RT Journal Article
SR Electronic
T1 Real-Time, Direct Classification of Nanopore Signals with SquiggleNet
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.01.15.426907
DO 10.1101/2021.01.15.426907
A1 Yuwei Bao
A1 Jack Wadden
A1 John R. Erb-Downward
A1 Piyush Ranjan
A1 Robert P. Dickson
A1 David Blaauw
A1 Joshua D. Welch
YR 2021
UL http://biorxiv.org/content/early/2021/01/17/2021.01.15.426907.abstract
AB Single-molecule sequencers made by Oxford Nanopore provide results in real time as DNA passes through a nanopore and can eject a molecule after it has been partly sequenced. However, the computational challenge of deciding whether to keep or reject a molecule in real time has limited the application of this capability. We present SquiggleNet, the first deep learning model that can classify nanopore reads directly from their electrical signals. SquiggleNet operates faster than the DNA passes through the pore, allowing real-time classification and read ejection. When given the amount of sequencing data generated in one second, the classifier achieves significantly higher accuracy than base calling followed by sequence alignment. Our approach is also faster and requires an order of magnitude less memory than approaches based on alignment. SquiggleNet distinguished human from bacterial DNA with over 90% accuracy across test datasets from different flowcells and sample preparations, generalized to unseen species, and identifies unseen bacterial species in a human respiratory meta genome sample.Competing Interest StatementThe authors have declared no competing interest.