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

Machine learning and especially deep learning has had an increasing impact onmolecule and materials design. In particular, given the growing access to anabundance of high-quality small molecule data for generative modeling for drugdesign, results for drug discovery have been promising. However, for manyimportant classes of materials such as catalysts, antioxidants, andmetal-organic frameworks, such large datasets are not available. Such familiesof molecules with limited samples and structural similarities are especiallyprevalent for industrial applications. As is well-known, retraining and evenfine-tuning are challenging on such small datasets. Novel, practicallyapplicable molecules are most often derivatives of well-known molecules,suggesting approaches to addressing data scarcity. To address this problem, weintroduce $\textbf{STRIDE}$, a generative molecule workflow that generatesnovel molecules with an unconditional generative model guided by knownmolecules without any retraining. We generate molecules outside of the trainingdata from a highly specialized set of antioxidant molecules. Our generatedmolecules have on average 21.7% lower synthetic accessibility scores and alsoreduce ionization potential by 5.9% of generated molecules via guiding.

STRIDE: Structure-guided Generation for Inverse Design of Molecules