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

Machine learning algorithms such as linear regression, SVM and neural networkhave played an increasingly important role in the process of scientificdiscovery. However, none of them is both interpretable and accurate onnonlinear datasets. Here we present contextual regression, a method that joinsthese two desirable properties together using a hybrid architecture of neuralnetwork embedding and dot product layer. We demonstrate its high predictionaccuracy and sensitivity through the task of predictive feature selection on asimulated dataset and the application of predicting open chromatin sites in thehuman genome. On the simulated data, our method achieved high fidelity recoveryof feature contributions under random noise levels up to 200%. On the openchromatin dataset, the application of our method not only outperformed thestate of the art method in terms of accuracy, but also unveiled two previouslyunfound open chromatin related histone marks. Our method can fill the blank ofaccurate and interpretable nonlinear modeling in scientific data mining tasks.

Contextual Regression: An Accurate and Conveniently Interpretable Nonlinear Model for Mining Discovery from Scientific Data