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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Even though deep neural networks (DNNs) achieve state-of-the-art results fora number of problems involving genomic data, getting DNNs to explain theirdecision-making process has been a major challenge due to their black-boxnature. One way to get DNNs to explain their reasoning for prediction is viaattribution methods which are assumed to highlight the parts of the input thatcontribute to the prediction the most. Given the existence of numerousattribution methods and a lack of quantitative results on the fidelity of thosemethods, selection of an attribution method for sequence-based tasks has beenmostly done qualitatively. In this work, we take a step towards identifying themost faithful attribution method by proposing a computational approach thatutilizes point mutations. Providing quantitative results on seven popularattribution methods, we find Layerwise Relevance Propagation (LRP) to be themost appropriate one for translation initiation, with LRP identifying twoimportant biological features for translation: the integrity of Kozak sequenceas well as the detrimental effects of premature stop codons.

Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data