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

Despite an explosion in the number of experimentally determined, atomicallydetailed structures of biomolecules, many critical tasks in structural biologyremain data-limited. Whether performance in such tasks can be improved by usinglarge repositories of tangentially related structural data remains an openquestion. To address this question, we focused on a central problem in biology:predicting how proteins interact with one another---that is, which surfaces ofone protein bind to those of another protein. We built a training dataset, theDatabase of Interacting Protein Structures (DIPS), that contains biases but istwo orders of magnitude larger than those used previously. We found that thesebiases significantly degrade the performance of existing methods ongold-standard data. Hypothesizing that assumptions baked into the hand-craftedfeatures on which these methods depend were the source of the problem, wedeveloped the first end-to-end learning model for protein interface prediction,the Siamese Atomic Surfacelet Network (SASNet). Using only spatial coordinatesand identities of atoms, SASNet outperforms state-of-the-art methods trained ongold-standard structural data, even when trained on only 3% of our new dataset.Code and data available at https://github.com/drorlab/DIPS.

End-to-End Learning on 3D Protein Structure for Interface Prediction