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

Motivation: Deep learning architectures have recently demonstrated theirpower in predicting DNA- and RNA-binding specificities. Existing methods fallinto three classes: Some are based on Convolutional Neural Networks (CNNs),others use Recurrent Neural Networks (RNNs), and others rely on hybridarchitectures combining CNNs and RNNs. However, based on existing studies it isstill unclear which deep learning architecture is achieving the bestperformance. Thus an in-depth analysis and evaluation of the different methodsis needed to fully evaluate their relative. Results: In this study, We presenta systematic exploration of various deep learning architectures for predictingDNA- and RNA-binding specificities. For this purpose, we present deepRAM, anend-to-end deep learning tool that provides an implementation of novel andpreviously proposed architectures; its fully automatic model selectionprocedure allows us to perform a fair and unbiased comparison of deep learningarchitectures. We find that an architecture that uses k-mer embedding torepresent the sequence, a convolutional layer and a recurrent layer,outperforms all other methods in terms of model accuracy. Our work providesguidelines that will assist the practitioner in choosing the best architecturefor the task at hand, and provides some insights on the differences between themodels learned by convolutional and recurrent networks. In particular, we findthat although recurrent networks improve model accuracy, this comes at theexpense of a loss in the interpretability of the features learned by the model.Availability and implementation: The source code for deepRAM is available athttps://github.com/MedChaabane/deepRAM

Comprehensive Evaluation of Deep Learning Architectures for Prediction of DNA/RNA Sequence Binding Specificities