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

Finely-tuned enzymatic pathways control cellular processes, and theirdysregulation can lead to disease. Creating predictive and interpretable modelsfor these pathways is challenging because of the complexity of the pathways andof the cellular and genomic contexts. Here we introduce Elektrum, a deeplearning framework which addresses these challenges with data-driven andbiophysically interpretable models for determining the kinetics of biochemicalsystems. First, it uses in vitro kinetic assays to rapidly hypothesize anensemble of high-quality Kinetically Interpretable Neural Networks (KINNs) thatpredict reaction rates. It then employs a novel transfer learning step, wherethe KINNs are inserted as intermediary layers into deeper convolutional neuralnetworks, fine-tuning the predictions for reaction-dependent in vivo outcomes.Elektrum makes effective use of the limited, but clean in vitro data and thecomplex, yet plentiful in vivo data that captures cellular context. We applyElektrum to predict CRISPR-Cas9 off-target editing probabilities anddemonstrate that Elektrum achieves state-of-the-art performance, regularizesneural network architectures, and maintains physical interpretability.

Interpretable neural architecture search and transfer learning for understanding CRISPR/Cas9 off-target enzymatic reactions