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/

Zendy Plus

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

Zendy Tools

Zendy Open

Properties of molecules are indicative of their functions and thus are usefulin many applications. With the advances of deep learning methods, computationalapproaches for predicting molecular properties are gaining increasing momentum.However, there lacks customized and advanced methods and comprehensive toolsfor this task currently. Here we develop a suite of comprehensive machinelearning methods and tools spanning different computational models, molecularrepresentations, and loss functions for molecular property prediction and drugdiscovery. Specifically, we represent molecules as both graphs and sequences.Built on these representations, we develop novel deep models for learning frommolecular graphs and sequences. In order to learn effectively from highlyimbalanced datasets, we develop advanced loss functions that optimize areasunder precision-recall curves. Altogether, our work not only serves as acomprehensive tool, but also contributes towards developing novel and advancedgraph and sequence learning methodologies. Results on both online and offlineantibiotics discovery and molecular property prediction tasks show that ourmethods achieve consistent improvements over prior methods. In particular, ourmethods achieve #1 ranking in terms of both ROC-AUC and PRC-AUC on the AI CuresOpen Challenge for drug discovery related to COVID-19. Our software is releasedas part of the MoleculeX library under AdvProp.

Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery