Computational Biology
@ Comenius University in Bratislava

Vladimír Boža, Broňa Brejová, Tomáš Vinař. DeepNano: Deep recurrent neural networks for base calling in MinION nanopore reads. PLoS One, 12(6):e0178751. 2017.

Download preprint: not available

Download from publisher: http://dx.doi.org/10.1371/journal.pone.0178751

Related web page: http://compbio.fmph.uniba.sk/deepnano/

Bibliography entry: BibTeX

See also: early version

Abstract:

The MinION device by Oxford Nanopore produces very long reads (reads over 100 kBp
were reported); however it suffers from high sequencing error rate. We present an
open-source DNA base caller based on deep recurrent neural networks and show that
the accuracy of base calling is much dependent on the underlying software and can
be improved by considering modern machine learning methods. By employing
carefully crafted recurrent neural networks, our tool significantly improves base
calling accuracy on data from R7.3 version of the platform compared to the
default base caller supplied by the manufacturer. On R9 version, we achieve
results comparable to Nanonet base caller provided by Oxford Nanopore.
Availability of an open source tool with high base calling accuracy will be
useful for development of new applications of the MinION device, including
infectious disease detection and custom target enrichment during sequencing.