English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate genome sequencing can improve our understanding of biology and thegenetic basis of disease. The standard approach for generating DNA sequencesfrom PacBio instruments relies on HMM-based models. Here, we introduceDistilled DeepConsensus - a distilled transformer-encoder model for sequencecorrection, which improves upon the HMM-based methods with runtime constraintsin mind. Distilled DeepConsensus is 1.3x faster and 1.5x smaller than itslarger counterpart while improving the yield of high quality reads (Q30) overthe HMM-based method by 1.69x (vs. 1.73x for larger model). With improvedaccuracy of genomic sequences, Distilled DeepConsensus improves downstreamapplications of genomic sequence analysis such as reducing variant callingerrors by 39% (34% for larger model) and improving genome assembly quality by3.8% (4.2% for larger model). We show that the representations learned byDistilled DeepConsensus are similar between faster and slower models.

Knowledge distillation for fast and accurate DNA sequence correction