Show simple item record

dc.contributor.authorLv, X
dc.contributor.authorChen, Z
dc.contributor.authorLu, Y
dc.contributor.authorYang, Y
dc.date.accessioned2021-05-14T02:07:32Z
dc.date.available2021-05-14T02:07:32Z
dc.date.issued2020
dc.identifier.isbn9781728162157
dc.identifier.doi10.1109/BIBM49941.2020.9313290
dc.identifier.urihttp://hdl.handle.net/10072/404392
dc.description.abstractOxford Nanopore sequencing is fastly becoming an active field in genomics, and it's critical to basecall nucleotide sequences from the complex electrical signals. Many efforts have been devoted to developing new basecalling tools over the years. However, the basecalled reads still suffer from a high error rate and slow speed. Here, we developed an open-source basecalling method, CATCaller, by simultaneously capturing global context through Attention and modeling local dependencies through dynamic convolution. The method was shown to consistently outperform the ONT default basecaller Albacore, Guppy, and a recently developed attention-based method SACall in read accuracy. More importantly, our method is fast through a heterogeneously computational model to integrate both CPUs and GPUs. When compared to SACall, the method is nearly 4 times faster on a single GPU, and is highly scalable in parallelization with a further speedup of 3.3 on a four-GPU node.
dc.description.peerreviewedYes
dc.publisherIEEE
dc.relation.ispartofconferencename2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
dc.relation.ispartofconferencetitleProceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
dc.relation.ispartofdatefrom2020-12-16
dc.relation.ispartofdateto2020-12-19
dc.relation.ispartofpagefrom337
dc.relation.ispartofpageto342
dc.subject.fieldofresearchBiological Sciences
dc.subject.fieldofresearchcode06
dc.titleAn End-to-end Oxford Nanopore Basecaller Using Convolution-augmented Transformer
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationLv, X; Chen, Z; Lu, Y; Yang, Y, An End-to-end Oxford Nanopore Basecaller Using Convolution-augmented Transformer, Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020, 2020, pp. 337-342
dc.date.updated2021-05-14T02:05:41Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
gro.hasfulltextFull Text
gro.griffith.authorYang, Yuedong


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record