieve base-calling accuracy in a range from 85% to 95%. Result In this work, we proposed a novel base-calling approach from a perspective of instance segmentation. Different from the previous sequence labeling approaches, we formulated the base-calling problem as a multi-label segmentation task. Meanwhile, we proposed a refined U-net model which we call UR-net that can model sequential dependencies for a one-dimensional segmentation task. The experiment results show that the proposed base-caller URnano achieves competitive results compared to recently proposed CTC-featured base-caller Chiron, on the same amount of training and test data for in-domain evaluation. Our results show that formulating the base-calling problem as a one-dimensional segmentation task is a promising approach.

show abstract

“…Base callers such as DeepNano [27] and Chiron [28] apply a Neural Network model to transfer wave signal into DNA sequence. The most accurate base caller is Albacore, which is a closed source software developed by ONT.…”

Section: Oxford Nanopore Sequencing Technologymentioning

confidence: 99%

“…It is estimated that the rates of substitution, insertion and deletion in 2D nanopore sequences are 5.1%, 4.9% and 7.8%, respectively [26]. These rates are 7.5%, 6.5% and 8.6% in new 1D nanopore sequence [28].…”

Section: Oxford Nanopore Sequencing Technologymentioning

confidence: 99%

Investigation of repetitive sequences in the human genome

Shao¹

View full text Add to dashboard Cite

Repetitive sequences and genomic variations mediated by repetitive sequences remain a barrier to our understanding of the function and dynamics of the human genome.Only recently have high throughput short and long reads sequencing provided an opportunity to overcome these challenges. In this thesis, I investigate the distribution, evolution and polymorphism of two types of repeats: subtelomeric and inverted repeats. I also investigate two distinct aspects of genomic mutations related to these repetitive sequences: inversion polymorphisms, and structural variation in chromosome subtelomeric regions.In the first chapter, I provide an overview of our current knowledge, as well as gaps in our understanding of the structure of the human genome. I also provide an overview of the sequencing technologies I will use in this thesis.In the second chapter, I show the performance of inversion detection by short read sequencing. Next, I develop and apply an approach for using long read nanopore sequencing data to detect inversion polymorphism. I show that using long reads it is possible to detect inversions mediated by long inverted repeats which are invisible to paired-end short read sequencing.

show abstract

Chiron: translating nanopore raw signal directly into nucleotide sequence using deep learning

Cited by 138 publications

References 31 publications

Nanopore sequencing: Review of potential applications in functional genomics

Nanopore sequencing: Review of potential applications in functional genomics

Nanopore base-calling from a perspective of instance segmentation

Investigation of repetitive sequences in the human genome

Contact Info

Product

Resources

About