Chiron: translating nanopore raw signal directly into nucleotide sequence using deep learning
Name:
giy037_giga-d-17-00305_original_submission.pdf
Size:
2.163Mb
Format:
PDF
Description:
Supplemental files
Name:
giy037_giga-d-17-00305_revision_1.pdf
Size:
1.620Mb
Format:
PDF
Description:
Supplemental files
Name:
giy037_giga-d-17-00305_revision_2.pdf
Size:
1.609Mb
Format:
PDF
Description:
Supplemental files
Name:
giy037_response_to_reviewer_comments_original_submission.pdf
Size:
22.64Kb
Format:
PDF
Description:
Supplemental files
Name:
giy037_response_to_reviewer_comments_revision_1.pdf
Size:
6.122Kb
Format:
PDF
Description:
Supplemental files
Name:
giy037_reviewer_1_report_(original_submission).pdf
Size:
23.67Kb
Format:
PDF
Description:
Supplemental files
Name:
giy037_reviewer_1_report_(revision_1).pdf
Size:
18.98Kb
Format:
PDF
Description:
Supplemental files
Name:
giy037_reviewer_2_report_(original_submission).pdf
Size:
21.10Kb
Format:
PDF
Description:
Supplemental files
Name:
giy037_reviewer_3_report_(revision_1).pdf
Size:
18.44Kb
Format:
PDF
Description:
Supplemental files
Type
ArticleKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionComputational Bioscience Research Center (CBRC)
Date
2018-04-10Online Publication Date
2018-04-10Print Publication Date
2018-05-01Permanent link to this record
http://hdl.handle.net/10754/627895
Metadata
Show full item recordAbstract
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.Citation
Teng H, Cao MD, Hall MB, Duarte T, Wang S, et al. (2018) Chiron: translating nanopore raw signal directly into nucleotide sequence using deep learning. GigaScience 7. Available: http://dx.doi.org/10.1093/gigascience/giy037.Sponsors
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.Publisher
Oxford University Press (OUP)Journal
GigaSciencePubMed ID
29648610Relations
Is Supplemented By:- [Software]
Title: haotianteng/Chiron: A basecaller for Oxford Nanopore Technologies' sequencers. Publication Date: 2017-05-07. github: haotianteng/Chiron Handle: 10754/667012
ae974a485f413a2113503eed53cd6c53
10.1093/gigascience/giy037
Scopus Count
Related articles
- Performance of neural network basecalling tools for Oxford Nanopore sequencing.
- Authors: Wick RR, Judd LM, Holt KE
- Issue date: 2019 Jun 24
- From squiggle to basepair: computational approaches for improving nanopore sequencing read accuracy.
- Authors: Rang FJ, Kloosterman WP, de Ridder J
- Issue date: 2018 Jul 13
- Nanopore basecalling from a perspective of instance segmentation.
- Authors: Zhang YZ, Akdemir A, Tremmel G, Imoto S, Miyano S, Shibuya T, Yamaguchi R
- Issue date: 2020 Apr 23
- NanoReviser: An Error-Correction Tool for Nanopore Sequencing Based on a Deep Learning Algorithm.
- Authors: Wang L, Qu L, Yang L, Wang Y, Zhu H
- Issue date: 2020
- DeepNano: Deep recurrent neural networks for base calling in MinION nanopore reads.
- Authors: Boža V, Brejová B, Vinař T
- Issue date: 2017