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

Identifying novel drug-target interactions (DTI) is a critical and ratelimiting step in drug discovery. While deep learning models have been proposedto accelerate the identification process, we show that state-of-the-art modelsfail to generalize to novel (i.e., never-before-seen) structures. We firstunveil the mechanisms responsible for this shortcoming, demonstrating howmodels rely on shortcuts that leverage the topology of the protein-ligandbipartite network, rather than learning the node features. Then, we introduceAI-Bind, a pipeline that combines network-based sampling strategies withunsupervised pre-training, allowing us to limit the annotation imbalance andimprove binding predictions for novel proteins and ligands. We illustrate thevalue of AI-Bind by predicting drugs and natural compounds with bindingaffinity to SARS-CoV-2 viral proteins and the associated human proteins. Wealso validate these predictions via docking simulations and comparison withrecent experimental evidence, and step up the process of interpreting machinelearning prediction of protein-ligand binding by identifying potential activebinding sites on the amino acid sequence. Overall, AI-Bind offers a powerfulhigh-throughput approach to identify drug-target combinations, with thepotential of becoming a powerful tool in drug discovery.

AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands