Real-Time, Direct Classification of Nanopore Signals with SquiggleNet

Abstract

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 identified bacterial species in a human respiratory meta genome sample.

Beyond sequencing: machine learning algorithms extract biology hidden in Nanopore signal data

“…and SquiggleNet [27]. The Readfish pipeline translates raw signals to nucleotide sequences in real time with guppy, aligns sequences to the reference, and then decides whether to eject the reads from the pores [25].…”

“…After clustering consistent reads and reference coordinates, UNCALLED filters out false positives and reports the best-supported location [26]. Using a neural-network framework, SquiggleNet uses a CNN and makes classification using a model that was learned on the reference training data [27]. These approaches have allowed the ReadUntil feature to classify target sequences in real-time.…”

baseLess: lightweight detection of sequences in raw MinION data

“…Efficiency decreases for larger and more repetitive genomes and re-indexing is required to attune the tool to a new target sequence. Moreover, accuracy was found to be low for short sequences [13]. Similarly to UNCALLED, SquiggleNet was designed for adaptive sampling [13].…”

Using Deep Learning for Gene Detection and Classification in Raw Nanopore Signals

“…NNs have also found applications in other parts of nanopore sequencing, such as selective sequencing. An example of a tool used to determine whether to eject the sequenced molecule or continue sequencing could be SquiggleNet [11], which uses a convolutional neural network learned from the reference organism’s sequencing data. The classifier then decides the sequenced segment’s location and whether to continue sequencing or eject the molecule.…”