Title |
Chiron: Translating nanopore raw signal directly into nucleotide sequence using deep learning
|
---|---|
Published in |
Giga Science, April 2018
|
DOI | 10.1093/gigascience/giy037 |
Pubmed ID | |
Authors |
Haotian Teng, Minh Duc Cao, Michael B Hall, Tania Duarte, Sheng Wang, Lachlan J M Coin |
Abstract |
Sequencing by translocating DNA fragments through an array of nanopores is a rapidly maturing technology which 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: directly translating the raw signal to DNA sequence without the error-prone segmentation step. Trained with only a small set of 4000 reads, we show that our model provides state-of-the-art basecalling accuracy even on previously unseen species. Chiron achieves basecalling speeds of over 2000 bases per second using desktop computer graphics processing units. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United Kingdom | 15 | 20% |
Australia | 12 | 16% |
United States | 8 | 11% |
Hong Kong | 3 | 4% |
Canada | 3 | 4% |
Sweden | 2 | 3% |
Germany | 2 | 3% |
Netherlands | 2 | 3% |
New Zealand | 2 | 3% |
Other | 6 | 8% |
Unknown | 21 | 28% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Scientists | 42 | 55% |
Members of the public | 32 | 42% |
Science communicators (journalists, bloggers, editors) | 2 | 3% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 308 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 60 | 19% |
Researcher | 44 | 14% |
Student > Master | 42 | 14% |
Student > Bachelor | 37 | 12% |
Other | 14 | 5% |
Other | 41 | 13% |
Unknown | 70 | 23% |
Readers by discipline | Count | As % |
---|---|---|
Biochemistry, Genetics and Molecular Biology | 67 | 22% |
Agricultural and Biological Sciences | 59 | 19% |
Computer Science | 50 | 16% |
Engineering | 19 | 6% |
Medicine and Dentistry | 7 | 2% |
Other | 32 | 10% |
Unknown | 74 | 24% |