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

One of the fundamental tasks in understanding genomics is the problem ofpredicting Transcription Factor Binding Sites (TFBSs). With more than hundredsof Transcription Factors (TFs) as labels, genomic-sequence based TFBSprediction is a challenging multi-label classification task. There are twomajor biological mechanisms for TF binding: (1) sequence-specific bindingpatterns on genomes known as "motifs" and (2) interactions among TFs known asco-binding effects. In this paper, we propose a novel deep architecture, thePrototype Matching Network (PMN) to mimic the TF binding mechanisms. Our PMNmodel automatically extracts prototypes ("motif"-like features) for each TFthrough a novel prototype-matching loss. Borrowing ideas from few-shot matchingmodels, we use the notion of support set of prototypes and an LSTM to learn howTFs interact and bind to genomic sequences. On a reference TFBS dataset with$2.1$ $million$ genomic sequences, PMN significantly outperforms baselines andvalidates our design choices empirically. To our knowledge, this is the firstdeep learning architecture that introduces prototype learning and considersTF-TF interactions for large-scale TFBS prediction. Not only is the proposedarchitecture accurate, but it also models the underlying biology.

Prototype Matching Networks for Large-Scale Multi-label Genomic Sequence Classification