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

The binding between proteins and ligands plays a crucial role in the realm ofdrug discovery. Previous deep learning approaches have shown promising resultsover traditional computationally intensive methods, but resulting in poorgeneralization due to limited supervised data. In this paper, we propose tolearn protein-ligand binding representation in a self-supervised learningmanner. Different from existing pre-training approaches which treat proteinsand ligands individually, we emphasize to discern the intricate bindingpatterns from fine-grained interactions. Specifically, this self-supervisedlearning problem is formulated as a prediction of the conclusive bindingcomplex structure given a pocket and ligand with a Transformer basedinteraction module, which naturally emulates the binding process. To ensure therepresentation of rich binding information, we introduce two pre-trainingtasks, i.e.~atomic pairwise distance map prediction and mask ligandreconstruction, which comprehensively model the fine-grained interactions fromboth structure and feature space. Extensive experiments have demonstrated thesuperiority of our method across various binding tasks, includingprotein-ligand affinity prediction, virtual screening and protein-liganddocking.

Protein-ligand binding representation learning from fine-grained interactions