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

Graph generation techniques are increasingly being adopted for drugdiscovery. Previous graph generation approaches have utilized relatively smallmolecular building blocks such as atoms or simple cycles, limiting theireffectiveness to smaller molecules. Indeed, as we demonstrate, theirperformance degrades significantly for larger molecules. In this paper, wepropose a new hierarchical graph encoder-decoder that employs significantlylarger and more flexible graph motifs as basic building blocks. Our encoderproduces a multi-resolution representation for each molecule in afine-to-coarse fashion, from atoms to connected motifs. Each level integratesthe encoding of constituents below with the graph at that level. Ourautoregressive coarse-to-fine decoder adds one motif at a time, interleavingthe decision of selecting a new motif with the process of resolving itsattachments to the emerging molecule. We evaluate our model on multiplemolecule generation tasks, including polymers, and show that our modelsignificantly outperforms previous state-of-the-art baselines.

Hierarchical Generation of Molecular Graphs using Structural Motifs