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

Haotian Teng; Minh Duc Cao; Michael B Hall; Tania Duarte; Sheng Wang; Lachlan J M Coin

doi:10.1093/gigascience/giy037

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

Haotian Teng, Minh Duc Cao, Michael B Hall, Tania Duarte, Sheng Wang, Lachlan J M Coin

Computer, Electrical and Mathematical Sciences and Engineering

Research output: Contribution to journal › Article › peer-review

102 Scopus citations

Abstract

Sequencing by translocating DNA fragments through an array of nanopores is a rapidly maturing technology that offers faster and cheaper sequencing than other approaches. However, accurately deciphering the DNA sequence from the noisy and complex electrical signal is challenging. Here, we report Chiron, the first deep learning model to achieve end-to-end basecalling and directly translate the raw signal to DNA sequence without the error-prone segmentation step. Trained with only a small set of 4,000 reads, we show that our model provides state-of-the-art basecalling accuracy, even on previously unseen species. Chiron achieves basecalling speeds of more than 2,000 bases per second using desktop computer graphics processing units.

Original language	English (US)
Journal	GigaScience
Volume	7
Issue number	5
DOIs	https://doi.org/10.1093/gigascience/giy037
State	Published - Apr 10 2018

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: We thank Jianhua Guo for contributing the DNA for the E. coli sample. We thank Arnold Bainomugisa for extracting DNA for the M. tuberculosis sample. We thank Sheng Wang and Han Qiao for the helpful discussion. We thank Jain et al. [14] for the open Human nanopore dataset.

Access to Document

10.1093/gigascience/giy037

https://repository.kaust.edu.sa/bitstream/10754/627895/1/giy037.pdf

Cite this

@article{934960501f3c44949a6722ae6645c611,

title = "Chiron: translating nanopore raw signal directly into nucleotide sequence using deep learning",

abstract = "Sequencing by translocating DNA fragments through an array of nanopores is a rapidly maturing technology that offers faster and cheaper sequencing than other approaches. However, accurately deciphering the DNA sequence from the noisy and complex electrical signal is challenging. Here, we report Chiron, the first deep learning model to achieve end-to-end basecalling and directly translate the raw signal to DNA sequence without the error-prone segmentation step. Trained with only a small set of 4,000 reads, we show that our model provides state-of-the-art basecalling accuracy, even on previously unseen species. Chiron achieves basecalling speeds of more than 2,000 bases per second using desktop computer graphics processing units.",

author = "Haotian Teng and Cao, {Minh Duc} and Hall, {Michael B} and Tania Duarte and Sheng Wang and Coin, {Lachlan J M}",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: We thank Jianhua Guo for contributing the DNA for the E. coli sample. We thank Arnold Bainomugisa for extracting DNA for the M. tuberculosis sample. We thank Sheng Wang and Han Qiao for the helpful discussion. We thank Jain et al. [14] for the open Human nanopore dataset.",

year = "2018",

month = apr,

day = "10",

doi = "10.1093/gigascience/giy037",

language = "English (US)",

volume = "7",

journal = "GigaScience",

issn = "2047-217X",

publisher = "Oxford University Press",

number = "5",

}

TY - JOUR

T1 - Chiron: translating nanopore raw signal directly into nucleotide sequence using deep learning

AU - Teng, Haotian

AU - Cao, Minh Duc

AU - Hall, Michael B

AU - Duarte, Tania

AU - Wang, Sheng

AU - Coin, Lachlan J M

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: We thank Jianhua Guo for contributing the DNA for the E. coli sample. We thank Arnold Bainomugisa for extracting DNA for the M. tuberculosis sample. We thank Sheng Wang and Han Qiao for the helpful discussion. We thank Jain et al. [14] for the open Human nanopore dataset.

PY - 2018/4/10

Y1 - 2018/4/10

N2 - Sequencing by translocating DNA fragments through an array of nanopores is a rapidly maturing technology that offers faster and cheaper sequencing than other approaches. However, accurately deciphering the DNA sequence from the noisy and complex electrical signal is challenging. Here, we report Chiron, the first deep learning model to achieve end-to-end basecalling and directly translate the raw signal to DNA sequence without the error-prone segmentation step. Trained with only a small set of 4,000 reads, we show that our model provides state-of-the-art basecalling accuracy, even on previously unseen species. Chiron achieves basecalling speeds of more than 2,000 bases per second using desktop computer graphics processing units.

AB - Sequencing by translocating DNA fragments through an array of nanopores is a rapidly maturing technology that offers faster and cheaper sequencing than other approaches. However, accurately deciphering the DNA sequence from the noisy and complex electrical signal is challenging. Here, we report Chiron, the first deep learning model to achieve end-to-end basecalling and directly translate the raw signal to DNA sequence without the error-prone segmentation step. Trained with only a small set of 4,000 reads, we show that our model provides state-of-the-art basecalling accuracy, even on previously unseen species. Chiron achieves basecalling speeds of more than 2,000 bases per second using desktop computer graphics processing units.

UR - http://hdl.handle.net/10754/627895

UR - https://academic.oup.com/gigascience/article/7/5/giy037/4966989#116612803

UR - http://www.scopus.com/inward/record.url?scp=85056709264&partnerID=8YFLogxK

U2 - 10.1093/gigascience/giy037

DO - 10.1093/gigascience/giy037

M3 - Article

C2 - 29648610

SN - 2047-217X

VL - 7

JO - GigaScience

JF - GigaScience

IS - 5

ER -

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

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this