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

Prediction of protein-ligand interactions (PLI) plays a crucial role in drugdiscovery as it guides the identification and optimization of molecules thateffectively bind to target proteins. Despite remarkable advances in deeplearning-based PLI prediction, the development of a versatile model capable ofaccurately scoring binding affinity and conducting efficient virtual screeningremains a challenge. The main obstacle in achieving this lies in the scarcityof experimental structure-affinity data, which limits the generalizationability of existing models. Here, we propose a viable solution to address thischallenge by introducing a novel data augmentation strategy combined with aphysics-informed graph neural network. The model showed significantimprovements in both scoring and screening, outperforming task-specific deeplearning models in various tests including derivative benchmarks, and notablyachieving results comparable to the state-of-the-art performance based ondistance likelihood learning. This demonstrates the potential of this approachto drug discovery.

PIGNet2: A Versatile Deep Learning-based Protein-Ligand Interaction Prediction Model for Binding Affinity Scoring and Virtual Screening